modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-08-30 06:27:36
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 527
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-08-30 06:27:12
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
tmnam20/bert-base-multilingual-cased-vsfc-10
|
tmnam20
| 2024-01-16T06:39:30Z | 94 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:tmnam20/VieGLUE",
"base_model:google-bert/bert-base-multilingual-cased",
"base_model:finetune:google-bert/bert-base-multilingual-cased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-16T06:38:08Z |
---
language:
- en
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
- generated_from_trainer
datasets:
- tmnam20/VieGLUE
metrics:
- accuracy
model-index:
- name: bert-base-multilingual-cased-vsfc-10
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: tmnam20/VieGLUE/VSFC
type: tmnam20/VieGLUE
config: vsfc
split: validation
args: vsfc
metrics:
- name: Accuracy
type: accuracy
value: 0.930511686670878
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-base-multilingual-cased-vsfc-10
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the tmnam20/VieGLUE/VSFC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2383
- Accuracy: 0.9305
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 10
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.1857 | 1.4 | 500 | 0.2337 | 0.9305 |
| 0.1134 | 2.79 | 1000 | 0.2434 | 0.9330 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.2.0.dev20231203+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
|
Makhmud/whisper-uzbek
|
Makhmud
| 2024-01-16T06:38:57Z | 157 | 1 |
transformers
|
[
"transformers",
"safetensors",
"whisper",
"automatic-speech-recognition",
"hf-asr-leaderboard",
"generated_from_trainer",
"uz",
"dataset:mozilla-foundation/common_voice_11_0",
"base_model:openai/whisper-small",
"base_model:finetune:openai/whisper-small",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2024-01-16T05:54:30Z |
---
language:
- uz
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
model-index:
- name: Whisper Small Uz - Makhmud Jumanazarov
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Small Uz - Makhmud Jumanazarov
This model is a fine-tuned version of [openai/whisper](https://huggingface.co/openai/whisper) on the Common Voice 11.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3416
- Wer: 34.9285
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.4794 | 0.54 | 1000 | 0.4504 | 42.0722 |
| 0.313 | 1.08 | 2000 | 0.3821 | 38.9392 |
| 0.2948 | 1.62 | 3000 | 0.3468 | 35.4270 |
| 0.249 | 2.16 | 4000 | 0.3416 | 34.9285 |
### Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
tmnam20/bert-base-multilingual-cased-vsmec-1
|
tmnam20
| 2024-01-16T06:38:07Z | 94 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:tmnam20/VieGLUE",
"base_model:google-bert/bert-base-multilingual-cased",
"base_model:finetune:google-bert/bert-base-multilingual-cased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-16T05:59:41Z |
---
language:
- en
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
- generated_from_trainer
datasets:
- tmnam20/VieGLUE
metrics:
- accuracy
model-index:
- name: bert-base-multilingual-cased-vsmec-1
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: tmnam20/VieGLUE/VSMEC
type: tmnam20/VieGLUE
config: vsmec
split: validation
args: vsmec
metrics:
- name: Accuracy
type: accuracy
value: 0.48104956268221577
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-base-multilingual-cased-vsmec-1
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the tmnam20/VieGLUE/VSMEC dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3663
- Accuracy: 0.4810
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 1
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.1286 | 2.87 | 500 | 1.3592 | 0.4869 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.2.0.dev20231203+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
|
svenbl80/roberta-base-finetuned-new-mnli-run-1
|
svenbl80
| 2024-01-16T06:29:41Z | 46 | 0 |
transformers
|
[
"transformers",
"tf",
"tensorboard",
"roberta",
"text-classification",
"generated_from_keras_callback",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-15T23:58:29Z |
---
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: svenbl80/roberta-base-finetuned-new-mnli-run-1
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# svenbl80/roberta-base-finetuned-new-mnli-run-1
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0248
- Validation Loss: 0.7357
- Train Accuracy: 0.8661
- Epoch: 9
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 245430, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 0.4558 | 0.3972 | 0.8495 | 0 |
| 0.3309 | 0.3834 | 0.8520 | 1 |
| 0.2465 | 0.4150 | 0.8627 | 2 |
| 0.1784 | 0.4412 | 0.8670 | 3 |
| 0.1288 | 0.4816 | 0.8626 | 4 |
| 0.0926 | 0.5470 | 0.8647 | 5 |
| 0.0666 | 0.5634 | 0.8669 | 6 |
| 0.0477 | 0.6574 | 0.8648 | 7 |
| 0.0345 | 0.6919 | 0.8641 | 8 |
| 0.0248 | 0.7357 | 0.8661 | 9 |
### Framework versions
- Transformers 4.28.0
- TensorFlow 2.9.1
- Datasets 2.15.0
- Tokenizers 0.13.3
|
OpenDILabCommunity/PongNoFrameskip-v4-EfficientZero
|
OpenDILabCommunity
| 2024-01-16T06:26:44Z | 0 | 0 |
pytorch
|
[
"pytorch",
"deep-reinforcement-learning",
"reinforcement-learning",
"DI-engine",
"PongNoFrameskip-v4",
"en",
"arxiv:2310.08348",
"license:apache-2.0",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-04T20:16:58Z |
---
language: en
license: apache-2.0
library_name: pytorch
tags:
- deep-reinforcement-learning
- reinforcement-learning
- DI-engine
- PongNoFrameskip-v4
benchmark_name: OpenAI/Gym/Atari
task_name: PongNoFrameskip-v4
pipeline_tag: reinforcement-learning
model-index:
- name: EfficientZero
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PongNoFrameskip-v4
type: PongNoFrameskip-v4
metrics:
- type: mean_reward
value: 20.4 +/- 0.66
name: mean_reward
---
# Play **PongNoFrameskip-v4** with **EfficientZero** Policy
## Model Description
<!-- Provide a longer summary of what this model is. -->
This implementation applies **EfficientZero** to the OpenAI/Gym/Atari **PongNoFrameskip-v4** environment using [LightZero](https://github.com/opendilab/LightZero) and [DI-engine](https://github.com/opendilab/di-engine).
**LightZero** is an efficient, easy-to-understand open-source toolkit that merges Monte Carlo Tree Search (MCTS) with Deep Reinforcement Learning (RL), simplifying their integration for developers and researchers. More details are in paper [LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios](https://huggingface.co/papers/2310.08348).
## Model Usage
### Install the Dependencies
<details close>
<summary>(Click for Details)</summary>
```shell
# install huggingface_ding
git clone https://github.com/opendilab/huggingface_ding.git
pip3 install -e ./huggingface_ding/
# install environment dependencies if needed
pip3 install DI-engine[common_env,video]
pip3 install LightZero
```
</details>
### Git Clone from Huggingface and Run the Model
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from lzero.agent import EfficientZeroAgent
from ding.config import Config
from easydict import EasyDict
import torch
# Pull model from files which are git cloned from huggingface
policy_state_dict = torch.load("pytorch_model.bin", map_location=torch.device("cpu"))
cfg = EasyDict(Config.file_to_dict("policy_config.py").cfg_dict)
# Instantiate the agent
agent = EfficientZeroAgent(
env_id="PongNoFrameskip-v4", exp_name="PongNoFrameskip-v4-EfficientZero", cfg=cfg.exp_config, policy_state_dict=policy_state_dict
)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
### Run Model by Using Huggingface_ding
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from lzero.agent import EfficientZeroAgent
from huggingface_ding import pull_model_from_hub
# Pull model from Hugggingface hub
policy_state_dict, cfg = pull_model_from_hub(repo_id="OpenDILabCommunity/PongNoFrameskip-v4-EfficientZero")
# Instantiate the agent
agent = EfficientZeroAgent(
env_id="PongNoFrameskip-v4", exp_name="PongNoFrameskip-v4-EfficientZero", cfg=cfg.exp_config, policy_state_dict=policy_state_dict
)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
## Model Training
### Train the Model and Push to Huggingface_hub
<details close>
<summary>(Click for Details)</summary>
```shell
#Training Your Own Agent
python3 -u train.py
```
**train.py**
```python
from lzero.agent import EfficientZeroAgent
from huggingface_ding import push_model_to_hub
# Instantiate the agent
agent = EfficientZeroAgent(env_id="PongNoFrameskip-v4", exp_name="PongNoFrameskip-v4-EfficientZero")
# Train the agent
return_ = agent.train(step=int(2000000))
# Push model to huggingface hub
push_model_to_hub(
agent=agent.best,
env_name="OpenAI/Gym/Atari",
task_name="PongNoFrameskip-v4",
algo_name="EfficientZero",
github_repo_url="https://github.com/opendilab/LightZero",
github_doc_model_url=None,
github_doc_env_url=None,
installation_guide='''
pip3 install DI-engine[common_env,video]
pip3 install LightZero
''',
usage_file_by_git_clone="./efficientzero/pong_efficientzero_deploy.py",
usage_file_by_huggingface_ding="./efficientzero/pong_efficientzero_download.py",
train_file="./efficientzero/pong_efficientzero.py",
repo_id="OpenDILabCommunity/PongNoFrameskip-v4-EfficientZero",
platform_info="[LightZero](https://github.com/opendilab/LightZero) and [DI-engine](https://github.com/opendilab/di-engine)",
model_description="**LightZero** is an efficient, easy-to-understand open-source toolkit that merges Monte Carlo Tree Search (MCTS) with Deep Reinforcement Learning (RL), simplifying their integration for developers and researchers. More details are in paper [LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios](https://huggingface.co/papers/2310.08348).",
create_repo=False
)
```
</details>
**Configuration**
<details close>
<summary>(Click for Details)</summary>
```python
exp_config = {
'main_config': {
'exp_name': 'PongNoFrameskip-v4-EfficientZero',
'seed': 0,
'env': {
'env_id': 'PongNoFrameskip-v4',
'env_name': 'PongNoFrameskip-v4',
'obs_shape': [4, 96, 96],
'collector_env_num': 8,
'evaluator_env_num': 3,
'n_evaluator_episode': 3,
'manager': {
'shared_memory': False
}
},
'policy': {
'on_policy': False,
'cuda': True,
'multi_gpu': False,
'bp_update_sync': True,
'traj_len_inf': False,
'model': {
'observation_shape': [4, 96, 96],
'frame_stack_num': 4,
'action_space_size': 6,
'downsample': True,
'discrete_action_encoding_type': 'one_hot',
'norm_type': 'BN'
},
'use_rnd_model': False,
'sampled_algo': False,
'gumbel_algo': False,
'mcts_ctree': True,
'collector_env_num': 8,
'evaluator_env_num': 3,
'env_type': 'not_board_games',
'action_type': 'fixed_action_space',
'battle_mode': 'play_with_bot_mode',
'monitor_extra_statistics': True,
'game_segment_length': 400,
'transform2string': False,
'gray_scale': False,
'use_augmentation': True,
'augmentation': ['shift', 'intensity'],
'ignore_done': False,
'update_per_collect': 1000,
'model_update_ratio': 0.1,
'batch_size': 256,
'optim_type': 'SGD',
'learning_rate': 0.2,
'target_update_freq': 100,
'target_update_freq_for_intrinsic_reward': 1000,
'weight_decay': 0.0001,
'momentum': 0.9,
'grad_clip_value': 10,
'n_episode': 8,
'num_simulations': 50,
'discount_factor': 0.997,
'td_steps': 5,
'num_unroll_steps': 5,
'reward_loss_weight': 1,
'value_loss_weight': 0.25,
'policy_loss_weight': 1,
'policy_entropy_loss_weight': 0,
'ssl_loss_weight': 2,
'lr_piecewise_constant_decay': True,
'threshold_training_steps_for_final_lr': 50000,
'manual_temperature_decay': False,
'threshold_training_steps_for_final_temperature': 100000,
'fixed_temperature_value': 0.25,
'use_ture_chance_label_in_chance_encoder': False,
'use_priority': True,
'priority_prob_alpha': 0.6,
'priority_prob_beta': 0.4,
'root_dirichlet_alpha': 0.3,
'root_noise_weight': 0.25,
'random_collect_episode_num': 0,
'eps': {
'eps_greedy_exploration_in_collect': False,
'type': 'linear',
'start': 1.0,
'end': 0.05,
'decay': 100000
},
'cfg_type': 'EfficientZeroPolicyDict',
'lstm_horizon_len': 5,
'reanalyze_ratio': 0.0,
'eval_freq': 2000,
'replay_buffer_size': 1000000
},
'wandb_logger': {
'gradient_logger': False,
'video_logger': False,
'plot_logger': False,
'action_logger': False,
'return_logger': False
}
},
'create_config': {
'env': {
'type': 'atari_lightzero',
'import_names': ['zoo.atari.envs.atari_lightzero_env']
},
'env_manager': {
'type': 'subprocess'
},
'policy': {
'type': 'efficientzero',
'import_names': ['lzero.policy.efficientzero']
}
}
}
```
</details>
**Training Procedure**
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
- **Weights & Biases (wandb):** [monitor link](<TODO>)
## Model Information
<!-- Provide the basic links for the model. -->
- **Github Repository:** [repo link](https://github.com/opendilab/LightZero)
- **Doc**: [Algorithm link](<TODO>)
- **Configuration:** [config link](https://huggingface.co/OpenDILabCommunity/PongNoFrameskip-v4-EfficientZero/blob/main/policy_config.py)
- **Demo:** [video](https://huggingface.co/OpenDILabCommunity/PongNoFrameskip-v4-EfficientZero/blob/main/replay.mp4)
<!-- Provide the size information for the model. -->
- **Parameters total size:** 33023.14 KB
- **Last Update Date:** 2024-01-16
## Environments
<!-- Address questions around what environment the model is intended to be trained and deployed at, including the necessary information needed to be provided for future users. -->
- **Benchmark:** OpenAI/Gym/Atari
- **Task:** PongNoFrameskip-v4
- **Gym version:** 0.25.1
- **DI-engine version:** v0.5.0
- **PyTorch version:** 2.0.1+cu117
- **Doc**: [Environments link](<TODO>)
|
G-ML-Hyly/cdp_hyl_fd
|
G-ML-Hyly
| 2024-01-16T06:26:10Z | 93 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-16T06:08:41Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: cdp_hyl_fd
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# cdp_hyl_fd
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4997
- Accuracy: 0.8235
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 25
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.7019 | 1.0 | 55 | 1.1939 | 0.5 |
| 0.1305 | 2.0 | 110 | 0.6574 | 0.7353 |
| 0.0242 | 3.0 | 165 | 0.5197 | 0.8235 |
| 0.0081 | 4.0 | 220 | 0.3666 | 0.8824 |
| 0.0051 | 5.0 | 275 | 0.4560 | 0.8529 |
| 0.0035 | 6.0 | 330 | 0.4470 | 0.8235 |
| 0.0026 | 7.0 | 385 | 0.4395 | 0.8529 |
| 0.0022 | 8.0 | 440 | 0.4486 | 0.8235 |
| 0.0018 | 9.0 | 495 | 0.4684 | 0.8235 |
| 0.0015 | 10.0 | 550 | 0.4644 | 0.8529 |
| 0.0013 | 11.0 | 605 | 0.4669 | 0.8235 |
| 0.0012 | 12.0 | 660 | 0.4657 | 0.8235 |
| 0.0011 | 13.0 | 715 | 0.4799 | 0.8235 |
| 0.001 | 14.0 | 770 | 0.4817 | 0.8235 |
| 0.0009 | 15.0 | 825 | 0.4998 | 0.8235 |
| 0.0008 | 16.0 | 880 | 0.4964 | 0.8235 |
| 0.0008 | 17.0 | 935 | 0.5025 | 0.8235 |
| 0.0007 | 18.0 | 990 | 0.4954 | 0.8235 |
| 0.0007 | 19.0 | 1045 | 0.4933 | 0.8235 |
| 0.0007 | 20.0 | 1100 | 0.5014 | 0.8235 |
| 0.0006 | 21.0 | 1155 | 0.4961 | 0.8235 |
| 0.0006 | 22.0 | 1210 | 0.4955 | 0.8235 |
| 0.0006 | 23.0 | 1265 | 0.4984 | 0.8235 |
| 0.0006 | 24.0 | 1320 | 0.4988 | 0.8235 |
| 0.0006 | 25.0 | 1375 | 0.4997 | 0.8235 |
### Framework versions
- Transformers 4.36.1
- Pytorch 2.1.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
IHaBiS/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss-exl2
|
IHaBiS
| 2024-01-16T06:25:12Z | 0 | 0 | null |
[
"license:cc-by-nc-4.0",
"region:us"
] | null | 2024-01-10T13:15:20Z |
---
license: cc-by-nc-4.0
---
## Exl2 version of [NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss](https://huggingface.co/NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss)
## branch
3.5bh8 : 3.5bpw h8
Using ThePile [0007.parquet](https://huggingface.co/datasets/EleutherAI/the_pile_deduplicated/resolve/refs%2Fconvert%2Fparquet/default/train/0007.parquet) as dataset
Quantization settings : ```python convert.py -i models/NeverSleep_Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss -o Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss-temp4 -cf Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss-3.5bpw-h8-exl2 -c 0007.parquet -l 8192 -b 3.5 -hb 8 -ml 8192```
### below this line is original readme
---
# Disclaimer:
## This model is experimental, do not expect everything to work.
This model uses the Chatml **prompting format**
---
Beeg noromaid on ***steroids***. Suitable for RP, ERP.
This model was trained on the Zloss fork of Charles, and should fix issue the model had.
Use Chatml prompt format, but not the special token.
The reason is that Axolotl merge the finetune with the base model at 1.0 weight basically, but this is too much, so I use another script available [HERE](https://github.com/DocShotgun/LLM-notebooks/blob/main/weighted-lora-merge.ipynb) to merge with less weight, sadly, it don't take the special Chatml token. It's like Orca2 for the matter.
## Credits:
- Undi
- IkariDev
<!-- description start -->
## Description
<!-- [Recommended settings - contributed by localfultonextractor](https://files.catbox.moe/ue0tja.json) -->
This repo contains FP16 files of Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss.
[FP16 - by IkariDev and Undi](https://huggingface.co/NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss)
<!-- [GGUF - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GGUF)-->
<!-- [GPTQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GPTQ)-->
<!-- [exl2[8bpw-8h] - by AzureBlack](https://huggingface.co/AzureBlack/Echidna-13b-v0.3-8bpw-8h-exl2)-->
<!-- [AWQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-AWQ)-->
<!-- [fp16 - by IkariDev+Undi95](https://huggingface.co/IkariDev/Athena-v4)-->
[GGUF - by IkariDev and Undi](https://huggingface.co/NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss-GGUF)
<!-- [OLD(GGUF - by IkariDev+Undi95)](https://huggingface.co/IkariDev/Athena-v4-GGUF)-->
## Ratings:
Note: We have permission of all users to upload their ratings, we DONT screenshot random reviews without asking if we can put them here!
No ratings yet!
If you want your rating to be here, send us a message over on DC and we'll put up a screenshot of it here. DC name is "ikaridev" and "undi".
<!-- description end -->
<!-- prompt-template start -->
### Prompt format: Chatml
```
<|im_start|>system
{sysprompt}<|im_end|>
<|im_start|>user
{input}<|im_end|>
<|im_start|>assistant
{output}<|im_end|>
```
## Datasets used:
- Aesir 1, 2 & 3 modified by us, credit to ([MinervaAI](https://huggingface.co/MinervaAI) / [Gryphe](https://huggingface.co/Gryphe))
- [LimaRP-20231109](https://huggingface.co/datasets/lemonilia/LimaRP) ([Lemonilia](https://huggingface.co/lemonilia))
- [ToxicQAFinal](https://huggingface.co/datasets/NobodyExistsOnTheInternet/ToxicQAFinal) ([NobodyExistsOnTheInternet](https://huggingface.co/NobodyExistsOnTheInternet)
- [No-robots-ShareGPT](https://huggingface.co/datasets/Doctor-Shotgun/no-robots-sharegpt) ([Doctor-Shotgun](https://huggingface.co/Doctor-Shotgun))
## Others
Undi: If you want to support me, you can [here](https://ko-fi.com/undiai).
IkariDev: Visit my [retro/neocities style website](https://ikaridevgit.github.io/) please kek
|
0xFE00/ppo-LunarLander-v2
|
0xFE00
| 2024-01-16T06:12:39Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-16T06:12:20Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 272.02 +/- 14.89
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
Roy029/ngmodel_distilled_nlp2024
|
Roy029
| 2024-01-16T06:11:46Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2024-01-12T03:25:59Z |
---
license: apache-2.0
---
# 有害コンテンツ判定のための有害濃縮語彙モデル(32k) for NLP2024
トークナイザのテキスト圧縮率を算出するためのモデル
## Model Description
SentencePieceのユニグラムモードを適用して構築した有害語彙モデル
## 圧縮率の算出方法
圧縮率 = 1 - (トークン数/元々のテキスト文字列長)
## 発表
```
@InProceedings{jwu:nlp2023,
author = {梶浦 照乃, 山内 璃乃, 小柳 響子, 東出 紗也夏, 倉光 君郎},
title = {トークナイザーの圧縮率を用いた有害コンテンツの判定法},
booktitle = {言語処理学会第30回年次大会 (NLP2024)},
year = {2024},
}
```
|
ryusangwon/9903_Llama-2-7b-hf
|
ryusangwon
| 2024-01-16T05:56:52Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"generated_from_trainer",
"dataset:xsum",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:adapter:meta-llama/Llama-2-7b-hf",
"region:us"
] | null | 2024-01-16T05:56:47Z |
---
base_model: meta-llama/Llama-2-7b-hf
tags:
- generated_from_trainer
datasets:
- xsum
model-index:
- name: 9903_Llama-2-7b-hf
results: []
library_name: peft
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# 9903_Llama-2-7b-hf
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the xsum dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- PEFT 0.4.0
- Transformers 4.36.2
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0
|
jakobixdeen/gegegege
|
jakobixdeen
| 2024-01-16T05:36:46Z | 0 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"art",
"text-to-image",
"de",
"dataset:LDJnr/Capybara",
"dataset:fka/awesome-chatgpt-prompts",
"license:openrail",
"region:us"
] |
text-to-image
| 2024-01-16T05:32:51Z |
---
license: openrail
datasets:
- LDJnr/Capybara
- fka/awesome-chatgpt-prompts
language:
- de
metrics:
- bleu
library_name: adapter-transformers
pipeline_tag: text-to-image
tags:
- art
---
|
hari560/falcon-health-model
|
hari560
| 2024-01-16T05:31:10Z | 6 | 1 |
peft
|
[
"peft",
"base_model:ybelkada/falcon-7b-sharded-bf16",
"base_model:adapter:ybelkada/falcon-7b-sharded-bf16",
"region:us"
] | null | 2023-07-31T13:22:30Z |
---
library_name: peft
base_model: ybelkada/falcon-7b-sharded-bf16
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0.dev0
|
hari560/medical-falcon-7b
|
hari560
| 2024-01-16T05:29:17Z | 6 | 1 |
peft
|
[
"peft",
"base_model:ybelkada/falcon-7b-sharded-bf16",
"base_model:adapter:ybelkada/falcon-7b-sharded-bf16",
"region:us"
] | null | 2023-08-05T13:25:04Z |
---
library_name: peft
base_model: ybelkada/falcon-7b-sharded-bf16
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0.dev0
|
macdog101/dqn-SpaceInvadersNoFrameskip-v4
|
macdog101
| 2024-01-16T05:24:10Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-16T05:23:35Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 584.00 +/- 157.75
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga macdog101 -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga macdog101 -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga macdog101
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
Seokeon/lora_pp_robot_toy
|
Seokeon
| 2024-01-16T05:17:42Z | 3 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-16T05:07:39Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks toy
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Seokeon/lora_pp_robot_toy
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks toy using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
SamagraDataGov/test_mistral
|
SamagraDataGov
| 2024-01-16T05:10:33Z | 0 | 0 | null |
[
"safetensors",
"autotrain",
"text-generation",
"conversational",
"license:other",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-16T01:05:23Z |
---
tags:
- autotrain
- text-generation
widget:
- text: "I love AutoTrain because "
license: other
---
# Model Trained Using AutoTrain
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
# Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "PATH_TO_THIS_REPO"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype='auto'
).eval()
# Prompt content: "hi"
messages = [
{"role": "user", "content": "hi"}
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
# Model response: "Hello! How can I assist you today?"
print(response)
```
|
Seokeon/lora_pp_rc_car
|
Seokeon
| 2024-01-16T05:00:05Z | 1 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-16T04:50:10Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks toy
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Seokeon/lora_pp_rc_car
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks toy using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
PQAshwin/trocr-base-printed_license_plates_ocr_timestamp
|
PQAshwin
| 2024-01-16T04:53:13Z | 89 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"vision-encoder-decoder",
"image-text-to-text",
"generated_from_trainer",
"base_model:microsoft/trocr-base-printed",
"base_model:finetune:microsoft/trocr-base-printed",
"endpoints_compatible",
"region:us"
] |
image-text-to-text
| 2024-01-16T04:28:43Z |
---
base_model: microsoft/trocr-base-printed
tags:
- generated_from_trainer
model-index:
- name: trocr-base-printed_license_plates_ocr_timestamp
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# trocr-base-printed_license_plates_ocr_timestamp
This model is a fine-tuned version of [microsoft/trocr-base-printed](https://huggingface.co/microsoft/trocr-base-printed) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0631
- Cer: 0.01
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 10.4185 | 1.0 | 315 | 0.3811 | 0.0792 |
| 0.5419 | 2.0 | 630 | 0.1693 | 0.0311 |
| 0.5419 | 3.0 | 945 | 0.0963 | 0.0134 |
| 0.0944 | 4.0 | 1260 | 0.0631 | 0.01 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
CallComply/DeciLM-7B-Instruct-128k
|
CallComply
| 2024-01-16T04:51:17Z | 44 | 3 |
transformers
|
[
"transformers",
"safetensors",
"deci",
"text-generation",
"conversational",
"custom_code",
"en",
"dataset:Open-Orca/SlimOrca",
"license:apache-2.0",
"autotrain_compatible",
"region:us"
] |
text-generation
| 2024-01-16T04:20:47Z |
---
license: apache-2.0
language:
- en
datasets:
- Open-Orca/SlimOrca
---
# DeciLM-7B-instruct (128k context)
DeciLM-7B-instruct is a model for short-form instruction following. It is built by LoRA fine-tuning on the [SlimOrca dataset](https://huggingface.co/datasets/Open-Orca/SlimOrca).
### 🔥 Click [here](https://console.deci.ai/infery-llm-demo) for a live demo of DeciLM-7B + Infery!
## Model Details
### Model Description
DeciLM-7B-instruct is a derivative of the recently released [DeciLM-7B](https://huggingface.co/Deci/DeciLM-7B) language model, a pre-trained, high-efficiency generative text model with 7 billion parameters. DeciLM-7B-instruct is one the best 7B instruct models obtained using simple LoRA fine-tuning, without relying on preference optimization techniques such as RLHF and DPO.
- **Developed by:** [Deci](https://deci.ai)
- **Model type:** DeciLM is an auto-regressive language model using an optimized transformer decoder architecture that includes variable Grouped-Query Attention.
- **Language(s) (NLP):** English
- **License:** Apache 2.0
## Model Architecture
| Parameters | Layers | Heads | Sequence Length | GQA num_key_value_heads* |
|:----------|:----------|:----------|:----------|:----------|
| 7.04 billion | 32 | 32 | 8192 | Variable |
*AutoNAC was employed to optimize the selection of the GQA num_key_value_heads for each model layer.
### Model Sources
- **Blog:** [DeciLM-7B Technical Blog](https://deci.ai/blog/introducing-DeciLM-7B-the-fastest-and-most-accurate-7b-large-language-model-to-date)
- **Demo:** [DeciLM-7B-instruct Demo](https://huggingface.co/spaces/Deci/DeciLM-7B-instruct)
- **Finetuning Notebook:** [DeciLM-7B Finetuning Notebook](https://colab.research.google.com/drive/1kEV6i96AQ94xTCvSd11TxkEaksTb5o3U?usp=sharing)
- **Text Generation Notebook:** [DeciLM-7B-instruct Text Generation Notebook](https://bit.ly/declm-7b-instruct)
### Prompt Template
```
### System:
{system_prompt}
### User:
{user_prompt}
### Assistant:
```
## Uses
The model is intended for commercial and research use in English.
## How to Get Started with the Model
Use the code below to get started with the model.
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, pipeline
model_name = "Deci/DeciLM-7B-instruct"
device = "cuda" # for GPU usage or "cpu" for CPU usage
quantize = False # Optional. Useful for GPUs with less than 24GB memory
if quantize:
dtype_kwargs = dict(quantization_config=BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_compute_dtype=torch.bfloat16
))
else:
dtype_kwargs = dict(torch_dtype="auto")
model = AutoModelForCausalLM.from_pretrained(
model_name,
device_map="auto",
trust_remote_code=True,
**dtype_kwargs
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenizer.pad_token = tokenizer.eos_token
deci_generator = pipeline("text-generation",
model=model,
tokenizer=tokenizer,
temperature=0.1,
device_map="auto",
max_length=4096,
return_full_text=False)
system_prompt = "You are an AI assistant that follows instruction extremely well. Help as much as you can."
user_prompt = "How do I make the most delicious pancakes the world has ever tasted?"
prompt = tokenizer.apply_chat_template([
{"role": "system", "content": system_prompt},
{"role": "user", "content": user_prompt},
], tokenize=False, add_generation_prompt=True)
response = deci_generator(prompt)[0]['generated_text']
print(prompt + response)
```
## Evaluation
Below are DeciLM-7B and DeciLM-7B-instruct's evaluation results.
| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|:----------|:---------:|:---------:|:---------:|:---------:|:---------:|:---------:|:---------:|
| DecilLM-7B | 61.55 | 59.39 | 82.51 | 59.76 | 40.33 | 79.95 | 47.38 |
| DecilLM-7B-instruct | 63.19 | 61.01 | 82.37 | 60.24 | 49.75 | 79.72 | 46.02 |
### Runtime Benchmarks
| Inference Tool | Hardware | Prompt length | Generation length | Generated tokens/sec | Batch Size | Number of Prompts |
|:----------|:----------|:---------:|:---------:|:---------:|:---------:|:---------:|
| HuggingFace (PyTorch) | A100 (SXM4-80GB-400W) | 512 | 512 | **1174** | 352 | 352 |
| HuggingFace (PyTorch) | A100 (SXM4-80GB-400W) | 2048 | 2048 | **328** | 72 | 72 |
| Infery-LLM | A100 (SXM4-80GB-400W)| 512 | 512 | **4559** | 1024 | 4096 |
| Infery-LLM | A100 (SXM4-80GB-400W) | 2048 | 2048 | **3997** | 512 | 2048 |
| Infery-LLM | A10 | 512 | 512 | **1345** | 128 | 512 |
| Infery-LLM | A10 | 2048 | 2048 | **599** | 32 | 128 |
- In order to replicate the results of the Hugging Face benchmarks, you can use this [code example](https://huggingface.co/Deci/DeciLM-7B/blob/main/benchmark_hf_model.py).
- Infery-LLM, Deci's inference engine, features a suite of optimization algorithms, including selective quantization, optimized beam search, continuous batching, and custom CUDA kernels. To witness the full capabilities of Infery-LLM first-hand, we invite you to engage with our [interactive demo](https://console.deci.ai/infery-llm-demo).
## Ethical Considerations and Limitations
DeciLM-7B-instruct is a new technology that comes with inherent risks associated with its use. The testing conducted so far has been primarily in English and does not encompass all possible scenarios. Like those of all large language models, DeciLM-7B's outputs are unpredictable, and the model may generate responses that are inaccurate, biased, or otherwise objectionable. Consequently, developers planning to use DeciLM-7B should undertake thorough safety testing and tuning designed explicitly for their intended applications of the model before deployment.
## How to Cite
Please cite this model using this format.
```bibtex
@misc{DeciFoundationModels,
title = {DeciLM-7B-instruct},
author = {DeciAI Research Team},
year = {2023}
url={https://huggingface.co/Deci/DeciLM-7B-instruct},
}
```
|
peebno/Carti
|
peebno
| 2024-01-16T04:46:55Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2024-01-16T04:46:55Z |
---
license: creativeml-openrail-m
---
|
Vijaypsb/mistralai-7B-v01-fine-tuned-using-ludwig-4bit
|
Vijaypsb
| 2024-01-16T04:46:30Z | 1 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:adapter:mistralai/Mistral-7B-v0.1",
"region:us"
] | null | 2024-01-16T04:46:29Z |
---
library_name: peft
base_model: mistralai/Mistral-7B-v0.1
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.1
|
rlenzen/distilbert-base-uncased-finetuned-imdb
|
rlenzen
| 2024-01-16T04:39:50Z | 111 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2024-01-14T21:37:22Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-imdb
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-imdb
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4118
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.7024 | 1.0 | 157 | 2.4965 |
| 2.5792 | 2.0 | 314 | 2.4280 |
| 2.5354 | 3.0 | 471 | 2.4508 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
IamYash/ImageNet-Medium-Attention-and-MLP
|
IamYash
| 2024-01-16T04:36:30Z | 0 | 0 | null |
[
"region:us"
] | null | 2024-01-12T05:18:39Z |
## ImageNet Results
In our ImageNet experiment, we aimed to assess the performance of Mice ViTs on a more complex and diverse dataset, ImageNet. We trained mice ViTs on classifying the 1000 ImageNet classes.
## Training Details
Similar to the dSprites experiment, for each attention layer setting, we explored two model variants: an attention-only model and a model combining attention with the MLP module. Dropout and layer normalization were not applied for simplicity. The detailed training logs and metrics can be found [here](https://wandb.ai/vit-prisma/Imagenet/overview?workspace=user-yash-vadi).
## Table of Results
Below table describe the accuracy `[ <Acc> | <Top5 Acc> ]` of Mice ViTs with different configurations.
| **Size** | **NumLayers** | **Attention+MLP** | **AttentionOnly** | **Model Link** |
|:--------:|:-------------:|:-----------------:|:-----------------:|--------------------------------------------|
| **tiny** | **1** | 0.16 \| 0.33 | 0.11 \| 0.25 | [AttentionOnly](https://huggingface.co/IamYash/ImageNet-tiny-AttentionOnly), [Attention+MLP](https://huggingface.co/IamYash/ImageNet-tiny-Attention-and-MLP) |
| **base** | **2** | 0.23 \| 0.44 | 0.16 \| 0.34 | [AttentionOnly](https://huggingface.co/IamYash/ImageNet-base-AttentionOnly), [Attention+MLP](https://huggingface.co/IamYash/ImageNet-base-Attention-and-MLP) |
| **small**| **3** | 0.28 \| 0.51 | 0.17 \| 0.35 | [AttentionOnly](https://huggingface.co/IamYash/ImageNet-small-AttentionOnly), [Attention+MLP](https://huggingface.co/IamYash/ImageNet-small-Attention-and-MLP) |
| **medium**|**4** | 0.33 \| 0.56 | 0.17 \| 0.36 | [AttentionOnly](https://huggingface.co/IamYash/ImageNet-medium-AttentionOnly), [Attention+MLP](https://huggingface.co/IamYash/ImageNet-medium-Attention-and-MLP) |
|
MilosKosRad/DeBERTa-v3-large-SciFact
|
MilosKosRad
| 2024-01-16T04:32:24Z | 92 | 0 |
transformers
|
[
"transformers",
"pytorch",
"deberta-v2",
"text-classification",
"medical",
"en",
"dataset:allenai/scifact",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-16T03:47:24Z |
---
datasets:
- allenai/scifact
widget:
- text: X-linked genes, particularly those related to chromatin structure/remodeling, segregation, and ribosomal biogenesis and translational control, may also play key regulatory roles in breast carcinogenesis<SEP>While contribution of X chromosome in the susceptibility of prostate and ovarian cancer has been demonstrated, the role of X-linked genes in breast carcinogenesis is not clearly known. This study investigated and compared the X-linked gene expression profiles of MMTV-c-myc transgenic mammary tumor (MT) or MMTV-c-myc/MT-tgf-alpha double transgenic mouse mammary tumor (DT) to lactating mammary gland. cDNA microarray analysis using the Affymetrix system identified 1081 genes localized on the X chromosome with 174 and 194 genes at +/-2-fold change levels in MT and DT samples, respectively. Differentially expressed X-linked genes were predominantly related to chromatin structure/remodeling (e.g., Hdac8, Suv39h1, RbAp46 and Adr1), segregation (e.g., CENP-I and smc111) and, ribosomal biogenesis and translational control (e.g., Dkc1, Rpl44, Rpl39, Eif2s3x, Gspt2 and Rsk4). Confirmation of microarray data by semi-quantitative and quantitative RT-PCR in selected X-linked genes also showed similar pattern. In addition, the expression pattern of two chromosomal regions, XE3 and XF5, suggests that XE3 may have escaped from inactivation and XF5 subjected to inactivation. In conclusion, our data suggest that X-linked genes may play the key regulatory roles in the maintenance of chromatin structure, accurate chromosomal segregation and translational control; hence deregulation of X-linked genes may promote mammary gland tumorigenesis by promoting genetic instability and cell proliferation. Increased understanding of the role of X-linked genes and genetic pathways will provide the strategies to develop the molecular therapeutics to treat and prevent reproductive related cancers.
language:
- en
metrics:
- accuracy
- f1
- precision
- recall
tags:
- medical
---
# Textual Entailment for biomedical texts
## Model Description
This model is fine-tuned on SciFact dataset for textual antailment task in the domain of biomedicine.
|
Kurrant/RevenueStreamJP
|
Kurrant
| 2024-01-16T04:31:54Z | 52 | 0 |
setfit
|
[
"setfit",
"safetensors",
"bert",
"sentence-transformers",
"text-classification",
"generated_from_setfit_trainer",
"arxiv:2209.11055",
"region:us"
] |
text-classification
| 2023-12-14T06:05:41Z |
---
library_name: setfit
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
metrics:
- accuracy
widget:
- text: '首都圏最大級の店舗物件専門情報サービス会社です。
次々に出店する店舗さま達と一緒に成長しましょう！
あの店も、この店も、ホクトシステムで出店したんだ！と街中を歩くのが楽しくなります( ^ω^ )'
- text: 'けやき出版は、多摩のひととまちをつないでいくという企業理念のもと、書籍・情報誌・パンフレット・会社案内・社史・ロゴ制作やWEBサイトの記事制作などの仕事をさせていただいています。
2020年6月には、新しい多摩の情報誌「BALL.」を創刊（年２回発行）し、多摩エリアではずむように働こう！というタグラインのもと、多摩エリアの仕事に特化した内容を読者の方に届けています。
BALL.を中心に始まった、WEB MAGAZINEなど、クリエイター自らの企画参加型のメディアを形成しています。
'
- text: '私たちの存在意義（Purpose）は、「利他であふれる社会を創る」です。
利他とは、他人に利益を与えること。自分の事よりも他人の幸福を願うこと。シンプルに言うと「求め合うより与え合う」そんな表現がぴったりかもしれません。
私たちの夢は、世界中のすべての人たちが夢と勇気と笑顔に溢れた社会を創ることです。そのためには「利他の精神」は必要不可欠です。
誰かに期待するのではなく、自ら利他の精神を持ち 「どうすれば社会や他人を幸せにすることができるのだろう」を日々考え行動し、社会を良くしていきます。'
- text: '「ラテンアメリカと日本の新しい歴史を創り、人々の人生を豊かにする」ことを理念に、メキシコ合衆国を中心に事業を展開しています！現在はメキシコ合衆国を中心に、メキシコ人・日本人およびセルビア人の合計80名で活動しています。
主な事業内容は 以下の通りです。
①広告代理店、ならびに各種コンサルティング事業 (企画・営業部)
②ラテンアメリカ域内における日本食レストランの運営事業 (Food & Beverage 事業部)
'
- text: 次世代を担う子どもたちへプログラミングの面白さを伝えるキッズプログラミングスクール「ツクル」を運営するスタートアップ。
pipeline_tag: text-classification
inference: true
---
# SetFit
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Model Details
### Model Description
- **Model Type:** SetFit
<!-- - **Sentence Transformer:** [Unknown](https://huggingface.co/unknown) -->
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 512 tokens
- **Number of Classes:** 2 classes
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
### Model Labels
| Label | Examples |
|:--------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Non-recurring | <ul><li>'海外に拠点を置くセカンダリー・プライベート・エクイティ投資に特化した独立系運用会社。'</li><li>'我々映像機器システム社は、大正11年から続く長い歴史のある企業です。\n「夢と感動を皆様にお届けする」という信念は今も昔も、これからも変わることはありません。\n\n我々の仕事を通して、エンドユーザーには想像以上の映像・音響体験が生まれ、感謝と感動が循環します。\nまるで自分も映像の中に入り込んだように、全身で作品を味わっていただいています。\n\nただ「映画を観る」だけではなく、「映画を体験」し、その先の感動をお届けし続ける企業であり続けたいと思っています！'</li><li>'報道関係者向けイベントのオンライン開催を支援する動画配信サービス「プレスメイク」などを運営するスタートアップ。'</li></ul> |
| Recurring | <ul><li>'お米・麦・大豆を使い、\n飲食業に特化した今までにない\n飲食業態を開発運営する会社です。\n\nキャッチコピーは「お米をデザインする」\n\n自社農園での農業から加工・販売まで\n\n育てる・作る・販売するを一貫して行なっており、\n一次産業から三次産業まで\n全てのシーンでお米をデザインしながら、\n日本の食文化で常に\n新しいチャレンジをしています。'</li><li>'アニメ評価ランキングサイト「あにこれ」を運営するスタートアップ。'</li><li>'100人いれば、100通りの美しさがあり、100通りのらしさがある。\n創業以来ずっと、私たちは患者様一人ひとりと向き合い、\n患者さまの立場に立った施術を行うことを信念としてやってきました。\n例えば、カウンセラーではなく医師が時間をかけて患者様と向き合って\nカウンセリングしているのもそのスタンスを実現するためです。\n\n一人一人にクオリティの高い治療を行うために。\n最新技術の研鑽はもちろんのこと、チームワークを大切にしながら、\n美容医療をいかに進化させることができるかを真剣に学べる環境です。'</li></ul> |
## Uses
### Direct Use for Inference
First install the SetFit library:
```bash
pip install setfit
```
Then you can load this model and run inference.
```python
from setfit import SetFitModel
# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("Kurrant/RevenueStreamJP")
# Run inference
preds = model("次世代を担う子どもたちへプログラミングの面白さを伝えるキッズプログラミングスクール「ツクル」を運営するスタートアップ。")
```
<!--
### Downstream Use
*List how someone could finetune this model on their own dataset.*
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Set Metrics
| Training set | Min | Median | Max |
|:-------------|:----|:-------|:----|
| Word count | 1 | 2.0785 | 65 |
| Label | Training Sample Count |
|:--------------|:----------------------|
| Non-recurring | 929 |
| Recurring | 1467 |
### Training Hyperparameters
- batch_size: (8, 8)
- num_epochs: (2, 2)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 3
- body_learning_rate: (2e-05, 2e-05)
- head_learning_rate: 2e-05
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: False
### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:------:|:----:|:-------------:|:---------------:|
| 0.0006 | 1 | 0.3 | - |
| 0.0278 | 50 | 0.2769 | - |
| 0.0556 | 100 | 0.2192 | - |
| 0.0835 | 150 | 0.323 | - |
| 0.1113 | 200 | 0.2692 | - |
| 0.1391 | 250 | 0.1603 | - |
| 0.1669 | 300 | 0.3578 | - |
| 0.1948 | 350 | 0.197 | - |
| 0.2226 | 400 | 0.3582 | - |
| 0.2504 | 450 | 0.2184 | - |
| 0.2782 | 500 | 0.182 | - |
| 0.3061 | 550 | 0.2353 | - |
| 0.3339 | 600 | 0.2287 | - |
| 0.3617 | 650 | 0.1228 | - |
| 0.3895 | 700 | 0.2276 | - |
| 0.4174 | 750 | 0.2181 | - |
| 0.4452 | 800 | 0.2857 | - |
| 0.4730 | 850 | 0.2361 | - |
| 0.5008 | 900 | 0.2545 | - |
| 0.5287 | 950 | 0.1986 | - |
| 0.5565 | 1000 | 0.3308 | - |
| 0.5843 | 1050 | 0.2126 | - |
| 0.6121 | 1100 | 0.18 | - |
| 0.6400 | 1150 | 0.1206 | - |
| 0.6678 | 1200 | 0.1441 | - |
| 0.6956 | 1250 | 0.1999 | - |
| 0.7234 | 1300 | 0.1518 | - |
| 0.7513 | 1350 | 0.1713 | - |
| 0.7791 | 1400 | 0.033 | - |
| 0.8069 | 1450 | 0.1999 | - |
| 0.8347 | 1500 | 0.0766 | - |
| 0.8625 | 1550 | 0.1551 | - |
| 0.8904 | 1600 | 0.363 | - |
| 0.9182 | 1650 | 0.0398 | - |
| 0.9460 | 1700 | 0.1047 | - |
| 0.9738 | 1750 | 0.0475 | - |
| 1.0017 | 1800 | 0.0331 | - |
| 1.0295 | 1850 | 0.0113 | - |
| 1.0573 | 1900 | 0.0099 | - |
| 1.0851 | 1950 | 0.2228 | - |
| 1.1130 | 2000 | 0.1168 | - |
| 1.1408 | 2050 | 0.0687 | - |
| 1.1686 | 2100 | 0.0018 | - |
| 1.1964 | 2150 | 0.0043 | - |
| 1.2243 | 2200 | 0.0016 | - |
| 1.2521 | 2250 | 0.0488 | - |
| 1.2799 | 2300 | 0.0029 | - |
| 1.3077 | 2350 | 0.0053 | - |
| 1.3356 | 2400 | 0.0659 | - |
| 1.3634 | 2450 | 0.0662 | - |
| 1.3912 | 2500 | 0.0013 | - |
| 1.4190 | 2550 | 0.1195 | - |
| 1.4469 | 2600 | 0.0004 | - |
| 1.4747 | 2650 | 0.0028 | - |
| 1.5025 | 2700 | 0.0002 | - |
| 1.5303 | 2750 | 0.2196 | - |
| 1.5582 | 2800 | 0.0011 | - |
| 1.5860 | 2850 | 0.0086 | - |
| 1.6138 | 2900 | 0.0017 | - |
| 1.6416 | 2950 | 0.0048 | - |
| 1.6694 | 3000 | 0.0003 | - |
| 1.6973 | 3050 | 0.0003 | - |
| 1.7251 | 3100 | 0.0002 | - |
| 1.7529 | 3150 | 0.0002 | - |
| 1.7807 | 3200 | 0.0003 | - |
| 1.8086 | 3250 | 0.0001 | - |
| 1.8364 | 3300 | 0.0002 | - |
| 1.8642 | 3350 | 0.0133 | - |
| 1.8920 | 3400 | 0.0003 | - |
| 1.9199 | 3450 | 0.0003 | - |
| 1.9477 | 3500 | 0.0007 | - |
| 1.9755 | 3550 | 0.0005 | - |
### Framework Versions
- Python: 3.10.12
- SetFit: 1.0.2
- Sentence Transformers: 2.2.2
- Transformers: 4.35.2
- PyTorch: 2.1.0+cu121
- Datasets: 2.16.1
- Tokenizers: 0.15.0
## Citation
### BibTeX
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->
|
Seokeon/lora_pp_cat
|
Seokeon
| 2024-01-16T04:25:20Z | 1 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-16T04:15:23Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks cat
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Seokeon/lora_pp_cat
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks cat using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
brucethemoose/Yi-34B-200K-DARE-megamerge-v8-31bpw-exl2-fiction
|
brucethemoose
| 2024-01-16T04:17:11Z | 13 | 1 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"Yi",
"en",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-14T18:44:59Z |
---
license: other
license_name: yi-license
license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE
language:
- en
library_name: transformers
base_model: []
tags:
- mergekit
- merge
- Yi
---
# **NOTE: THIS QUANTIZATION IS BROKEN**
See: https://huggingface.co/brucethemoose/Yi-34B-200K-DARE-megamerge-v8-31bpw-exl2-fiction/discussions/4#65a5eb3aee220af178d28541
# Yi 34B Merge v8
A merge of several Yi 34B 200K models using the new DARE Ties method via mergekit, quantized with exllamav2 on ~300K tokens of a sci-fi story, a fantasy story, and a vicuna chat for optimal long context storywriting performance.
See the main model card: https://huggingface.co/brucethemoose/Yi-34B-200K-DARE-megamerge-v8
## Prompt template: Orca-Vicuna
```
SYSTEM: {system_message}
USER: {prompt}
ASSISTANT:
```
It might recognize ChatML, and possibly Alpaca-like formats. Raw prompting as described here is also effective: https://old.reddit.com/r/LocalLLaMA/comments/18zqy4s/the_secret_to_writing_quality_stories_with_llms/
## Running
24GB GPUs can run 3.1bpw Yi-34B-200K models at **75K context** with exllamav2, and performant UIs like [exui](https://github.com/turboderp/exui). I go into more detail in this [post](https://old.reddit.com/r/LocalLLaMA/comments/1896igc/how_i_run_34b_models_at_75k_context_on_24gb_fast/)
Being a Yi model, try running a lower temperature with 0.05+ MinP, a little repetition penalty, maybe mirostat with a low tau, and no other samplers. Yi tends to run "hot" by default, and it really needs a low temperature + MinP to cull the huge vocabulary.
## Quantization Commands
First pass:
```
python /home/alpha/AI/exllamav2/convert.py --in_dir /home/alpha/FastModels/v8/v8 -o /home/alpha/FastModels/scratch -om /home/alpha/FastModels/v8meas.json --cal_dataset /home/alpha/Documents/stories.parquet -ml 32768 -mr 8 -ss 4096 -b 4.0 -hb 6 -nr
```
Second pass:
```
python /home/alpha/AI/exllamav2/convert.py --in_dir /home/alpha/FastModels/v8/v8 -o /home/alpha/FastModels/scratch -m /home/alpha/FastModels/v8meas.json --cal_dataset /home/alpha/Documents/stories.parquet -l 12288 -r 26 -ml 32768 -mr 8 -ss 4096 -b 4.0 -hb 6 -cf /home/alpha/FastModels/v8-exl2-4bpw-fiction -nr
```
|
klein-zcy/Phi-1_5-MetaMathQA
|
klein-zcy
| 2024-01-16T03:59:35Z | 35 | 1 |
transformers
|
[
"transformers",
"safetensors",
"phi",
"text-generation",
"custom_code",
"en",
"dataset:meta-math/MetaMathQA",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-16T01:47:21Z |
---
license: apache-2.0
datasets:
- meta-math/MetaMathQA
language:
- en
---
Supervised Finetuning the phi1.5 on MetaMathQA datasets. The results are as follows:
| Model | GSM8k Pass@1 | MATH Pass@1 |
|---------------------|--------------|-------------|
| MPT-7B | 6.8 | 3.0 |
| Falcon-7B | 6.8 | 2.3 |
| LLaMA-1-7B | 11.0 | 2.9 |
| LLaMA-2-7B | 14.6 | 2.5 |
| MPT-30B | 15.2 | 3.1 |
| LLaMA-1-13B | 17.8 | 3.9 |
| GPT-Neo-2.7B | 19.5 | -- |
| Falcon-40B | 19.6 | 2.5 |
| Baichuan-chat-13B | 23.9 | -- |
| Vicuna-v1.3-13B | 27.6 | -- |
| LLaMA-2-13B | 28.7 | 3.9 |
| InternLM-7B | 31.2 | -- |
| ChatGLM-2-6B | 32.4 | -- |
| GPT-J-6B | 34.9 | -- |
| LLaMA-1-33B | 35.6 | 3.9 |
| LLaMA-2-34B | 42.2 | 6.24 |
| RFT-7B | 50.3 | -- |
| LLaMA-1-65B | 50.9 | 10.6 |
| Qwen-7B | 51.6 | -- |
| **Phi1.5-1.3B** | **54.3** | **15.5** |
| WizardMath-7B | 54.9 | 10.7 |
| LLaMA-2-70B | 56.8 | 13.5 |
| WizardMath-13B | 63.9 | 14.0 |
| MAmmoTH-7B (COT) | 50.5 | 10.4 |
| MAmmoTH-7B (POT+COT)| 53.6 | 31.5 |
| Arithmo-Mistral-7B | 74.7 | 25.3 |
| MetaMath-7B | 66.5 | 19.8 |
| MetaMath-13B | 72.3 | 22.4 |
| **MetaMath-Mistral-7B** | **77.7** | **28.2** |
It achieves remarkable performance with only 1.3B parameters !!!
You can evaluate the results by [metamath](https://huggingface.co/meta-math/MetaMath-Mistral-7B) evaluation code.
|
cocoirun/Yi-Ko-6B-instruct-v1.5-DPO
|
cocoirun
| 2024-01-16T03:58:49Z | 59 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-16T03:24:26Z |
---
license: cc-by-sa-4.0
---
<h1>instruct 모델 v1.5</h1>
<b><학습 데이터 구축></b>
Open-Orca-ko 데이터를 분석하여 태스크를 추출한 뒤
해당 태스크에 맞춰서 NLP 관련 오픈소스 데이터를 활용하여 학습데이터를 자체적으로
약 4만건(역사, 과학, 수학, 기계독해, 리뷰 분석) 구축하였고,
그 외에 Open-Orca-Ko에서 데이터를 일부 필터링하여 정제해거나 KoBEST 데이터를 함께 추가하였습니다.
aihub 일반상식 및 기계독해 데이터를 활용하여 추가로 학습 데이터를 구축(형태소 관련, 기계독해 관련 및 요약)
각종 블로그에서 역사 및 상식 퀴즈를 사람이 직접 학습데이터 형태로 변경
AI2AI Challenge 데이터를 파파고를 통해 번역 및 오역된 부분을 사람이 직접 수정 하는 작업을 수행
영어 번역 데이터 영한/한영 데이터 학습 데이터로 활용 진행
총 11만개의 학습데이터로 sft를 진행하였습니다.
<br>
현재, 새로운 버전의 모델 학습 및 성능을 위해 Open-Orca 데이터셋 일부를 번역하여 정제 중에 있습니다.
<br>
+ 고등학교 역사 문제 및 TruthfulQA 관련 문제 추가를 진행하였습니다.
+ 각종 it 지식 데이터 추가진행.
+ 기계독해 관련 학습 데이터를 ChatGPT를 통해서 답변을 얻어 학습
+ 문법관련 학습 데이터
<br>
###학습 데이터 파일은 비공개입니다.
<br>
<b><학습></b>
학습은 LoRA를 사용하여 A100 40G *2에서 학습을 진행하였습니다.
|
tshrjn/TinyLlama_pubmed_v0-4
|
tshrjn
| 2024-01-16T03:58:35Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-01-16T03:58:28Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
shitshow123/TinyLlama-1.1B-ChatStrong-DPO-PPO
|
shitshow123
| 2024-01-16T03:57:53Z | 136 | 1 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"feature-extraction",
"license:apache-2.0",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2024-01-13T02:29:58Z |
---
license: apache-2.0
---
This is a strong TinyLlama-1.1B-Chat-Model trained using a modified version of PPO + DPO algo
*****Score rated by ChatGPT + Claude + Gemini (max-score is 3)*****
| Characteristic | Baseline (TinyLlama/TinyLlama-1.1B-Chat-v1.0) | Ours (TinyLlama-1.1B-ChatStrong-DPO-PPO) |
|-----------------|--------------------------------------------------|--------------------------------------------------------|
| Fluency | 2 | 3 |
| Coherence | 1 | 3 |
| Non-repetition | 1 | 3 |
| Engagement | 1 | 2 |
| Creativity | 1 | 2 |
| Accuracy | 2 | 2 |
| Relevance | 2 | 3 |
| Knowledge | 2 | 2 |
| Common sense | 1 | 2 |
| Empathy | 1 | 2 |
| Humor | 1 | 2 |
| Logic | 1 | 2 |
| Grammar | 2 | 3 |
*Note: score is based on prompt generated by GPT4.
```python
# Install transformers from source - only needed for versions <= v4.34
# pip install git+https://github.com/huggingface/transformers.git
# pip install accelerate
import torch
from transformers import pipeline
pipe = pipeline("text-generation", model="shitshow123/TinyLlama-1.1B-ChatStrong-DPO-PPO", torch_dtype=torch.bfloat16, device_map="auto")
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
{
"role": "system",
"content": "You are a friendly chatbot who always responds in the style of a pirate",
},
{"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
#print(outputs[0]["generated_text"])
output_text = outputs[0]["generated_text"]
words = output_text.split()
# Insert a newline character every 50 words
formatted_output = ""
for i in range(0, len(words), 10):
formatted_output += ' '.join(words[i:i+10]) + "\n"
print(formatted_output)
# ...
```
## Example Output by this model:
<|system|> You are a friendly chatbot who always responds in
the style of a pirate</s> ******<|user|> Provide a summary of
the latest developments in renewable energy technologies, focusing on solar
and wind power advancements in the past year.</s> <|assistant|>****** In
the past year, significant advancements have been made in the
renewable energy sector, particularly in the areas of solar and
wind power. Here's a summary of some of the notable
developments: 1. Solar: - Solar panels have become more efficient,
with a record-breaking 29.2% conversion efficiency achieved in 2020. -
The world's largest solar farm, located in China, has a
capacity of 1.2 GW, making it the largest solar power
plant in the world. - The European Union has set
a target of achieving 32% renewable energy by 2030, with
solar power expected to play a significant role in achieving
this goal. 2. Wind: - Wind turbines have become more
efficient, with a record-breaking 1.2 GW of wind power capacity
installed in 2020. - The world's largest offshore wind farm,
located in the UK, has a capacity of 670 MW.
- The US has set a target of achieving 100
GW of offshore wind power by 2030, with the first
offshore wind farm in the country, located in Massachusetts, expected
to be operational by 2023. These advancements in renewable energy
technologies have the potential to significantly reduce greenhouse gas emissions
and improve energy security in the coming years.
## Example Output by the baseline TinyLamma model (see the repetition of Novemeber 2020):
<|system|> You are a friendly chatbot who always responds in
the style of a pirate</s> ******<|user|> Provide a summary of
the latest developments in renewable energy technologies, focusing on solar
and wind power advancements in the past year.</s> <|assistant|>****** In
the past year, there have been significant advancements in renewable
energy technologies, particularly in solar and wind power. Here's a
summary: 1. Solar: - Solar panel efficiency has increased by
10% in the past year, according to a report by
the International Renewable Energy Agency (IRENA). - The world's largest
solar power plant, the 1.2 GW Solar Park in Abu
Dhabi, opened in November 2020. - The world's largest solar
power plant, the 1.2 GW Solar Park in Abu Dhabi,
opened in November 2020. It is expected to generate enough
electricity to power 500,000 homes. - The world's largest solar
power plant, the 1.2 GW Solar Park in Abu Dhabi,
opened in November 2020. It is expected to generate enough
electricity to power 500,000 homes. - The world's largest solar
power plant, the 1.2 GW Solar Park in Abu Dhabi,
opened in November 2020. It is expected to generate enough
electricity to power 500,000 homes. 2. Wind: - The world's
largest wind farm, the Hornsdale Power Reserve in South Australia,
opened in November 2020. It is expected to generate enough
electricity to power 100,000 homes. - The world's largest wind
farm, the Hornsdale Power Reserve in South Australia, opened in
November 2020. It is expected to generate enough electricity to
power 100,000 homes. - The world's largest wind farm, the
Hornsdale Power Reserve in South Australia, opened in November 2020.
It is expected to generate enough electricity to power 100,000
homes. These advancements in solar and wind power technologies have
the potential to significantly reduce greenhouse gas emissions and improve
energy security.
|
remmymilkyway/deeprl-course-unit1
|
remmymilkyway
| 2024-01-16T03:51:50Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-16T03:51:28Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 233.31 +/- 63.40
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
Seokeon/lora_pp_dog6
|
Seokeon
| 2024-01-16T03:46:20Z | 1 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-16T03:36:24Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Seokeon/lora_pp_dog6
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
SeeonQwQ/blip2_frame_v0
|
SeeonQwQ
| 2024-01-16T03:41:54Z | 1 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:Salesforce/blip2-opt-2.7b",
"base_model:adapter:Salesforce/blip2-opt-2.7b",
"region:us"
] | null | 2024-01-16T03:40:47Z |
---
library_name: peft
base_model: Salesforce/blip2-opt-2.7b
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.2.dev0
|
amy011872/finetune-mistral-cleaner-v3
|
amy011872
| 2024-01-16T03:40:45Z | 0 | 0 |
peft
|
[
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:mistralai/Mistral-7B-Instruct-v0.1",
"base_model:adapter:mistralai/Mistral-7B-Instruct-v0.1",
"license:apache-2.0",
"region:us"
] | null | 2024-01-16T03:40:30Z |
---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.1
model-index:
- name: finetune-mistral-cleaner-v3
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# finetune-mistral-cleaner-v3
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8435
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-07
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.37 | 0.08 | 20 | 1.8455 |
| 1.9081 | 0.16 | 40 | 1.8453 |
| 1.9063 | 0.24 | 60 | 1.8451 |
| 1.7914 | 0.32 | 80 | 1.8450 |
| 2.2449 | 0.4 | 100 | 1.8448 |
| 1.7181 | 0.48 | 120 | 1.8446 |
| 1.9602 | 0.56 | 140 | 1.8444 |
| 2.1923 | 0.64 | 160 | 1.8442 |
| 1.7254 | 0.72 | 180 | 1.8440 |
| 2.0513 | 0.8 | 200 | 1.8438 |
| 1.7509 | 0.88 | 220 | 1.8437 |
| 1.9919 | 0.96 | 240 | 1.8435 |
### Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.1
- Datasets 2.16.1
- Tokenizers 0.15.0
|
Seokeon/lora_none_bear_plushie
|
Seokeon
| 2024-01-16T03:30:45Z | 1 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-16T03:26:32Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks stuffed animal
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Seokeon/lora_none_bear_plushie
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks stuffed animal using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
Seokeon/lora_pp_grey_sloth_plushie
|
Seokeon
| 2024-01-16T03:28:47Z | 2 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-16T03:17:58Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks stuffed animal
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Seokeon/lora_pp_grey_sloth_plushie
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks stuffed animal using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
Seokeon/lora_none_monster_toy
|
Seokeon
| 2024-01-16T03:26:12Z | 1 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-16T03:22:20Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks toy
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Seokeon/lora_none_monster_toy
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks toy using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
ShengGao/mistral-7b_v0.2_summarization
|
ShengGao
| 2024-01-16T03:25:56Z | 1 | 0 |
peft
|
[
"peft",
"safetensors",
"region:us"
] | null | 2024-01-16T03:25:46Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0
|
Seokeon/lora_none_grey_sloth_plushie
|
Seokeon
| 2024-01-16T03:22:02Z | 2 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-16T03:17:51Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks stuffed animal
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Seokeon/lora_none_grey_sloth_plushie
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks stuffed animal using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
Seokeon/lora_none_dog8
|
Seokeon
| 2024-01-16T03:17:33Z | 1 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-16T03:13:46Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Seokeon/lora_none_dog8
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
alpha-brain/finetuned_mistral_alpaca
|
alpha-brain
| 2024-01-16T03:13:35Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-01-16T03:13:14Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
Seokeon/lora_none_dog2
|
Seokeon
| 2024-01-16T03:09:22Z | 1 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-16T03:05:36Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Seokeon/lora_none_dog2
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
Seokeon/lora_none_cat
|
Seokeon
| 2024-01-16T03:05:18Z | 1 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-16T03:01:32Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks cat
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Seokeon/lora_none_cat
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks cat using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
Seokeon/lora_none_robot_toy
|
Seokeon
| 2024-01-16T03:01:14Z | 1 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-16T02:57:20Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks toy
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Seokeon/lora_none_robot_toy
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks toy using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
Kquant03/Ryu-4x7B-MoE-GGUF
|
Kquant03
| 2024-01-16T03:00:21Z | 7 | 1 | null |
[
"gguf",
"merge",
"en",
"arxiv:2101.03961",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-01-13T07:13:52Z |
---
license: apache-2.0
language:
- en
tags:
- merge
---
# Intuition sharp as a blade
A merge of [fblgit/UNA-TheBeagle-7b-v1](https://huggingface.co/fblgit/UNA-TheBeagle-7b-v1), [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca), [samir-fama/FernandoGPT-v1](https://huggingface.co/samir-fama/FernandoGPT-v1) and [Neuronovo/neuronovo-7B-v0.3](https://huggingface.co/Neuronovo/neuronovo-7B-v0.3).
The idea is that these models perform very well in their respective fields, and that they're also likely to work just as well together. I will submit it to the open llm eval, and I will also be testing the q5_k_m version for results.
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [Q2_K Tiny](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q2_k.gguf) | Q2_K | 2 | 8.06 GB| 10.06 GB | smallest, significant quality loss - not recommended for most purposes |
| [Q3_K_M](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q3_k_m.gguf) | Q3_K_M | 3 | 10.5 GB| 12.5 GB | very small, high quality loss |
| [Q4_0](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q4_0.gguf) | Q4_0 | 4 | 13.6 GB| 15.6 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [Q4_K_M](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q4_k_m.gguf) | Q4_K_M | 4 | ~13.6 GB| ~15.6 GB | medium, balanced quality - recommended |
| [Q5_0](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q5_0.gguf) | Q5_0 | 5 | 16.6 GB| 18.6 GB | legacy; large, balanced quality |
| [Q5_K_M](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q5_k_m.gguf) | Q5_K_M | 5 | ~16.6 GB| ~18.6 GB | large, balanced quality - recommended |
| [Q6 XL](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q6_k.gguf) | Q6_K | 6 | 19.8 GB| 21.8 GB | very large, extremely low quality loss |
| [Q8 XXL](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q8_0.gguf) | Q8_0 | 8 | 25.7 GB| 27.7 GB | very large, extremely low quality loss - not recommended |
| [f16 XXXL](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-f16.gguf) | f16 | 8 | 48.3 GB| 50.3 GB | very VERY large, nearly lossless - not recommended |
# "[What is a Mixture of Experts (MoE)?](https://huggingface.co/blog/moe)"
### (from the MistralAI papers...click the quoted question above to navigate to it directly.)
The scale of a model is one of the most important axes for better model quality. Given a fixed computing budget, training a larger model for fewer steps is better than training a smaller model for more steps.
Mixture of Experts enable models to be pretrained with far less compute, which means you can dramatically scale up the model or dataset size with the same compute budget as a dense model. In particular, a MoE model should achieve the same quality as its dense counterpart much faster during pretraining.
So, what exactly is a MoE? In the context of transformer models, a MoE consists of two main elements:
Sparse MoE layers are used instead of dense feed-forward network (FFN) layers. MoE layers have a certain number of “experts” (e.g. 32 in my "frankenMoE"), where each expert is a neural network. In practice, the experts are FFNs, but they can also be more complex networks or even a MoE itself, leading to hierarchical MoEs!
A gate network or router, that determines which tokens are sent to which expert. For example, in the image below, the token “More” is sent to the second expert, and the token "Parameters” is sent to the first network. As we’ll explore later, we can send a token to more than one expert. How to route a token to an expert is one of the big decisions when working with MoEs - the router is composed of learned parameters and is pretrained at the same time as the rest of the network.
At every layer, for every token, a router network chooses two of these groups (the “experts”) to process the token and combine their output additively.
Switch Layer
MoE layer from the [Switch Transformers paper](https://arxiv.org/abs/2101.03961)
So, to recap, in MoEs we replace every FFN layer of the transformer model with an MoE layer, which is composed of a gate network and a certain number of experts.
Although MoEs provide benefits like efficient pretraining and faster inference compared to dense models, they also come with challenges:
Training: MoEs enable significantly more compute-efficient pretraining, but they’ve historically struggled to generalize during fine-tuning, leading to overfitting.
Inference: Although a MoE might have many parameters, only some of them are used during inference. This leads to much faster inference compared to a dense model with the same number of parameters. However, all parameters need to be loaded in RAM, so memory requirements are high. For example, [given a MoE like Mixtral 8x7B](https://huggingface.co/blog/moe), we’ll need to have enough VRAM to hold a dense 47B parameter model. Why 47B parameters and not 8 x 7B = 56B? That’s because in MoE models, only the FFN layers are treated as individual experts, and the rest of the model parameters are shared. At the same time, assuming just two experts are being used per token, the inference speed (FLOPs) is like using a 12B model (as opposed to a 14B model), because it computes 2x7B matrix multiplications, but with some layers shared (more on this soon).
If all our tokens are sent to just a few popular experts, that will make training inefficient. In a normal MoE training, the gating network converges to mostly activate the same few experts. This self-reinforces as favored experts are trained quicker and hence selected more. To mitigate this, an auxiliary loss is added to encourage giving all experts equal importance. This loss ensures that all experts receive a roughly equal number of training examples. The following sections will also explore the concept of expert capacity, which introduces a threshold of how many tokens can be processed by an expert. In transformers, the auxiliary loss is exposed via the aux_loss parameter.
## "Wait...but you called this a frankenMoE?"
The difference between MoE and "frankenMoE" lies in the fact that the router layer in a model like the one on this repo is not trained simultaneously. There are rumors about someone developing a way for us to unscuff these frankenMoE models by training the router layer simultaneously. This model seems to overcome that.
|
slauw87/phi-2_7b_orcaSFT
|
slauw87
| 2024-01-16T02:49:39Z | 57 | 0 |
transformers
|
[
"transformers",
"safetensors",
"phi-msft",
"text-generation",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2024-01-16T02:47:01Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
mrow/finetuning-sentiment-model-40000-samples
|
mrow
| 2024-01-16T02:36:54Z | 92 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-14T16:45:35Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: finetuning-sentiment-model-40000-samples
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# finetuning-sentiment-model-40000-samples
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.1153
- eval_accuracy: 0.9741
- eval_f1: 0.9741
- eval_runtime: 141.3267
- eval_samples_per_second: 56.606
- eval_steps_per_second: 3.538
- epoch: 1.5
- step: 3004
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
Seokeon/bear_plushie
|
Seokeon
| 2024-01-16T02:36:32Z | 1 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-16T02:25:56Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks stuffed animal
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Seokeon/bear_plushie
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks stuffed animal using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
Seokeon/example6
|
Seokeon
| 2024-01-16T02:35:30Z | 0 | 1 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:finetune:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2024-01-16T01:02:30Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - Seokeon/example6
This is a dreambooth model derived from runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
|
jlbaker361/restest
|
jlbaker361
| 2024-01-16T02:18:38Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-12-31T22:00:24Z |
---
{}
---
trained to classify images
epochs: 1
dataset jlbaker361/wikiart
n classes 27
image dim 224
pretrained version resnet18
batch_size 4
|
Seokeon/example7
|
Seokeon
| 2024-01-16T02:18:21Z | 1 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-16T02:04:49Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Seokeon/example7
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
YaHi/teacher_electra_small
|
YaHi
| 2024-01-16T02:10:28Z | 7 | 0 |
transformers
|
[
"transformers",
"pytorch",
"electra",
"text-classification",
"generated_from_trainer",
"base_model:google/electra-small-discriminator",
"base_model:finetune:google/electra-small-discriminator",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-25T15:24:40Z |
---
license: apache-2.0
base_model: google/electra-small-discriminator
tags:
- generated_from_trainer
model-index:
- name: teacher_electra_small
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# teacher_electra_small
This model is a fine-tuned version of [google/electra-small-discriminator](https://huggingface.co/google/electra-small-discriminator) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2845
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 1022
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.3902 | 1.99 | 3000 | 0.2789 |
| 0.2522 | 3.98 | 6000 | 0.2845 |
### Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0
- Datasets 2.12.0
- Tokenizers 0.13.2
|
DopeorNope/COKAL_merged_test-v1-13B
|
DopeorNope
| 2024-01-16T01:59:37Z | 64 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"ko",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-12-19T06:51:26Z |
---
language:
- ko
library_name: transformers
pipeline_tag: text-generation
license: cc-by-nc-sa-4.0
tags:
- merge
---
**The license is `cc-by-nc-sa-4.0`.**
**(주)미디어그룹사람과숲과 (주)마커의 LLM 연구 컨소시엄으로 개발된 모델입니다**
# **🐻❄️COKAL_merged_test-v1-13B🐻❄️**
## Model Details
**Model Developers** Seungyoo Lee(DopeorNope)
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture**
COKAL_merged_test-v1-13B is an auto-regressive language model based on the LLaMA2 transformer architecture.
---
## **Base Model**
[HumanF-MarkrAI/COKAL-DPO-13b-v2](https://huggingface.co/HumanF-MarkrAI/COKAL-DPO-13b-v2)
[MarkrAI/DopeorNope-maestro-v2-DPO-13b](https://huggingface.co/MarkrAI/DopeorNope-maestro-v2-DPO-13b)
## **Implemented Method**
I utilized `slerp merge` to smoothly blend the gradients of the base models to create it.
The merging approach relies on some luck, but at the same time, if I have an accurate understanding of my model's performance, I can carefully select models that excel in each aspect to develop a well-balanced model.
Thanks to [maywell](https://huggingface.co/maywell) for sharing useful tips related to the merge method.
---
# **Model Benchmark**
## KO-LLM leaderboard
- Follow up as [Open KO-LLM LeaderBoard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard).
| Model | Average |Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
| --- | --- | --- | --- | --- | --- | --- |
| COKAL_merged_test-v1-13B🐻❄️ | 52.72 | 51.45 | 60.55 | 44.8 | 49.05 | 57.73 |
| [COKAL-DPO-13b-v2🐻❄️](https://huggingface.co/HumanF-MarkrAI/COKAL-DPO-13b-v2) | 52.69 | 54.95 | 63.02 | 43.98 | 51.67 | 49.82 |
| [COKAL-DPO_test-v2-13b🐻❄️](https://huggingface.co/DopeorNope/COKAL-DPO_test-v2-13b) | 52.67 | 55.63 | 63.5 | 43.49 | 51.5 | 49.23 |
| [hyeogi/Yi-6b-dpo-v0.2](https://huggingface.co/hyeogi/Yi-6b-dpo-v0.2) | 52.63 | 41.72 | 52.96 | 46.69 | 52.38 | 69.42 |
| [DopeorNope-maestro-v2-DPO-13b🐻❄️](https://huggingface.co/MarkrAI/DopeorNope-maestro-v2-DPO-13b) | 49.42 | 45.14 | 56.69 | 41.37 | 42.26 | 61.63 |
---
# Implementation Code
## Load model
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "DopeorNope/COKAL_merged_test-v1-13B"
OpenOrca = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)
```
## Prompt (Alpaca format)
```python
prompt= f"아래는 문제를 설명하는 지시사항과, 구체적인 답변을 방식을 요구하는 입력이 함께 있는 문장입니다. 이 요청에 대해 적절하게 답변해주세요.\n\n### 지시사항:\n{instruction}\n\n### 입력:\n{input}\n\n### 답변:\n"
prompt_no_input = f"아래는 문제를 설명하는 지시사항입니다. 이 요청에 대해 적절하게 답변해주세요.\n\n### 지시사항:\n{instruction}\n\n### 답변:\n"
```
# Acknowledgement
- 이 모델은 과학기술정보통신부·광주광역시가 공동 지원한 '인공지능 중심 산업융합 집적단지 조성사업'으로 지원을 받아 수행된 연구 결과입니다.
- This model was supported by Artificial intelligence industrial convergence cluster development project funded by the Ministry of Science and ICT(MSIT, Korea)&Gwangju Metropolitan City.
---
|
mikerjacobi/asteroid-lora-model
|
mikerjacobi
| 2024-01-16T01:58:27Z | 2 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-16T01:55:59Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks asteroids
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - mikerjacobi/model
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks asteroids using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
DopeorNope/Dear_My_best_Friends-v2-13B
|
DopeorNope
| 2024-01-16T01:57:44Z | 2,239 | 1 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"ko",
"dataset:DopeorNope/DPO-Ko-Dataset",
"dataset:DopeorNope/New_Data_Technology",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-11-24T12:10:42Z |
---
language:
- ko
datasets:
- DopeorNope/DPO-Ko-Dataset
- DopeorNope/New_Data_Technology
library_name: transformers
pipeline_tag: text-generation
license: cc-by-nc-sa-4.0
---
**The license is `cc-by-nc-sa-4.0`.**
**(주)미디어그룹사람과숲과 (주)마커의 LLM 연구 컨소시엄으로 개발된 모델입니다**
# **🌙Dear_My_best_Friends-v2-13B🌙**
The main image is generated image using playground AI.
## Model Details
**Model Developers** Seungyoo Lee (DopeorNope)
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture**
Dear_My_best_Friends-13B is an auto-regressive 13B language model based on the LLaMA2 transformer architecture.
**Base Model** [DopeorNope/Dear_My_best_Friend-SFT-v2-13B](https://huggingface.co/DopeorNope/Dear_My_best_Friend-SFT-v2-13B)- not uploaded yet
COKAL_pre_DPO_Test_v3-13b is the SFT model to train the DPO method.
**Training Dataset**
- DPO training dataset: [DopeorNope/DPO-Ko-Dataset](private) - private
This dataset was constructed by directly collecting and reorganizing data by DopeorNope, obtaining insights from ["lvwerra/stack-exchange-paired"](https://huggingface.co/datasets/lvwerra/stack-exchange-paired) to create a paired dataset. (It means I do not use stack-exchange-paired; I just got an insight from it.)
- SFT training dataset: [DopeorNope/New_Data_Technology](private) - private
This dataset is based on ["HumanF-MarkrAI's private data"](private) and has been processed using the Near Dedup algorithm to remove items with a Jaccard Similarity threshold of 0.8 or higher. In addition, inconsistent inputs have been cleaned and modified.
Moreover, I implemented a new method(It is a test version, and I will share it soon).
**Training**
I developed the model in an environment with four RTX 3090 GPUs running Ubuntu 18.04.
It seems that when uploading the model directly to a repository from a Linux server, there may be an issue causing the model to appear to have more parameters. However, this model is based on a 13B architecture.
# Implementation Code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "Dear_My_best_Friends-v2-13B"
model = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
model_tokenizer = AutoTokenizer.from_pretrained(repo)
```
# Acknowledgement
이 모델은 과학기술정보통신부·광주광역시가 공동 지원한 '인공지능 중심 산업융합 집적단지 조성사업'으로 지원을 받아 수행된 연구 결과입니다.
This model was supported by Artificial intelligence industrial convergence cluster development project funded by the Ministry of Science and ICT(MSIT, Korea)&Gwangju Metropolitan City.
---
|
DopeorNope/COKAL-DPO_test-v2-13b
|
DopeorNope
| 2024-01-16T01:54:37Z | 2,256 | 2 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"ko",
"dataset:DopeorNope/DPO-Ko-Dataset",
"dataset:DopeorNope/Orca_Near_Dedup-v2",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-11-09T18:44:41Z |
---
language:
- ko
datasets:
- DopeorNope/DPO-Ko-Dataset
- DopeorNope/Orca_Near_Dedup-v2
library_name: transformers
pipeline_tag: text-generation
license: cc-by-nc-sa-4.0
---
**(주)미디어그룹사람과숲과 (주)마커의 LLM 연구 컨소시엄으로 개발된 모델입니다**
**The license is `cc-by-nc-sa-4.0`.**
# **🐻❄️COKAL-DPO_test-v2🐻❄️**
## Model Details
**Model Developers** Seungyoo Lee (DopeorNope)
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture**
COKAL-DPO_test-v2 is an auto-regressive 13B language model based on the LLaMA2 transformer architecture.
**Base Model** [DopeorNope/COKAL_pre_DPO_Test_v1-13b](https://huggingface.co/DopeorNope/COKAL_pre_DPO_Test_v1-13b)
COKAL_pre_DPO_Test_v1-13b is SFT model to train DPO method
**Training Dataset**
- DPO training dataset: [DopeorNope/DPO-Ko-Dataset](private) - private
This dataset was constructed by directly collecting and reorganizing data by DopeorNope, obtaining insights from ["lvwerra/stack-exchange-paired"](https://huggingface.co/datasets/lvwerra/stack-exchange-paired) to create a paired dataset. (It means I do not use stack-exchange-paired; I just got an insight from it.)
- SFT training dataset: [DopeorNope/Orca_Near_Dedup-v2](private) - private
This dataset is based on ["kyujinpy/OpenOrca-KO"](https://huggingface.co/datasets/kyujinpy/OpenOrca-KO) and has been processed using the Near Dedup algorithm to remove items with a Jaccard Similarity threshold of 0.8 or higher. In addition, inconsistent inputs have been cleaned and modified.
**Training**
I developed the model in an environment with four RTX 3090 GPUs running Ubuntu 18.04.
It seems that when uploading the model directly to a repository from a Linux server, there may be an issue causing the model to appear to have more parameters. However, this model is based on a 13B architecture.
# Implementation Code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "DopeorNope/COKAL-DPO_test-v2"
model = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
model_tokenizer = AutoTokenizer.from_pretrained(repo)
```
# Acknowledgement
- 이 모델은 과학기술정보통신부·광주광역시가 공동 지원한 '인공지능 중심 산업융합 집적단지 조성사업'으로 지원을 받아 수행된 연구 결과입니다.
- This model was supported by Artificial intelligence industrial convergence cluster development project funded by the Ministry of Science and ICT(MSIT, Korea)&Gwangju Metropolitan City.
---
|
HumanF-MarkrAI/COKAL-DPO-13b-v2
|
HumanF-MarkrAI
| 2024-01-16T01:54:13Z | 2,250 | 9 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"ko",
"dataset:DopeorNope/DPO-Ko-Dataset",
"dataset:DopeorNope/Orca_Near_Dedup-v2",
"arxiv:2305.11206",
"arxiv:2107.06499",
"arxiv:2307.09288",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-11-11T06:29:44Z |
---
language:
- ko
datasets:
- DopeorNope/DPO-Ko-Dataset
- DopeorNope/Orca_Near_Dedup-v2
library_name: transformers
pipeline_tag: text-generation
license: cc-by-nc-sa-4.0
---
**(주)미디어그룹사람과숲과 (주)마커의 LLM 연구 컨소시엄으로 개발된 모델입니다**
**The license is `cc-by-nc-sa-4.0`.**
# **🐻❄️COKAL-DPO_13b-v2🐻❄️**
## Model Details
**Model Developers** Seungyoo Lee (DopeorNope)
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture**
COKAL-DPO_13b-v2 is an auto-regressive 13B language model based on the LLaMA2 transformer architecture.
**Base Model** [DopeorNope/COKAL_pre_DPO_Test_v2-13b](https://huggingface.co/DopeorNope/COKAL_pre_DPO_Test_v2-13b)
DopeorNope/COKAL_pre_DPO_Test_v2-13b is the SFT model to train with DPO methodology.
**Training Dataset**
- DPO training dataset: [DopeorNope/DPO-Ko-Dataset](private) - private
This dataset was constructed by directly collecting and reorganizing data by DopeorNope, obtaining insights from ["lvwerra/stack-exchange-paired"](https://huggingface.co/datasets/lvwerra/stack-exchange-paired) to create a paired dataset. (It means I do not use stack-exchange-paired; I just got an insight from it.)
- SFT training dataset: [DopeorNope/Orca_Near_Dedup-v2](private) - private
This dataset is based on ["kyujinpy/OpenOrca-KO"](https://huggingface.co/datasets/kyujinpy/OpenOrca-KO) and has been processed using the Near Dedup algorithm to remove items with a Jaccard Similarity threshold of 0.8 or higher. In addition, inconsistent inputs have been cleaned and modified.
**Training**
The difference between "DopeorNope/COKAL-DPO_test-v2" and this model is that this model has different hyper-parameters from the one in that setting regarding the final version.
I developed the model in an environment with four RTX 3090 GPUs running Ubuntu 18.04.
It seems that when uploading the model directly to a repository from a Linux server, there may be an issue causing the model to appear to have more parameters. However, this model is based on a 13B architecture.
**Reference papers**
- Data Strategy:
- [LIMA(Zhou et al., 2023)](https://arxiv.org/abs/2305.11206)
- [Near Dedup algorithm(Lee et al., 2022)](https://arxiv.org/abs/2107.06499)
- Model Architecture:
- [Llama2(Touvron et al., 2023)](https://arxiv.org/abs/2307.09288)
# Implementation Code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "HumanF-MarkrAI/COKAL-DPO-13b-v2"
model = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
model_tokenizer = AutoTokenizer.from_pretrained(repo)
```
# Acknowledgement
- 이 모델은 과학기술정보통신부·광주광역시가 공동 지원한 '인공지능 중심 산업융합 집적단지 조성사업'으로 지원을 받아 수행된 연구 결과입니다.
- This model was supported by Artificial intelligence industrial convergence cluster development project funded by the Ministry of Science and ICT(MSIT, Korea)&Gwangju Metropolitan City.
---
|
SJ-Donald/kcbert-large-unsmile
|
SJ-Donald
| 2024-01-16T01:42:10Z | 9 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"kcbert",
"unsmile",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-16T01:27:18Z |
---
license: apache-2.0
tags:
- bert
- kcbert
- unsmile
---
# SJ-Donald/kcbert-large-unsmile
SJ-Donald/kcbert-large-unsmile is pretrained model using follow:
## Models
* [beomi/kcbert-large](https://huggingface.co/beomi/kcbert-large)
## Datasets
* [smilegate-ai/kor_unsmile](smilegate-ai/kor_unsmile)
## How to use
```Python
from transformers import TextClassificationPipeline, BertForSequenceClassification, AutoTokenizer+
model_name = 'SJ-Donald/kcbert-large-unsmile'
model = BertForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
pipe = TextClassificationPipeline(
model = model,
tokenizer = tokenizer,
device = 0, # cpu: -1, gpu: gpu number
return_all_scores = True,
function_to_apply = 'sigmoid'
)
for result in pipe("이래서 여자는 게임을 하면 안된다")[0]:
print(result)
{'label': '여성/가족', 'score': 0.9793611168861389}
{'label': '남성', 'score': 0.006330598145723343}
{'label': '성소수자', 'score': 0.007870828732848167}
{'label': '인종/국적', 'score': 0.010810344479978085}
{'label': '연령', 'score': 0.020540334284305573}
{'label': '지역', 'score': 0.015790466219186783}
{'label': '종교', 'score': 0.014563685283064842}
{'label': '기타 혐오', 'score': 0.04097242280840874}
{'label': '악플/욕설', 'score': 0.019168635830283165}
{'label': 'clean', 'score': 0.014866289682686329}
```
|
LGLT/distilbert-base-uncased-finetuned-emotion
|
LGLT
| 2024-01-16T01:37:09Z | 1 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-16T00:43:38Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.936
- name: F1
type: f1
value: 0.9362848609596471
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1737
- Accuracy: 0.936
- F1: 0.9363
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.4271 | 1.0 | 2000 | 0.2148 | 0.9285 | 0.9278 |
| 0.159 | 2.0 | 4000 | 0.1737 | 0.936 | 0.9363 |
### Framework versions
- Transformers 4.32.1
- Pytorch 2.1.2+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2
|
FractalGPT/SbertSVDDistil
|
FractalGPT
| 2024-01-16T01:13:15Z | 6 | 3 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"sentence-transformers",
"feature-extraction",
"sentence-similarity",
"ru",
"en",
"dataset:wikimedia/wikipedia",
"dataset:SiberiaSoft/SiberianPersonaChat-2",
"license:apache-2.0",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2024-01-12T13:20:47Z |
---
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
license: apache-2.0
datasets:
- wikimedia/wikipedia
- SiberiaSoft/SiberianPersonaChat-2
language:
- ru
- en
metrics:
- mse
library_name: transformers
---
# FractalGPT/SbertSVDDistil
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
* [Run example in Collab](https://colab.research.google.com/drive/1R9hHbEpyGEYO5Nw3p5VWTc-bny3PqiZs?hl)
```
pip install -U sentence-transformers -q
```
Then you can use the model like this:
```python
from transformers import BertModel
import numpy as np
import torch
from torch import nn
from sentence_transformers import SentenceTransformer, util
```
```python
class SVDLinearLayer(nn.Module):
def __init__(self, in_features, out_features, h_dim):
super(SVDLinearLayer, self).__init__()
self.encoder = nn.Linear(in_features, h_dim, bias=False)
self.decoder = nn.Linear(h_dim, out_features, bias=True)
def forward(self, x):
x = self.encoder(x)
x = self.decoder(x)
return x
class SVDBertModel(BertModel):
def __init__(self, config):
super(SVDBertModel, self).__init__(config)
for i, layer in enumerate(self.encoder.layer):
intermediate_size = layer.intermediate.dense.out_features
output_size = layer.output.dense.out_features
if i > 0:
layer.intermediate.dense = SVDLinearLayer(layer.intermediate.dense.in_features, intermediate_size, 5)
layer.output.dense = SVDLinearLayer(layer.output.dense.in_features, output_size, 5)
else:
layer.intermediate.dense = nn.Linear(layer.intermediate.dense.in_features, intermediate_size, True)
layer.output.dense = nn.Linear(layer.output.dense.in_features, output_size, True)
def sim(texts_1, texts_2):
embedding_1 = model.encode(texts_1)
embedding_2 = model.encode(texts_2)
s = util.pytorch_cos_sim(embedding_1, embedding_2)
return s.detach().numpy()
```
```python
path = 'FractalGPT/SbertSVDDistil'
model = SentenceTransformer(path)
model[0].auto_model = SVDBertModel.from_pretrained(path) # Правильная загрузка слоев с SVD
```
```python
sim(["I'm happy",
"Transistor (English transistor, an acronym invented in 1947 - from the English transfer + English resistor [1] - for a device for passing current through a resistance), semiconductor triode - an electronic component made of semiconductor material, capable of controlling a significant current into the output with a small input signal circuits, which allows it to be used to amplify, generate, switch and convert electrical signals. Currently, the transistor is the basis of the circuit design of the vast majority of electronic devices and integrated circuits.",
"That is a happy dog",
"Today is a sunny day",
"An electric vacuum triode, or simply triode, is an electronic tube that allows an input signal to control the current in an electrical circuit. It has three electrodes: a thermionic cathode (direct or indirectly heated), an anode and one control grid."],
["Я счастлив",
"Транзи́стор (англ. transistor, придуманный в 1947 году акроним — от англ. transfer + англ. resistor[1] — для устройства пропуска тока через сопротивление), полупроводнико́вый трио́д — электронный компонент из полупроводникового материала, способный небольшим входным сигналом управлять значительным током в выходной цепи, что позволяет использовать его для усиления, генерирования, коммутации и преобразования электрических сигналов. В настоящее время транзистор является основой схемотехники подавляющего большинства электронных устройств и интегральных микросхем.",
"Это счастливая собака",
"Сегодня солнечный день",
"Эле́ктрова́куумный трио́д, или просто трио́д, — электронная лампа, позволяющая входным сигналом управлять током в электрической цепи. Имеет три электрода: термоэлектронный катод (прямого или косвенного накала), анод и одну управляющую сетку."])
```
```
array([[ 0.92624545, -0.1081745 , 0.5569258 , 0.4006917 , 0.0524814 ],
[-0.10137352, 0.9214004 , -0.0590867 , -0.05579955, 0.6043041 ],
[ 0.56128216, -0.08206842, 0.9496383 , 0.23291808, 0.03726077],
[ 0.34002465, -0.05840789, 0.240945 , 0.9276679 , 0.09676868],
[-0.01571994, 0.60077745, -0.00638374, -0.02819303, 0.8434113 ]],
dtype=float32)
```
## Training
* Base model [FractalGPT/SbertDistil](https://huggingface.co/FractalGPT/SbertDistil).
* Log of additional training after decomposition.
<img src="https://github.com/FractalGPT/ModelEmbedderDistillation/blob/main/SbertSVDDistil/Train/en.JPG?raw=true" width=700 />
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: SVDBertModel
(1): Pooling({'word_embedding_dimension': 312, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
(2): Dense({'in_features': 312, 'out_features': 384, 'bias': True, 'activation_function': 'torch.nn.modules.linear.Identity'})
)
```
|
Seokeon/example2
|
Seokeon
| 2024-01-16T01:04:49Z | 0 | 1 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:finetune:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2024-01-15T17:09:26Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - Seokeon/example2
This is a dreambooth model derived from runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
|
JeaHyung/test_trainer
|
JeaHyung
| 2024-01-16T01:01:51Z | 4 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:google-bert/bert-base-cased",
"base_model:finetune:google-bert/bert-base-cased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-16T01:01:23Z |
---
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
model-index:
- name: test_trainer
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# test_trainer
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
CYONG/v2
|
CYONG
| 2024-01-16T00:59:33Z | 1 | 0 |
transformers
|
[
"transformers",
"tf",
"distilbert",
"question-answering",
"generated_from_keras_callback",
"base_model:distilbert/distilbert-base-multilingual-cased",
"base_model:finetune:distilbert/distilbert-base-multilingual-cased",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2024-01-16T00:34:33Z |
---
license: apache-2.0
base_model: distilbert-base-multilingual-cased
tags:
- generated_from_keras_callback
model-index:
- name: CYONG/v2
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# CYONG/v2
This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 1.6834
- Validation Loss: 1.9935
- Epoch: 2
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 500, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 3.2713 | 2.2642 | 0 |
| 1.9407 | 1.9935 | 1 |
| 1.6834 | 1.9935 | 2 |
### Framework versions
- Transformers 4.31.0
- TensorFlow 2.13.0
- Datasets 2.14.3
- Tokenizers 0.13.3
|
Seokeon/example5
|
Seokeon
| 2024-01-16T00:56:11Z | 0 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-16T00:44:30Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Seokeon/example5
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
FractalGPT/SbertDistilAIFr
|
FractalGPT
| 2024-01-16T00:49:09Z | 3 | 0 |
transformers
|
[
"transformers",
"onnx",
"bert",
"feature-extraction",
"AIFramework 2.2 Open",
".net",
"sbert",
"C#",
"ru",
"en",
"dataset:wikimedia/wikipedia",
"dataset:SiberiaSoft/SiberianPersonaChat-2",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2024-01-15T09:40:51Z |
---
license: apache-2.0
datasets:
- wikimedia/wikipedia
- SiberiaSoft/SiberianPersonaChat-2
language:
- ru
- en
metrics:
- mse
tags:
- AIFramework 2.2 Open
- .net
- sbert
- C#
---
### Porting [this model](https://huggingface.co/FractalGPT/SbertDistil) for use in C#
* Example of use in C#:
```csharp
using AI.DataPrepaire.DataLoader.NNWBlockLoader;
using AI.DataStructs.Algebraic;
using AI.ONNX.NLP.Bert;
string path = "SbertDistilAIFr";
// Загрузка модели Bert
BertEmbedder embedder = BertEmbedder.FromPretrained(path);
// Добавление последнего(линейного) слоя
LinearLayerLoader linearLayer = LinearLayerLoader.LoadFromBinary(@$"{path}\1_Linear\model.aifr");
embedder.V2VBlocks.Add(linearLayer);
// Векторизация предложений
Vector vects1 = embedder.ForwardSBert("Kittens love milk");
Vector vects2 = embedder.ForwardSBert("Visual Studio Code (VS Code) — текстовый редактор, разработанный Microsoft для Windows, Linux и macOS.");
Vector vects3 = embedder.ForwardSBert("Visual Studio Code, also commonly referred to as VS Code,[12] is a source-code editor developed by Microsoft for Windows, Linux and macOS.");
Vector vects1_rus = embedder.ForwardSBert("Котята любят молоко");
// Рассчет близости между текстами
Console.WriteLine(vects1.Cos(vects1_rus));
Console.WriteLine(vects1.Cos(vects2));
Console.WriteLine(vects2.Cos(vects3));
Console.WriteLine(vects1.Cos(vects3));
Console.ReadKey();
```
* Network output
```
0.8312274467817271
0.18402859300814606
0.9556528309990797
0.14738954582438052
```
* [GitHub](https://github.com/AIFramework/AIFrameworkOpen)
|
Seokeon/example4
|
Seokeon
| 2024-01-16T00:24:57Z | 1 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-15T17:09:30Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Seokeon/example4
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
gayanin/babylon-clinical-native
|
gayanin
| 2024-01-16T00:13:26Z | 4 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bart",
"text2text-generation",
"generated_from_trainer",
"base_model:facebook/bart-base",
"base_model:finetune:facebook/bart-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2024-01-15T23:24:51Z |
---
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
model-index:
- name: babylon-clinical-native
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# babylon-clinical-native
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4225
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.4838 | 1.51 | 500 | 0.4225 |
### Framework versions
- Transformers 4.36.1
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.0
|
PhaedrusFlow/Gottacatchemall
|
PhaedrusFlow
| 2024-01-16T00:12:26Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"doi:10.57967/hf/1614",
"endpoints_compatible",
"region:us"
] | null | 2024-01-16T00:12:22Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
learn3r/bart_large_gov
|
learn3r
| 2024-01-16T00:10:21Z | 6 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bart",
"text2text-generation",
"generated_from_trainer",
"dataset:learn3r/gov_report_memsum_oracle",
"base_model:facebook/bart-large",
"base_model:finetune:facebook/bart-large",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2024-01-12T11:14:13Z |
---
license: apache-2.0
base_model: facebook/bart-large
tags:
- generated_from_trainer
datasets:
- learn3r/gov_report_memsum_oracle
metrics:
- rouge
model-index:
- name: bart_large_gov
results:
- task:
name: Summarization
type: summarization
dataset:
name: learn3r/gov_report_memsum_oracle
type: learn3r/gov_report_memsum_oracle
metrics:
- name: Rouge1
type: rouge
value: 71.9948
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bart_large_gov
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the learn3r/gov_report_memsum_oracle dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4266
- Rouge1: 71.9948
- Rouge2: 41.0084
- Rougel: 38.0938
- Rougelsum: 69.4488
- Gen Len: 751.0288
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:--------:|
| 1.7352 | 1.0 | 136 | 1.5224 | 72.0472 | 41.3267 | 36.4817 | 69.4011 | 685.9300 |
| 1.6874 | 1.99 | 272 | 1.4779 | 71.7737 | 40.8546 | 36.8472 | 69.2034 | 699.4866 |
| 1.5695 | 3.0 | 409 | 1.4583 | 72.2243 | 41.372 | 37.8382 | 69.6295 | 695.0977 |
| 1.4951 | 3.99 | 545 | 1.4495 | 71.5808 | 40.5556 | 37.152 | 69.0536 | 753.5967 |
| 1.496 | 5.0 | 682 | 1.4386 | 72.1271 | 41.1645 | 38.4096 | 69.6176 | 700.2160 |
| 1.4258 | 6.0 | 818 | 1.4374 | 71.9975 | 41.0013 | 37.9947 | 69.449 | 743.7068 |
| 1.4301 | 7.0 | 955 | 1.4296 | 71.8896 | 40.8303 | 38.346 | 69.357 | 724.5062 |
| 1.4015 | 8.0 | 1091 | 1.4313 | 72.0031 | 40.9229 | 38.2581 | 69.4154 | 731.2685 |
| 1.391 | 8.99 | 1227 | 1.4266 | 71.9948 | 41.0084 | 38.0938 | 69.4488 | 751.0288 |
| 1.3642 | 10.0 | 1364 | 1.4287 | 71.9115 | 40.8683 | 38.1602 | 69.3514 | 756.9568 |
| 1.3516 | 10.99 | 1500 | 1.4289 | 72.3822 | 41.5074 | 38.8088 | 69.8232 | 719.2798 |
| 1.3243 | 12.0 | 1637 | 1.4301 | 71.83 | 40.764 | 38.1124 | 69.2767 | 749.9475 |
| 1.3582 | 12.99 | 1773 | 1.4283 | 71.9495 | 40.9556 | 38.4201 | 69.4394 | 736.6698 |
| 1.3149 | 14.0 | 1910 | 1.4298 | 71.9599 | 40.8875 | 38.2722 | 69.4209 | 753.3230 |
| 1.288 | 15.0 | 2046 | 1.4326 | 72.1615 | 41.1549 | 38.611 | 69.5977 | 744.8858 |
| 1.2937 | 16.0 | 2183 | 1.4315 | 71.9783 | 40.9073 | 38.4263 | 69.4109 | 755.5340 |
| 1.258 | 17.0 | 2319 | 1.4328 | 72.0298 | 40.931 | 38.4845 | 69.4823 | 734.6399 |
| 1.2617 | 17.99 | 2455 | 1.4336 | 71.9488 | 40.8816 | 38.4521 | 69.4151 | 744.7068 |
| 1.2864 | 19.0 | 2592 | 1.4346 | 72.1334 | 40.9965 | 38.5682 | 69.5666 | 744.2449 |
| 1.2936 | 19.94 | 2720 | 1.4351 | 72.0397 | 40.9431 | 38.4161 | 69.5028 | 744.4588 |
### Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.15.0
|
TheBloke/LLaMA2-13B-Estopia-GPTQ
|
TheBloke
| 2024-01-15T23:43:57Z | 51 | 8 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"base_model:KoboldAI/LLaMA2-13B-Estopia",
"base_model:quantized:KoboldAI/LLaMA2-13B-Estopia",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2024-01-15T22:59:02Z |
---
base_model: KoboldAI/LLaMA2-13B-Estopia
inference: false
license: cc-by-nc-4.0
model_creator: KoboldAI
model_name: Llama2 13B Estopia
model_type: llama
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'
quantized_by: TheBloke
tags:
- mergekit
- merge
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Llama2 13B Estopia - GPTQ
- Model creator: [KoboldAI](https://huggingface.co/KoboldAI)
- Original model: [Llama2 13B Estopia](https://huggingface.co/KoboldAI/LLaMA2-13B-Estopia)
<!-- description start -->
# Description
This repo contains GPTQ model files for [KoboldAI's Llama2 13B Estopia](https://huggingface.co/KoboldAI/LLaMA2-13B-Estopia).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GGUF)
* [KoboldAI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/KoboldAI/LLaMA2-13B-Estopia)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `cc-by-nc-4.0`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [KoboldAI's Llama2 13B Estopia](https://huggingface.co/KoboldAI/LLaMA2-13B-Estopia).
<!-- licensing end -->
<!-- README_GPTQ.md-compatible clients start -->
## Known compatible clients / servers
GPTQ models are currently supported on Linux (NVidia/AMD) and Windows (NVidia only). macOS users: please use GGUF models.
These GPTQ models are known to work in the following inference servers/webuis.
- [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
- [KoboldAI United](https://github.com/henk717/koboldai)
- [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
This may not be a complete list; if you know of others, please let me know!
<!-- README_GPTQ.md-compatible clients end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama and Mistral models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 7.26 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 8.00 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 14.54 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 7.51 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download, including from branches
### In text-generation-webui
To download from the `main` branch, enter `TheBloke/LLaMA2-13B-Estopia-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/LLaMA2-13B-Estopia-GPTQ:gptq-4bit-32g-actorder_True`
### From the command line
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `LLaMA2-13B-Estopia-GPTQ`:
```shell
mkdir LLaMA2-13B-Estopia-GPTQ
huggingface-cli download TheBloke/LLaMA2-13B-Estopia-GPTQ --local-dir LLaMA2-13B-Estopia-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir LLaMA2-13B-Estopia-GPTQ
huggingface-cli download TheBloke/LLaMA2-13B-Estopia-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir LLaMA2-13B-Estopia-GPTQ --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
mkdir LLaMA2-13B-Estopia-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/LLaMA2-13B-Estopia-GPTQ --local-dir LLaMA2-13B-Estopia-GPTQ --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
### With `git` (**not** recommended)
To clone a specific branch with `git`, use a command like this:
```shell
git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GPTQ
```
Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/LLaMA2-13B-Estopia-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/LLaMA2-13B-Estopia-GPTQ:gptq-4bit-32g-actorder_True`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `LLaMA2-13B-Estopia-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
- Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-tgi start -->
## Serving this model from Text Generation Inference (TGI)
It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/LLaMA2-13B-Estopia-GPTQ --port 3000 --quantize gptq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(
prompt_template,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(f"Model output: {response}")
```
<!-- README_GPTQ.md-use-from-tgi end -->
<!-- README_GPTQ.md-use-from-python start -->
## Python code example: inference from this GPTQ model
### Install the necessary packages
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install --upgrade transformers optimum
# If using PyTorch 2.1 + CUDA 12.x:
pip3 install --upgrade auto-gptq
# or, if using PyTorch 2.1 + CUDA 11.x:
pip3 install --upgrade auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
```
If you are using PyTorch 2.0, you will need to install AutoGPTQ from source. Likewise if you have problems with the pre-built wheels, you should try building from source:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.5.1
pip3 install .
```
### Example Python code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/LLaMA2-13B-Estopia-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-32g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Write a story about llamas"
system_message = "You are a story writing assistant"
prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with Transformers. For non-Mistral models, AutoGPTQ can also be used directly.
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama architecture models (including Mistral, Yi, DeepSeek, SOLAR, etc) in 4-bit. Please see the Provided Files table above for per-file compatibility.
For a list of clients/servers, please see "Known compatible clients / servers", above.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: KoboldAI's Llama2 13B Estopia
# Introduction
- Estopia is a model focused on improving the dialogue and prose returned when using the instruct format. As a side benefit, character cards and similar seem to have also improved, remembering details well in many cases.
- It focuses on "guided narratives" - using instructions to guide or explore fictional stories, where you act as a guide for the AI to narrate and fill in the details.
- It has primarily been tested around prose, using instructions to guide narrative, detail retention and "neutrality" - in particular with regards to plot armour. Unless you define different rules for your adventure / narrative with instructions, it should be realistic in the responses provided.
- It has been tested using different modes, such as instruct, chat, adventure and story modes - and should be able to do them all to a degree, with it's strengths being instruct and adventure, with story being a close second.
# Usage
- The Estopia model has been tested primarily using the Alpaca format, but with the range of models included likely has some understanding of others. Some examples of tested formats are below:
- ```\n### Instruction:\nWhat colour is the sky?\n### Response:\nThe sky is...```
- ```<Story text>\n***\nWrite a summary of the text above\n***\nThe story starts by...```
- Using the Kobold Lite AI adventure mode
- ```User:Hello there!\nAssistant:Good morning...\n```
- For settings, the following are recommended for general use:
- Temperature: 0.8-1.2
- Min P: 0.05-0.1
- Max P: 0.92, or 1 if using a Min P greater than 0
- Top K: 0
- Response length: Higher than your usual amount most likely - for example a common value selected is 512.
- Note: Response lengths are not guaranteed to always be this length. On occasion, responses may be shorter if they convey the response entirely, other times they could be upwards of this value. It depends mostly on the character card, instructions, etc.
- Rep Pen: 1.1
- Rep Pen Range: 2 or 3x your response length
- Stopping tokens (Not needed, but can help if the AI is writing too much):
- ```##||$||---||$||ASSISTANT:||$||[End||$||</s>``` - A single string for Kobold Lite combining the ones below
- ```##```
- ```---```
- ```ASSISTANT:```
- ```[End```
- ```</s>```
- The settings above should provide a generally good experience balancing instruction following and creativity. Generally the higher you set the temperature, the greater the creativity and higher chance of logical errors when providing responses from the AI.
# Recipe
This model was made in three stages, along with many experimental stages which will be skipped for brevity. The first was internally referred to as EstopiaV9, which has a high degree of instruction following and creativity in responses, though they were generally shorter and a little more restricted in the scope of outputs, but conveyed nuance better.
```yaml
merge_method: task_arithmetic
base_model: TheBloke/Llama-2-13B-fp16
models:
- model: TheBloke/Llama-2-13B-fp16
- model: Undi95/UtopiaXL-13B
parameters:
weight: 1.0
- model: Doctor-Shotgun/cat-v1.0-13b
parameters:
weight: 0.02
- model: PygmalionAI/mythalion-13b
parameters:
weight: 0.10
- model: Undi95/Emerhyst-13B
parameters:
weight: 0.05
- model: CalderaAI/13B-Thorns-l2
parameters:
weight: 0.05
- model: KoboldAI/LLaMA2-13B-Tiefighter
parameters:
weight: 0.20
dtype: float16
```
The second part of the merge was known as EstopiaV13. This produced responses which were long, but tended to write beyond good stopping points for further instructions to be added as it leant heavily on novel style prose. It did however benefit from a greater degree of neutrality as described above, and retained many of the detail tracking abilities of V9.
```yaml
merge_method: task_arithmetic
base_model: TheBloke/Llama-2-13B-fp16
models:
- model: TheBloke/Llama-2-13B-fp16
- model: Undi95/UtopiaXL-13B
parameters:
weight: 1.0
- model: Doctor-Shotgun/cat-v1.0-13b
parameters:
weight: 0.01
- model: chargoddard/rpguild-chatml-13b
parameters:
weight: 0.02
- model: PygmalionAI/mythalion-13b
parameters:
weight: 0.08
- model: CalderaAI/13B-Thorns-l2
parameters:
weight: 0.02
- model: KoboldAI/LLaMA2-13B-Tiefighter
parameters:
weight: 0.20
dtype: float16
```
The third step was a merge between the two to retain the benefits of both as much as possible. This was performed using the dare merging technique.
```yaml
# task-arithmetic style
models:
- model: EstopiaV9
parameters:
weight: 1
density: 1
- model: EstopiaV13
parameters:
weight: 0.05
density: 0.30
merge_method: dare_ties
base_model: TheBloke/Llama-2-13B-fp16
parameters:
int8_mask: true
dtype: bfloat16
```
# Model selection
- Undi95/UtopiaXL-13B
- Solid all around base for models, with the ability to write longer responses and generally good retension to detail.
- Doctor-Shotgun/cat-v1.0-13b
- A medical focused model which is added to focus a little more on the human responses, such as for psycology.
- PygmalionAI/mythalion-13b
- A roleplay and instruct focused model, which improves attentiveness to character card details and the variety of responses
- Undi95/Emerhyst-13B
- A roleplay but also longer form response model. It can be quite variable, but helps add to the depth and possible options the AI can respond with during narratives.
- CalderaAI/13B-Thorns-l2
- A neutral and very attentive model. It is good at chat and following instructions, which help benefit these modes.
- KoboldAI/LLaMA2-13B-Tiefighter
- A solid all around model, focusing on story writing and adventure modes. It provides all around benefits to creativity and the prose in models, along with adventure mode support.
- chargoddard/rpguild-chatml-13b
- A roleplay model, which introduces new data and also improves the detail retention in longer narratives.
# Notes
- With the differing models inside, this model will not have perfect end of sequence tokens which is a problem many merges can share. While attempts have been made to minimise this, you may occasionally get oddly behaving tokens - this should be possible to resolve with a quick manual edit once and the model should pick up on it.
- Chat is one of the least tested areas for this model. It works fairly well, but it can be quite character card dependant.
- This is a narrative and prose focused model. As a result, it can and will talk for you if guided to do so (such as asking it to act as a co-author or narrator) within instructions or other contexts. This can be mitigated mostly by adding instructions to limit this, or using chat mode instead.
# Future areas
- Llava
- Some success has been had with merging the llava lora on this. While no in depth testing has been performed, more narrative responses based on the images could be obtained - though there were drawbacks in the form of degraded performance in other areas, and hallucinations due to the fictional focus of this model.
- Stheno
- A merge which has similar promise from Sao. Some merge attempts have been made between the two and were promising, but not entirely consistent at the moment. With some possible refinement, this could produce an even stronger model.
- DynamicFactor
- All the merges used have been based on llama two in this merge, but a dare merge with dynamic factor (an attempted refinement of llama two) showed a beneficial improvement to the instruction abilities of the model, along with lengthy responses. It lost a little of the variety of responses, so perhaps if a balance of it could be added the instruction abilities and reasoning could be improved even further.
|
dylanebert/4K4D
|
dylanebert
| 2024-01-15T23:32:16Z | 0 | 6 | null |
[
"image-to-3d",
"arxiv:2310.11448",
"license:other",
"region:us"
] |
image-to-3d
| 2024-01-15T23:25:21Z |
---
license: other
pipeline_tag: image-to-3d
---
Model for [4K4D: Real-Time 4D View Synthesis at 4K Resolution](https://huggingface.co/papers/2310.11448).
Originally hosted on [Drive](https://drive.google.com/drive/folders/1mBMsYeXawU_sF3NFyuWC1hnfrYbSfDfi?usp=sharing).
|
KaiKapioka/mistral-finetuned-samsum
|
KaiKapioka
| 2024-01-15T23:31:51Z | 3 | 0 |
peft
|
[
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TheBloke/una-cybertron-7B-v3-OMA-GPTQ",
"base_model:adapter:TheBloke/una-cybertron-7B-v3-OMA-GPTQ",
"license:apache-2.0",
"region:us"
] | null | 2024-01-15T19:16:24Z |
---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TheBloke/una-cybertron-7B-v3-OMA-GPTQ
model-index:
- name: mistral-finetuned-samsum
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mistral-finetuned-samsum
This model is a fine-tuned version of [TheBloke/una-cybertron-7B-v3-OMA-GPTQ](https://huggingface.co/TheBloke/una-cybertron-7B-v3-OMA-GPTQ) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.7.1
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
|
alexsherstinsky/llama-2-7b-based-finetuned-using-ludwig-with-jigsaw-toxicity-classification-T4-4bit-notmerged
|
alexsherstinsky
| 2024-01-15T23:20:03Z | 2 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:adapter:meta-llama/Llama-2-7b-hf",
"region:us"
] | null | 2023-12-27T01:29:10Z |
---
library_name: peft
base_model: meta-llama/Llama-2-7b-hf
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.1
|
TheBloke/LLaMA2-13B-Estopia-GGUF
|
TheBloke
| 2024-01-15T22:59:09Z | 403 | 8 |
transformers
|
[
"transformers",
"gguf",
"llama",
"mergekit",
"merge",
"base_model:KoboldAI/LLaMA2-13B-Estopia",
"base_model:quantized:KoboldAI/LLaMA2-13B-Estopia",
"license:cc-by-nc-4.0",
"region:us"
] | null | 2024-01-15T22:39:05Z |
---
base_model: KoboldAI/LLaMA2-13B-Estopia
inference: false
license: cc-by-nc-4.0
model_creator: KoboldAI
model_name: Llama2 13B Estopia
model_type: llama
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'
quantized_by: TheBloke
tags:
- mergekit
- merge
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Llama2 13B Estopia - GGUF
- Model creator: [KoboldAI](https://huggingface.co/KoboldAI)
- Original model: [Llama2 13B Estopia](https://huggingface.co/KoboldAI/LLaMA2-13B-Estopia)
<!-- description start -->
## Description
This repo contains GGUF format model files for [KoboldAI's Llama2 13B Estopia](https://huggingface.co/KoboldAI/LLaMA2-13B-Estopia).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GGUF)
* [KoboldAI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/KoboldAI/LLaMA2-13B-Estopia)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `cc-by-nc-4.0`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [KoboldAI's Llama2 13B Estopia](https://huggingface.co/KoboldAI/LLaMA2-13B-Estopia).
<!-- licensing end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [llama2-13b-estopia.Q2_K.gguf](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GGUF/blob/main/llama2-13b-estopia.Q2_K.gguf) | Q2_K | 2 | 4.85 GB| 7.35 GB | significant quality loss - not recommended for most purposes |
| [llama2-13b-estopia.Q3_K_S.gguf](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GGUF/blob/main/llama2-13b-estopia.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |
| [llama2-13b-estopia.Q3_K_M.gguf](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GGUF/blob/main/llama2-13b-estopia.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |
| [llama2-13b-estopia.Q3_K_L.gguf](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GGUF/blob/main/llama2-13b-estopia.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |
| [llama2-13b-estopia.Q4_0.gguf](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GGUF/blob/main/llama2-13b-estopia.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [llama2-13b-estopia.Q4_K_S.gguf](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GGUF/blob/main/llama2-13b-estopia.Q4_K_S.gguf) | Q4_K_S | 4 | 7.42 GB| 9.92 GB | small, greater quality loss |
| [llama2-13b-estopia.Q4_K_M.gguf](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GGUF/blob/main/llama2-13b-estopia.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
| [llama2-13b-estopia.Q5_0.gguf](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GGUF/blob/main/llama2-13b-estopia.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [llama2-13b-estopia.Q5_K_S.gguf](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GGUF/blob/main/llama2-13b-estopia.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
| [llama2-13b-estopia.Q5_K_M.gguf](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GGUF/blob/main/llama2-13b-estopia.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
| [llama2-13b-estopia.Q6_K.gguf](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GGUF/blob/main/llama2-13b-estopia.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |
| [llama2-13b-estopia.Q8_0.gguf](https://huggingface.co/TheBloke/LLaMA2-13B-Estopia-GGUF/blob/main/llama2-13b-estopia.Q8_0.gguf) | Q8_0 | 8 | 13.83 GB| 16.33 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/LLaMA2-13B-Estopia-GGUF and below it, a specific filename to download, such as: llama2-13b-estopia.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/LLaMA2-13B-Estopia-GGUF llama2-13b-estopia.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/LLaMA2-13B-Estopia-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/LLaMA2-13B-Estopia-GGUF llama2-13b-estopia.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m llama2-13b-estopia.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./llama2-13b-estopia.Q4_K_M.gguf", # Download the model file first
n_ctx=4096, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./llama2-13b-estopia.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: KoboldAI's Llama2 13B Estopia
# Introduction
- Estopia is a model focused on improving the dialogue and prose returned when using the instruct format. As a side benefit, character cards and similar seem to have also improved, remembering details well in many cases.
- It focuses on "guided narratives" - using instructions to guide or explore fictional stories, where you act as a guide for the AI to narrate and fill in the details.
- It has primarily been tested around prose, using instructions to guide narrative, detail retention and "neutrality" - in particular with regards to plot armour. Unless you define different rules for your adventure / narrative with instructions, it should be realistic in the responses provided.
- It has been tested using different modes, such as instruct, chat, adventure and story modes - and should be able to do them all to a degree, with it's strengths being instruct and adventure, with story being a close second.
# Usage
- The Estopia model has been tested primarily using the Alpaca format, but with the range of models included likely has some understanding of others. Some examples of tested formats are below:
- ```\n### Instruction:\nWhat colour is the sky?\n### Response:\nThe sky is...```
- ```<Story text>\n***\nWrite a summary of the text above\n***\nThe story starts by...```
- Using the Kobold Lite AI adventure mode
- ```User:Hello there!\nAssistant:Good morning...\n```
- For settings, the following are recommended for general use:
- Temperature: 0.8-1.2
- Min P: 0.05-0.1
- Max P: 0.92, or 1 if using a Min P greater than 0
- Top K: 0
- Response length: Higher than your usual amount most likely - for example a common value selected is 512.
- Note: Response lengths are not guaranteed to always be this length. On occasion, responses may be shorter if they convey the response entirely, other times they could be upwards of this value. It depends mostly on the character card, instructions, etc.
- Rep Pen: 1.1
- Rep Pen Range: 2 or 3x your response length
- Stopping tokens (Not needed, but can help if the AI is writing too much):
- ```##||$||---||$||ASSISTANT:||$||[End||$||</s>``` - A single string for Kobold Lite combining the ones below
- ```##```
- ```---```
- ```ASSISTANT:```
- ```[End```
- ```</s>```
- The settings above should provide a generally good experience balancing instruction following and creativity. Generally the higher you set the temperature, the greater the creativity and higher chance of logical errors when providing responses from the AI.
# Recipe
This model was made in three stages, along with many experimental stages which will be skipped for brevity. The first was internally referred to as EstopiaV9, which has a high degree of instruction following and creativity in responses, though they were generally shorter and a little more restricted in the scope of outputs, but conveyed nuance better.
```yaml
merge_method: task_arithmetic
base_model: TheBloke/Llama-2-13B-fp16
models:
- model: TheBloke/Llama-2-13B-fp16
- model: Undi95/UtopiaXL-13B
parameters:
weight: 1.0
- model: Doctor-Shotgun/cat-v1.0-13b
parameters:
weight: 0.02
- model: PygmalionAI/mythalion-13b
parameters:
weight: 0.10
- model: Undi95/Emerhyst-13B
parameters:
weight: 0.05
- model: CalderaAI/13B-Thorns-l2
parameters:
weight: 0.05
- model: KoboldAI/LLaMA2-13B-Tiefighter
parameters:
weight: 0.20
dtype: float16
```
The second part of the merge was known as EstopiaV13. This produced responses which were long, but tended to write beyond good stopping points for further instructions to be added as it leant heavily on novel style prose. It did however benefit from a greater degree of neutrality as described above, and retained many of the detail tracking abilities of V9.
```yaml
merge_method: task_arithmetic
base_model: TheBloke/Llama-2-13B-fp16
models:
- model: TheBloke/Llama-2-13B-fp16
- model: Undi95/UtopiaXL-13B
parameters:
weight: 1.0
- model: Doctor-Shotgun/cat-v1.0-13b
parameters:
weight: 0.01
- model: chargoddard/rpguild-chatml-13b
parameters:
weight: 0.02
- model: PygmalionAI/mythalion-13b
parameters:
weight: 0.08
- model: CalderaAI/13B-Thorns-l2
parameters:
weight: 0.02
- model: KoboldAI/LLaMA2-13B-Tiefighter
parameters:
weight: 0.20
dtype: float16
```
The third step was a merge between the two to retain the benefits of both as much as possible. This was performed using the dare merging technique.
```yaml
# task-arithmetic style
models:
- model: EstopiaV9
parameters:
weight: 1
density: 1
- model: EstopiaV13
parameters:
weight: 0.05
density: 0.30
merge_method: dare_ties
base_model: TheBloke/Llama-2-13B-fp16
parameters:
int8_mask: true
dtype: bfloat16
```
# Model selection
- Undi95/UtopiaXL-13B
- Solid all around base for models, with the ability to write longer responses and generally good retension to detail.
- Doctor-Shotgun/cat-v1.0-13b
- A medical focused model which is added to focus a little more on the human responses, such as for psycology.
- PygmalionAI/mythalion-13b
- A roleplay and instruct focused model, which improves attentiveness to character card details and the variety of responses
- Undi95/Emerhyst-13B
- A roleplay but also longer form response model. It can be quite variable, but helps add to the depth and possible options the AI can respond with during narratives.
- CalderaAI/13B-Thorns-l2
- A neutral and very attentive model. It is good at chat and following instructions, which help benefit these modes.
- KoboldAI/LLaMA2-13B-Tiefighter
- A solid all around model, focusing on story writing and adventure modes. It provides all around benefits to creativity and the prose in models, along with adventure mode support.
- chargoddard/rpguild-chatml-13b
- A roleplay model, which introduces new data and also improves the detail retention in longer narratives.
# Notes
- With the differing models inside, this model will not have perfect end of sequence tokens which is a problem many merges can share. While attempts have been made to minimise this, you may occasionally get oddly behaving tokens - this should be possible to resolve with a quick manual edit once and the model should pick up on it.
- Chat is one of the least tested areas for this model. It works fairly well, but it can be quite character card dependant.
- This is a narrative and prose focused model. As a result, it can and will talk for you if guided to do so (such as asking it to act as a co-author or narrator) within instructions or other contexts. This can be mitigated mostly by adding instructions to limit this, or using chat mode instead.
# Future areas
- Llava
- Some success has been had with merging the llava lora on this. While no in depth testing has been performed, more narrative responses based on the images could be obtained - though there were drawbacks in the form of degraded performance in other areas, and hallucinations due to the fictional focus of this model.
- Stheno
- A merge which has similar promise from Sao. Some merge attempts have been made between the two and were promising, but not entirely consistent at the moment. With some possible refinement, this could produce an even stronger model.
- DynamicFactor
- All the merges used have been based on llama two in this merge, but a dare merge with dynamic factor (an attempted refinement of llama two) showed a beneficial improvement to the instruction abilities of the model, along with lengthy responses. It lost a little of the variety of responses, so perhaps if a balance of it could be added the instruction abilities and reasoning could be improved even further.
<!-- original-model-card end -->
|
dylanebert/SyncDreamer
|
dylanebert
| 2024-01-15T22:35:48Z | 0 | 4 | null |
[
"image-to-3d",
"arxiv:2309.03453",
"license:mit",
"region:us"
] |
image-to-3d
| 2024-01-15T22:32:47Z |
---
license: mit
pipeline_tag: image-to-3d
---
Model for [SyncDreamer: Generating Multiview-consistent Images from a Single-view Image](https://huggingface.co/papers/2309.03453).
Originally hosted on [OneDrive](https://connecthkuhk-my.sharepoint.com/:f:/g/personal/yuanly_connect_hku_hk/EjYHbCBnV-VPjBqNHdNulIABq9sYAEpSz4NPLDI72a85vw).
|
pocasrocas/recipe-gantt-v0.1
|
pocasrocas
| 2024-01-15T22:29:19Z | 14 | 0 | null |
[
"gguf",
"food",
"text2text-generation",
"en",
"dataset:pocasrocas/recipe-gantt",
"license:mit",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2024-01-15T15:03:31Z |
---
license: mit
pipeline_tag: text2text-generation
tags:
- food
datasets:
- pocasrocas/recipe-gantt
language:
- en
---
## Model Summary
recipe-gantt is a monotask language model to translate recipes into gantt charts in a TSV format.
It is a QLoRA finetune of [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the [pocasrocas/recipe-gantt](https://huggingface.co/datasets/pocasrocas/recipe-gantt) dataset. I then used [llama.cpp](https://github.com/ggerganov/llama.cpp) to convert it to .gguf format for fast local inference.
## Intended use
To create recipe gantt charts and recipe gantt charts only 🧑🍳
It's released here to accompany the [recipe-gantt tool](https://github.com/jbremz/recipe-gantt).
## Input format
The model was trained with the [alpaca](https://github.com/tatsu-lab/stanford_alpaca?tab=readme-ov-file#data-release) instruction/input/response prompt format. Exact details on the expected input can be inferred from the inference code [here](https://github.com/jbremz/recipe-gantt/blob/main/recipe-gantt.py).
## Limitations
- the model will inherit any limitations of the parent model (Mistral-7B-v0.1)
- it was finetuned on a tiny synthetic dataset of only 288 examples so sometimes produces corrupted TSV files and populates cells inaccurately.
## Training
- QLoRA finetune using [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl)
- ~1hr on NVIDIA GeForce RTX 3090 Ti ([wandb](https://wandb.ai/pocasrocas/recipe-gantt/runs/1ostj66y?workspace=user-pocasrocas))
- Training code [here](https://github.com/jbremz/recipe-gantt/tree/720a7e1b3594c03b46209671271fe3c2159fff16/notebooks/002-train)
|
wooseok0303/xlm-roberta-base-finetuned-panx-all
|
wooseok0303
| 2024-01-15T22:22:24Z | 3 | 0 |
transformers
|
[
"transformers",
"safetensors",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-12-25T14:22:34Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-all
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# xlm-roberta-base-finetuned-panx-all
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1742
- F1: 0.8559
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.2918 | 1.0 | 835 | 0.2059 | 0.8093 |
| 0.1558 | 2.0 | 1670 | 0.1755 | 0.8454 |
| 0.1018 | 3.0 | 2505 | 0.1742 | 0.8559 |
### Framework versions
- Transformers 4.36.2
- Pytorch 1.13.1+cu116
- Datasets 2.16.1
- Tokenizers 0.15.0
|
TheBloke/finance-LLM-13B-GGUF
|
TheBloke
| 2024-01-15T22:07:55Z | 665 | 17 |
transformers
|
[
"transformers",
"gguf",
"llama",
"finance",
"text-generation",
"en",
"dataset:Open-Orca/OpenOrca",
"dataset:GAIR/lima",
"dataset:WizardLM/WizardLM_evol_instruct_V2_196k",
"arxiv:2309.09530",
"base_model:AdaptLLM/finance-LLM-13B",
"base_model:quantized:AdaptLLM/finance-LLM-13B",
"license:other",
"region:us"
] |
text-generation
| 2024-01-15T22:00:36Z |
---
base_model: AdaptLLM/finance-LLM-13B
datasets:
- Open-Orca/OpenOrca
- GAIR/lima
- WizardLM/WizardLM_evol_instruct_V2_196k
inference: false
language:
- en
license: other
metrics:
- accuracy
model_creator: AdaptLLM
model_name: Finance LLM 13B
model_type: llama
pipeline_tag: text-generation
prompt_template: '### User Input:
{prompt}
### Assistant Output:
'
quantized_by: TheBloke
tags:
- finance
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Finance LLM 13B - GGUF
- Model creator: [AdaptLLM](https://huggingface.co/AdaptLLM)
- Original model: [Finance LLM 13B](https://huggingface.co/AdaptLLM/finance-LLM-13B)
<!-- description start -->
## Description
This repo contains GGUF format model files for [AdaptLLM's Finance LLM 13B](https://huggingface.co/AdaptLLM/finance-LLM-13B).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/finance-LLM-13B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/finance-LLM-13B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/finance-LLM-13B-GGUF)
* [AdaptLLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/AdaptLLM/finance-LLM-13B)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: AdaptLLM
```
### User Input:
{prompt}
### Assistant Output:
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [finance-llm-13b.Q2_K.gguf](https://huggingface.co/TheBloke/finance-LLM-13B-GGUF/blob/main/finance-llm-13b.Q2_K.gguf) | Q2_K | 2 | 4.85 GB| 7.35 GB | significant quality loss - not recommended for most purposes |
| [finance-llm-13b.Q3_K_S.gguf](https://huggingface.co/TheBloke/finance-LLM-13B-GGUF/blob/main/finance-llm-13b.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |
| [finance-llm-13b.Q3_K_M.gguf](https://huggingface.co/TheBloke/finance-LLM-13B-GGUF/blob/main/finance-llm-13b.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |
| [finance-llm-13b.Q3_K_L.gguf](https://huggingface.co/TheBloke/finance-LLM-13B-GGUF/blob/main/finance-llm-13b.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |
| [finance-llm-13b.Q4_0.gguf](https://huggingface.co/TheBloke/finance-LLM-13B-GGUF/blob/main/finance-llm-13b.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [finance-llm-13b.Q4_K_S.gguf](https://huggingface.co/TheBloke/finance-LLM-13B-GGUF/blob/main/finance-llm-13b.Q4_K_S.gguf) | Q4_K_S | 4 | 7.42 GB| 9.92 GB | small, greater quality loss |
| [finance-llm-13b.Q4_K_M.gguf](https://huggingface.co/TheBloke/finance-LLM-13B-GGUF/blob/main/finance-llm-13b.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
| [finance-llm-13b.Q5_0.gguf](https://huggingface.co/TheBloke/finance-LLM-13B-GGUF/blob/main/finance-llm-13b.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [finance-llm-13b.Q5_K_S.gguf](https://huggingface.co/TheBloke/finance-LLM-13B-GGUF/blob/main/finance-llm-13b.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
| [finance-llm-13b.Q5_K_M.gguf](https://huggingface.co/TheBloke/finance-LLM-13B-GGUF/blob/main/finance-llm-13b.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
| [finance-llm-13b.Q6_K.gguf](https://huggingface.co/TheBloke/finance-LLM-13B-GGUF/blob/main/finance-llm-13b.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |
| [finance-llm-13b.Q8_0.gguf](https://huggingface.co/TheBloke/finance-LLM-13B-GGUF/blob/main/finance-llm-13b.Q8_0.gguf) | Q8_0 | 8 | 13.83 GB| 16.33 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/finance-LLM-13B-GGUF and below it, a specific filename to download, such as: finance-llm-13b.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/finance-LLM-13B-GGUF finance-llm-13b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/finance-LLM-13B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/finance-LLM-13B-GGUF finance-llm-13b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m finance-llm-13b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### User Input:\n{prompt}\n\n### Assistant Output:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./finance-llm-13b.Q4_K_M.gguf", # Download the model file first
n_ctx=2048, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"### User Input:\n{prompt}\n\n### Assistant Output:", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./finance-llm-13b.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: AdaptLLM's Finance LLM 13B
# Adapt (Large) Language Models to Domains
This repo contains the domain-specific base model developed from **LLaMA-1-13B**, using the method in our paper [Adapting Large Language Models via Reading Comprehension](https://huggingface.co/papers/2309.09530).
We explore **continued pre-training on domain-specific corpora** for large language models. While this approach enriches LLMs with domain knowledge, it significantly hurts their prompting ability for question answering. Inspired by human learning via reading comprehension, we propose a simple method to **transform large-scale pre-training corpora into reading comprehension texts**, consistently improving prompting performance across tasks in biomedicine, finance, and law domains. **Our 7B model competes with much larger domain-specific models like BloombergGPT-50B**.
### 🤗 We are currently working hard on developing models across different domains, scales and architectures! Please stay tuned! 🤗
**************************** **Updates** ****************************
* 12/19: Released our [13B base models](https://huggingface.co/AdaptLLM/finance-LLM-13B) developed from LLaMA-1-13B.
* 12/8: Released our [chat models](https://huggingface.co/AdaptLLM/finance-chat) developed from LLaMA-2-Chat-7B.
* 9/18: Released our [paper](https://huggingface.co/papers/2309.09530), [code](https://github.com/microsoft/LMOps), [data](https://huggingface.co/datasets/AdaptLLM/finance-tasks), and [base models](https://huggingface.co/AdaptLLM/finance-LLM) developed from LLaMA-1-7B.
## Domain-Specific LLaMA-1
### LLaMA-1-7B
In our paper, we develop three domain-specific models from LLaMA-1-7B, which are also available in Huggingface: [Biomedicine-LLM](https://huggingface.co/AdaptLLM/medicine-LLM), [Finance-LLM](https://huggingface.co/AdaptLLM/finance-LLM) and [Law-LLM](https://huggingface.co/AdaptLLM/law-LLM), the performances of our AdaptLLM compared to other domain-specific LLMs are:
<p align='center'>
<img src="https://cdn-uploads.huggingface.co/production/uploads/650801ced5578ef7e20b33d4/6efPwitFgy-pLTzvccdcP.png" width="700">
</p>
### LLaMA-1-13B
Moreover, we scale up our base model to LLaMA-1-13B to see if **our method is similarly effective for larger-scale models**, and the results are consistently positive too: [Biomedicine-LLM-13B](https://huggingface.co/AdaptLLM/medicine-LLM-13B), [Finance-LLM-13B](https://huggingface.co/AdaptLLM/finance-LLM-13B) and [Law-LLM-13B](https://huggingface.co/AdaptLLM/law-LLM-13B).
## Domain-Specific LLaMA-2-Chat
Our method is also effective for aligned models! LLaMA-2-Chat requires a [specific data format](https://huggingface.co/blog/llama2#how-to-prompt-llama-2), and our **reading comprehension can perfectly fit the data format** by transforming the reading comprehension into a multi-turn conversation. We have also open-sourced chat models in different domains: [Biomedicine-Chat](https://huggingface.co/AdaptLLM/medicine-chat), [Finance-Chat](https://huggingface.co/AdaptLLM/finance-chat) and [Law-Chat](https://huggingface.co/AdaptLLM/law-chat)
For example, to chat with the finance model:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("AdaptLLM/finance-LLM-13B")
tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/finance-LLM-13B", use_fast=False)
# Put your input here:
user_input = '''Use this fact to answer the question: Title of each class Trading Symbol(s) Name of each exchange on which registered
Common Stock, Par Value $.01 Per Share MMM New York Stock Exchange
MMM Chicago Stock Exchange, Inc.
1.500% Notes due 2026 MMM26 New York Stock Exchange
1.750% Notes due 2030 MMM30 New York Stock Exchange
1.500% Notes due 2031 MMM31 New York Stock Exchange
Which debt securities are registered to trade on a national securities exchange under 3M's name as of Q2 of 2023?'''
# Simply use your input as the prompt for base models
prompt = user_input
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).input_ids.to(model.device)
outputs = model.generate(input_ids=inputs, max_length=2048)[0]
answer_start = int(inputs.shape[-1])
pred = tokenizer.decode(outputs[answer_start:], skip_special_tokens=True)
print(f'### User Input:\n{user_input}\n\n### Assistant Output:\n{pred}')
```
## Domain-Specific Tasks
To easily reproduce our results, we have uploaded the filled-in zero/few-shot input instructions and output completions of each domain-specific task: [biomedicine-tasks](https://huggingface.co/datasets/AdaptLLM/medicine-tasks), [finance-tasks](https://huggingface.co/datasets/AdaptLLM/finance-tasks), and [law-tasks](https://huggingface.co/datasets/AdaptLLM/law-tasks).
**Note:** those filled-in instructions are specifically tailored for models before alignment and do NOT fit for the specific data format required for chat models.
## Citation
If you find our work helpful, please cite us:
```bibtex
@article{adaptllm,
title = {Adapting Large Language Models via Reading Comprehension},
author = {Daixuan Cheng and Shaohan Huang and Furu Wei},
journal = {CoRR},
volume = {abs/2309.09530},
year = {2023}
}
```
<!-- original-model-card end -->
|
dylanebert/EasyVolcap
|
dylanebert
| 2024-01-15T22:04:16Z | 0 | 3 | null |
[
"image-to-3d",
"arxiv:2312.06575",
"license:other",
"region:us"
] |
image-to-3d
| 2024-01-15T22:01:58Z |
---
license: other
pipeline_tag: image-to-3d
---
Model for [EasyVolcap: Accelerating Neural Volumetric Video Research](https://huggingface.co/papers/2312.06575).
Originally hosted on [Drive](https://drive.google.com/file/d/1OFBFxes9kje02RARFpYpQ6SkmYlulYca/view?usp=sharing).
|
knowledgator/UTC-T5-large
|
knowledgator
| 2024-01-15T22:00:52Z | 12 | 5 |
transformers
|
[
"transformers",
"pytorch",
"T5",
"token-classification",
"NER",
"token classification",
"information extraction",
"question answering",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2024-01-14T14:25:18Z |
---
license: apache-2.0
language:
- en
library_name: transformers
pipeline_tag: token-classification
tags:
- NER
- token classification
- information extraction
- question answering
---
**UTC-T5-large** - universal token classificator
***🚀 Meet the first prompt-tuned universal token classification model 🚀***
This is a model based on [flan-T5-large](https://huggingface.co/google/flan-t5-large) that was trained on multiple token classification tasks or tasks that can be represented in this way.
Such multi-task fine-tuning enabled better generalization; even small models can be used for zero-shot named entity recognition and demonstrate good performance on reading comprehension tasks.
The model can be used for the following tasks:
* Named entity recognition (NER);
* Question answering;
* Relation extraction;
* Coreference resolution;
* Text cleaning;
* Summarization;
#### How to use
We recommend to use the model with transformers `ner` pipeline:
```python
from transformers import AutoTokenizer, T5PreTrainedModel, T5Config, T5EncoderModel
from transformers.modeling_outputs import TokenClassifierOutput
from typing import Union, Optional, Tuple
from transformers import pipeline
import torch
class T5EncoderForTokenClassification(T5PreTrainedModel):
_tied_weights_keys = ["encoder.embed_tokens.weight"]
def __init__(self, config: T5Config):
super().__init__(config)
self.transformer = T5EncoderModel(config)
self.classification_head = torch.nn.Linear(config.hidden_size, config.num_labels)
# Initialize weights and apply final processing
self.post_init()
self.model_parallel = False
def forward(
self,
input_ids: Optional[torch.LongTensor] = None,
attention_mask: Optional[torch.FloatTensor] = None,
head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
labels: Optional[torch.LongTensor] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[Tuple, TokenClassifierOutput]:
r"""
Returns:
Example:
```python
>>> from transformers import AutoTokenizer, MTxEncoderForTokenClassification
>>> tokenizer = AutoTokenizer.from_pretrained("MTx-small")
>>> model = MTxEncoderForTokenClassification.from_pretrained("MTx-small")
>>> input_ids = tokenizer(
... "Studies have been shown that owning a dog is good for you", return_tensors="pt"
... ).input_ids # Batch size 1
>>> outputs = model(input_ids=input_ids)
>>> logits = outputs.logits
```"""
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
outputs = self.transformer(
input_ids,
attention_mask=attention_mask,
head_mask=head_mask,
inputs_embeds=inputs_embeds,
output_attentions=output_attentions,
output_hidden_states=output_hidden_states,
return_dict=return_dict,
)
sequence_output = outputs[0]
logits = self.classification_head(sequence_output)
loss = None
if labels is not None:
labels = labels.to(logits.device)
loss_fct = CrossEntropyLoss()
loss = loss_fct(logits.view(-1, self.config.num_labels), labels.view(-1))
if not return_dict:
output = (logits,) + outputs[1:]
return ((loss,) + output) if loss is not None else output
return TokenClassifierOutput(
loss=loss,
logits=logits,
hidden_states=outputs.hidden_states,
attentions=outputs.attentions,
)
def process(text, prompt, treshold=0.5):
"""
Processes text by preparing prompt and adjusting indices.
Args:
text (str): The text to process
prompt (str): The prompt to prepend to the text
Returns:
list: A list of dicts with adjusted spans and scores
"""
# Concatenate text and prompt for full input
input_ = f"{prompt}\n{text}"
results = nlp(input_) # Run NLP on full input
processed_results = []
prompt_length = len(prompt) # Get prompt length
for result in results:
# check whether score is higher than treshold
if result['score']<treshold:
continue
# Adjust indices by subtracting prompt length
start = result['start'] - prompt_length
# If indexes belongs to the prompt - continue
if start<0:
continue
end = result['end'] - prompt_length
# Extract span from original text using adjusted indices
span = text[start:end]
# Create processed result dict
processed_result = {
'span': span,
'start': start,
'end': end,
'score': result['score']
}
processed_results.append(processed_result)
return processed_results
tokenizer = AutoTokenizer.from_pretrained("knowledgator/UTC-T5-large")
model = T5EncoderForTokenClassification.from_pretrained("knowledgator/UTC-T5-large")
nlp = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy = 'first')
```
To use the model for **zero-shot named entity recognition**, we recommend to utilize the following prompt:
```python
prompt = """Identify the following entity classes in the text:
computer
Text:
"""
text = """Apple was founded as Apple Computer Company on April 1, 1976, by Steve Wozniak, Steve Jobs (1955–2011) and Ronald Wayne to develop and sell Wozniak's Apple I personal computer.
It was incorporated by Jobs and Wozniak as Apple Computer, Inc. in 1977. The company's second computer, the Apple II, became a best seller and one of the first mass-produced microcomputers.
Apple went public in 1980 to instant financial success."""
results = process(text, prompt)
print(results)
```
To try the model in **question answering**, just specify question and text passage:
```python
question = """Who are the founders of Microsoft?"""
text = """Microsoft was founded by Bill Gates and Paul Allen on April 4, 1975 to develop and sell BASIC interpreters for the Altair 8800.
During his career at Microsoft, Gates held the positions of chairman, chief executive officer, president and chief software architect, while also being the largest individual shareholder until May 2014."""
input_ = f"{question} {text}"
results = process(text, question)
print(results)
```
For the **text cleaning**, please, specify the following prompt, it will recognize the part of the text that should be erased:
```python
prompt = """Clean the following text extracted from the web matching not relevant parts:"""
text = """The mechanism of action was characterized using native mass spectrometry, the thermal shift-binding assay, and enzymatic kinetic studies (Figure ). In the native mass spectrometry binding assay, compound 23R showed dose-dependent binding to SARS-CoV-2 Mpro, similar to the positive control GC376, with a binding stoichiometry of one drug per monomer (Figure A).
Similarly, compound 23R showed dose-dependent stabilization of the SARS-CoV-2 Mpro in the thermal shift binding assay with an apparent Kd value of 9.43 μM, a 9.3-fold decrease compared to ML188 (1) (Figure B). In the enzymatic kinetic studies, 23R was shown to be a noncovalent inhibitor with a Ki value of 0.07 μM (Figure C, D top and middle panels). In comparison, the Ki for the parent compound ML188 (1) is 2.29 μM.
The Lineweaver–Burk or double-reciprocal plot with different compound concentrations yielded an intercept at the Y-axis, suggesting that 23R is a competitive inhibitor similar to ML188 (1) (Figure C, D bottom panel). Buy our T-shirts for the lowerst prices you can find!!! Overall, the enzymatic kinetic studies confirmed that compound 23R is a noncovalent inhibitor of SARS-CoV-2 Mpro."""
results = process(text, prompt)
print(results)
```
It's possible to use the model for **relation extraction**, it allows in N*C operations to extract all relations between entities, where N - number of entities and C - number of classes:
```python
rex_prompt="""
Identify target entity given the following relation: "{}" and the following source entity: "{}"
Text:
"""
text = """Dr. Paul Hammond, a renowned neurologist at Johns Hopkins University, has recently published a paper in the prestigious journal "Nature Neuroscience". """
entity = "Paul Hammond"
relation = "worked at"
prompt = rex_prompt.format(relation, entity)
results = process(text, prompt)
print(results)
```
To **find similar entities** in the text, consider the following example:
```python
ent_prompt = "Find all '{}' mentions in the text:"
text = """Several studies have reported its pharmacological activities, including anti-inflammatory, antimicrobial, and antitumoral effects. The effect of E-anethole was studied in the osteosarcoma MG-63 cell line, and the antiproliferative activity was evaluated by an MTT assay. It showed a GI50 value of 60.25 μM with apoptosis induction through the mitochondrial-mediated pathway. Additionally, it induced cell cycle arrest at the G0/G1 phase, up-regulated the expression of p53, caspase-3, and caspase-9, and down-regulated Bcl-xL expression. Moreover, the antitumoral activity of anethole was assessed against oral tumor Ca9-22 cells, and the cytotoxic effects were evaluated by MTT and LDH assays. It demonstrated a LD50 value of 8 μM, and cellular proliferation was 42.7% and 5.2% at anethole concentrations of 3 μM and 30 μM, respectively. It was reported that it could selectively and in a dose-dependent manner decrease cell proliferation and induce apoptosis, as well as induce autophagy, decrease ROS production, and increase glutathione activity. The cytotoxic effect was mediated through NF-kB, MAP kinases, Wnt, caspase-3 and -9, and PARP1 pathways. Additionally, treatment with anethole inhibited cyclin D1 oncogene expression, increased cyclin-dependent kinase inhibitor p21WAF1, up-regulated p53 expression, and inhibited the EMT markers."""
entity = "anethole"
prompt = ent_prompt.format(entity)
results = process(text, prompt)
print(results)
```
Currently **summarization** with UTC model works purely, however, we want to highlight the potential of such approach and use cases when it's beneficial:
```python
prompt = "Summarize the following text, highlighting the most important sentences:"
text = """Apple was founded as Apple Computer Company on April 1, 1976, by Steve Wozniak, Steve Jobs (1955–2011) and Ronald Wayne to develop and sell Wozniak's Apple I personal computer. It was incorporated by Jobs and Wozniak as Apple Computer, Inc. in 1977. The company's second computer, the Apple II, became a best seller and one of the first mass-produced microcomputers. Apple went public in 1980 to instant financial success. The company developed computers featuring innovative graphical user interfaces, including the 1984 original Macintosh, announced that year in a critically acclaimed advertisement called "1984". By 1985, the high cost of its products, and power struggles between executives, caused problems. Wozniak stepped back from Apple and pursued other ventures, while Jobs resigned and founded NeXT, taking some Apple employees with him.
Apple Inc. is an American multinational technology company headquartered in Cupertino, California. Apple is the world's largest technology company by revenue, with US$394.3 billion in 2022 revenue. As of March 2023, Apple is the world's biggest company by market capitalization. As of June 2022, Apple is the fourth-largest personal computer vendor by unit sales and the second-largest mobile phone manufacturer in the world. It is considered one of the Big Five American information technology companies, alongside Alphabet (parent company of Google), Amazon, Meta Platforms, and Microsoft.
As the market for personal computers expanded and evolved throughout the 1990s, Apple lost considerable market share to the lower-priced duopoly of the Microsoft Windows operating system on Intel-powered PC clones (also known as "Wintel"). In 1997, weeks away from bankruptcy, the company bought NeXT to resolve Apple's unsuccessful operating system strategy and entice Jobs back to the company. Over the next decade, Jobs guided Apple back to profitability through a number of tactics including introducing the iMac, iPod, iPhone and iPad to critical acclaim, launching the "Think different" campaign and other memorable advertising campaigns, opening the Apple Store retail chain, and acquiring numerous companies to broaden the company's product portfolio. When Jobs resigned in 2011 for health reasons, and died two months later, he was succeeded as CEO by Tim Cook"""
results = process(text, prompt)
print(results)
```
### Future reading
Check our blogpost - ["As GPT4 but for token classification"](https://medium.com/p/9b5a081fbf27), where we highlighted possible use-cases of the model and why next-token prediction is not the only way to achive amazing zero-shot capabilites.
While most of the AI industry is focused on generative AI and decoder-based models, we are committed to developing encoder-based models.
We aim to achieve the same level of generalization for such models as their decoder brothers. Encoders have several wonderful properties, such as bidirectional attention, and they are the best choice for many information extraction tasks in terms of efficiency and controllability.
### Feedback
We value your input! Share your feedback and suggestions to help us improve our models.
Fill out the feedback [form](https://forms.gle/5CPFFuLzNWznjcpL7)
### Join Our Discord
Connect with our community on Discord for news, support, and discussion about our models.
Join [Discord](https://discord.gg/dkyeAgs9DG)
|
dylanebert/En3D-human-animation
|
dylanebert
| 2024-01-15T21:55:37Z | 0 | 12 | null |
[
"Animated avatar",
"3D rigged human",
"image-to-3d",
"arxiv:2401.01173",
"license:apache-2.0",
"region:us"
] |
image-to-3d
| 2024-01-15T21:47:59Z |
---
license: apache-2.0
tags:
- Animated avatar
- 3D rigged human
pipeline_tag: image-to-3d
---
Model [En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data](https://huggingface.co/papers/2401.01173).
Originally hosted on [ModelScope](https://modelscope.cn/models/damo/cv_3d-human-animation).
|
wooseok0303/xlm-roberta-base-finetuned-panx-en
|
wooseok0303
| 2024-01-15T21:54:31Z | 4 | 0 |
transformers
|
[
"transformers",
"safetensors",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-12-25T14:20:25Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-en
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# xlm-roberta-base-finetuned-panx-en
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3893
- F1: 0.7071
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 1.0175 | 1.0 | 50 | 0.5024 | 0.6003 |
| 0.4492 | 2.0 | 100 | 0.4148 | 0.6959 |
| 0.3572 | 3.0 | 150 | 0.3893 | 0.7071 |
### Framework versions
- Transformers 4.36.2
- Pytorch 1.13.1+cu116
- Datasets 2.16.1
- Tokenizers 0.15.0
|
yuxue/sd-deepfashion-lora
|
yuxue
| 2024-01-15T21:45:04Z | 3 | 1 |
diffusers
|
[
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2024-01-15T08:55:06Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA text2image fine-tuning - yuxue/sd-deepfashion-lora
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the DeepFashion dataset. You can find some example images in the following.
|
wooseok0303/xlm-roberta-base-finetuned-panx-fr
|
wooseok0303
| 2024-01-15T21:19:40Z | 3 | 0 |
transformers
|
[
"transformers",
"safetensors",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-12-25T14:12:37Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-fr
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# xlm-roberta-base-finetuned-panx-fr
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2637
- F1: 0.8447
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.5535 | 1.0 | 191 | 0.2988 | 0.8052 |
| 0.25 | 2.0 | 382 | 0.2680 | 0.8215 |
| 0.1748 | 3.0 | 573 | 0.2637 | 0.8447 |
### Framework versions
- Transformers 4.36.2
- Pytorch 1.13.1+cu116
- Datasets 2.16.1
- Tokenizers 0.15.0
|
nfaheem/Marcoroni-7b-DPO-Merge
|
nfaheem
| 2024-01-15T21:08:46Z | 1,378 | 2 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"fblgit/UNA-TheBeagle-7b-v1",
"udkai/Turdus",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-15T18:27:31Z |
---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- fblgit/UNA-TheBeagle-7b-v1
- udkai/Turdus
---
# Marcoroni-7b-DPO-Merge
Marcoroni-7b-DPO-Merge is a merge of the following models using [mergekit](https://github.com/cg123/mergekit) and inspired by [Maxime Labonne's work](https://medium.com/@mlabonne):
* [fblgit/UNA-TheBeagle-7b-v1](https://huggingface.co/fblgit/UNA-TheBeagle-7b-v1)
* [udkai/Turdus](https://huggingface.co/udkai/Turdus)
## 🧩 Configuration
```yaml
models:
- model: madatnlp/marcoroni-7b-v3-safetensor
# no parameters necessary for base model
- model: fblgit/UNA-TheBeagle-7b-v1
parameters:
density: 0.3
weight: 0.5
- model: udkai/Turdus
parameters:
density: 0.7
weight: 0.3
merge_method: ties
base_model: madatnlp/marcoroni-7b-v3-safetensor
parameters:
normalize: true
dtype: float16
```
## 💻 Example Python Code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "nfaheem/Marcoroni-7b-DPO-Merge"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Write a story about llamas"
system_message = "You are a story writing assistant"
prompt_template=f'''{prompt}
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
## 📋 Summary Eval:
| Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|---------|-------|-----------|--------|------------|------------|-------|
| 74.9 | 73.04 | 88.8 | 64.24 | 70.47 | 85.24 | 67.63 |
## 📈 Huggingface Leaderboard
It's Ranked # 1 on HuggingFace Leaderboard among around 13B parameters (01/15/2024)
| Model | Average | ARC | HellaSwag | MMLU | Truthful QA | Winogrande | GSM8K |
| ---------------------------------- | ------- | ----- | --------- | ----- | ----------- | ------------| ----- |
| nfaheem/Marcoroni-7b-DPO-Merge | 74.9 | 73.04 | 88.8 | 64.24 | 70.47 | 85.24 | 67.63 |
| mlabonne/Beagle14-7b | 74.76 | 72.95 | 87.95 | 64.7 | 68.38 | 82.64 | 71.42 |
| udkai/Turdus | 74.66 | 73.38 | 88.56 | 64.52 | 67.11 | 86.66 | 67.7 |
| CultriX/MergeTrix-7B | 74.33 | 72.24 | 87.84 | 64.88 | 66.27 | 83.5 | 71.19 |
| fblgit/UNA-TheBeagle-7b-v1 | 73.87 | 73.04 | 88 | 63.48 | 69.85 | 82.16 | 66.72 |
|
bpben/llama_friends_block
|
bpben
| 2024-01-15T21:02:20Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Llama-2-7b-chat-hf",
"base_model:adapter:meta-llama/Llama-2-7b-chat-hf",
"region:us"
] | null | 2024-01-15T21:02:15Z |
---
library_name: peft
base_model: meta-llama/Llama-2-7b-chat-hf
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.1
|
NouRed/Med-BLIP-2-QLoRA-ROCO
|
NouRed
| 2024-01-15T20:59:16Z | 2 | 0 |
peft
|
[
"peft",
"safetensors",
"image-to-text",
"arxiv:1910.09700",
"base_model:Salesforce/blip2-opt-2.7b",
"base_model:adapter:Salesforce/blip2-opt-2.7b",
"region:us"
] |
image-to-text
| 2024-01-13T03:01:54Z |
---
library_name: peft
base_model: Salesforce/blip2-opt-2.7b
pipeline_tag: image-to-text
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.1
|
jlvdoorn/whisper-medium-atco2-asr
|
jlvdoorn
| 2024-01-15T20:55:20Z | 33 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"base_model:openai/whisper-medium",
"base_model:finetune:openai/whisper-medium",
"doi:10.57967/hf/1632",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2024-01-15T15:45:07Z |
---
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-medium-atco2-asr
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# whisper-medium-atco2-asr
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7769
- Wer: 23.9769
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.5002 | 12.5 | 50 | 0.6266 | 23.6655 |
| 0.0013 | 25.0 | 100 | 0.6931 | 21.6637 |
| 0.0004 | 37.5 | 150 | 0.7297 | 21.7082 |
| 0.0003 | 50.0 | 200 | 0.7492 | 21.8416 |
| 0.0002 | 62.5 | 250 | 0.7622 | 21.8861 |
| 0.0002 | 75.0 | 300 | 0.7703 | 21.9306 |
| 0.0002 | 87.5 | 350 | 0.7753 | 23.0872 |
| 0.0002 | 100.0 | 400 | 0.7769 | 23.9769 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.15.0
- Tokenizers 0.15.0
|
wooseok0303/xlm-roberta-base-finetuned-panx-de-fr
|
wooseok0303
| 2024-01-15T20:51:59Z | 5 | 0 |
transformers
|
[
"transformers",
"safetensors",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-12-25T13:59:32Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-de-fr
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# xlm-roberta-base-finetuned-panx-de-fr
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1612
- F1: 0.8573
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.2802 | 1.0 | 715 | 0.1743 | 0.8292 |
| 0.1475 | 2.0 | 1430 | 0.1613 | 0.8459 |
| 0.0951 | 3.0 | 2145 | 0.1612 | 0.8573 |
### Framework versions
- Transformers 4.36.2
- Pytorch 1.13.1+cu116
- Datasets 2.16.1
- Tokenizers 0.15.0
|
Neuronovo/neuronovo-9B-v0.1
|
Neuronovo
| 2024-01-15T20:49:36Z | 11 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-05T22:12:42Z |
---
license: apache-2.0
language:
- en
library_name: transformers
pipeline_tag: text-generation
---
The model described by the provided code, named "Neuronovo/neuronovo-9B-v0.1," is a sophisticated and fine-tuned version of a large language model, originally based on the "teknium/OpenHermes-2.5-Mistral-7B." This model exhibits several distinct characteristics and functionalities as derived from the code snippet:
1. **Dataset and Preprocessing**: It is trained on a dataset named "Intel/orca_dpo_pairs," which is likely a specialized dataset for dialogue systems. The data is preprocessed to format dialogues, with specific attention to system messages, user queries, chosen answers, and rejected answers.
2. **Tokenizer**: The model utilizes a tokenizer from the original "OpenHermes-2.5-Mistral-7B" model. This tokenizer is configured to have the end-of-sequence token as the padding token and pads from the left, indicating a particular focus on language generation tasks.
3. **LoRA Configuration**: The model employs a LoRA (Low-Rank Adaptation) configuration with specific parameters (r=16, lora_alpha=16, etc.) and targets multiple modules within the transformer architecture. This suggests an approach focused on efficient fine-tuning and adaptation of the model while preserving the majority of the pre-trained weights.
4. **Fine-Tuning Specifications**: The model is fine-tuned using a custom training setup, including a special DPO (Data Parallel Optimization) Trainer. This indicates an advanced fine-tuning process that likely emphasizes both efficiency and effectiveness, possibly with a focus on parallel processing and optimization.
5. **Training Arguments**: The training uses specific arguments like a cosine learning rate scheduler, paged AdamW optimizer, and training in 4-bit precision (indicating a focus on memory efficiency). It also employs gradient checkpointing and accumulation steps, which are typical in training large models efficiently.
6. **Performance and Output**: The model is configured for causal language modeling (indicative of generating text or continuing dialogues), with a maximum prompt length of 1024 and maximum generation length of 1536 tokens. This setup suggests its capability for handling extended dialogues or text generation tasks.
7. **Special Features**: The use of LoRA, DPO training, and specific fine-tuning methods highlight the model's advanced capabilities in adapting large-scale language models to specific tasks or datasets while maintaining computational efficiency.
In summary, "Neuronovo/neuronovo-9B-v0.1" is a highly specialized, efficient, and capable large language model fine-tuned for advanced language generation tasks, particularly in the context of dialogues or interactions, leveraging cutting-edge techniques in NLP model adaptation and training.
---
license: apache-2.0
---
|
Neuronovo/neuronovo-9B-v0.3
|
Neuronovo
| 2024-01-15T20:48:04Z | 12 | 4 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"en",
"dataset:Intel/orca_dpo_pairs",
"dataset:mlabonne/chatml_dpo_pairs",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-10T13:49:55Z |
---
license: apache-2.0
datasets:
- Intel/orca_dpo_pairs
- mlabonne/chatml_dpo_pairs
language:
- en
library_name: transformers
---
More information about previous [Neuronovo/neuronovo-9B-v0.2](https://huggingface.co/Neuronovo/neuronovo-9B-v0.2) version available here: 🔗[Don't stop DPOptimizing!](https://www.linkedin.com/pulse/dont-stop-dpoptimizing-jan-koco%2525C5%252584-mq4qf)
Author: Jan Kocoń 🔗[LinkedIn](https://www.linkedin.com/in/jankocon/) 🔗[Google Scholar](https://scholar.google.com/citations?user=pmQHb5IAAAAJ&hl=en&oi=ao) 🔗[ResearchGate](https://www.researchgate.net/profile/Jan-Kocon-2)
Changes concerning [Neuronovo/neuronovo-9B-v0.2](https://huggingface.co/Neuronovo/neuronovo-9B-v0.2):
1. **Training Dataset**: In addition to the [Intel/orca_dpo_pairs](Intel/orca_dpo_pairs) dataset, this version incorporates a [mlabonne/chatml_dpo_pairs](https://huggingface.co/datasets/mlabonne/chatml_dpo_pairs). The combined datasets enhance the model's capabilities in dialogues and interactive scenarios, further specializing it in natural language understanding and response generation.
2. **Tokenizer and Formatting**: The tokenizer now originates directly from the [Neuronovo/neuronovo-9B-v0.2](https://huggingface.co/Neuronovo/neuronovo-9B-v0.2) model.
3. **Training Configuration**: The training approach has shifted from using `max_steps=200` to `num_train_epochs=1`. This represents a change in the training strategy, focusing on epoch-based training rather than a fixed number of steps.
4. **Learning Rate**: The learning rate has been reduced to a smaller value of `5e-6`. This finer learning rate allows for more precise adjustments during the training process, potentially leading to better model performance.
|
TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF
|
TheBloke
| 2024-01-15T20:37:21Z | 520 | 13 |
transformers
|
[
"transformers",
"gguf",
"yi",
"mergekit",
"merge",
"Yi",
"en",
"arxiv:2311.03099",
"arxiv:2306.01708",
"base_model:brucethemoose/Yi-34B-200K-DARE-megamerge-v8",
"base_model:quantized:brucethemoose/Yi-34B-200K-DARE-megamerge-v8",
"license:other",
"region:us"
] | null | 2024-01-15T17:06:46Z |
---
base_model: brucethemoose/Yi-34B-200K-DARE-megamerge-v8
inference: false
language:
- en
library_name: transformers
license: other
license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE
license_name: yi-license
model_creator: brucethemoose
model_name: Yi 34B 200K DARE MegaMerge V8
model_type: yi
prompt_template: 'SYSTEM: {system_message}
USER: {prompt}
ASSISTANT:
'
quantized_by: TheBloke
tags:
- mergekit
- merge
- Yi
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Yi 34B 200K DARE MegaMerge V8 - GGUF
- Model creator: [brucethemoose](https://huggingface.co/brucethemoose)
- Original model: [Yi 34B 200K DARE MegaMerge V8](https://huggingface.co/brucethemoose/Yi-34B-200K-DARE-megamerge-v8)
<!-- description start -->
## Description
This repo contains GGUF format model files for [brucethemoose's Yi 34B 200K DARE MegaMerge V8](https://huggingface.co/brucethemoose/Yi-34B-200K-DARE-megamerge-v8).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### New GGUF formats
The GGUF files in this repo were made using new k-quant methods, added Jan 2024.
They will only be compatible with llama.cpp from Jan 4th onwards. Other clients may not have been updated for support yet.
The new GGUF k-quant method enables use of an "importance matrix", which is similar in concept to the calibration datasets used by GPTQ, AWQ and EXL2. This improves GGUF quantization quality.
The dataset used for generating the importance matrix for these GGUFs was: VMware open-instruct (5K lines).
Use of the importance matrix enables providing new quant formats: IQ2_XXS, IQ2_XS and Q2_K_S.
Note: adding support for this new GGUF quant method is still a work-in-progress for me. Other GGUF repos I'm creating won't necessarily have this, at least for the next couple of days.
### Clients with GGUF support (not tested with this GGUF quant format specifically, yet)
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF)
* [brucethemoose's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/brucethemoose/Yi-34B-200K-DARE-megamerge-v8)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Orca-Vicuna
```
SYSTEM: {system_message}
USER: {prompt}
ASSISTANT:
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [yi-34b-200k-dare-megamerge-v8.IQ2_XXS.gguf](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF/blob/main/yi-34b-200k-dare-megamerge-v8.IQ2_XXS.gguf) | IQ2_XXS | 2 | 9.31 GB| 11.81 GB | smallest size. 2.06 bpw. New IQuant method, Jan 2024 |
| [yi-34b-200k-dare-megamerge-v8.IQ2_XS.gguf](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF/blob/main/yi-34b-200k-dare-megamerge-v8.IQ2_XS.gguf) | IQ2_XS | 2 | 10.31 GB| 12.81 GB | second smallest size. 2.31 bpw quant. New IQuant method, Jan 2024 |
| [yi-34b-200k-dare-megamerge-v8.Q2_K_S.gguf](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF/blob/main/yi-34b-200k-dare-megamerge-v8.Q2_K_S.gguf) | Q2_K_S | 2 | 11.76 GB| 14.26 GB | significant quality loss - not recommended for most purposes. New method, Jan 2024 |
| [yi-34b-200k-dare-megamerge-v8.Q2_K.gguf](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF/blob/main/yi-34b-200k-dare-megamerge-v8.Q2_K.gguf) | Q2_K | 2 | 12.77 GB| 15.27 GB | significant quality loss - not recommended for most purposes |
| [yi-34b-200k-dare-megamerge-v8.Q3_K_S.gguf](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF/blob/main/yi-34b-200k-dare-megamerge-v8.Q3_K_S.gguf) | Q3_K_S | 3 | 14.96 GB| 17.46 GB | very small, high quality loss |
| [yi-34b-200k-dare-megamerge-v8.Q3_K_M.gguf](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF/blob/main/yi-34b-200k-dare-megamerge-v8.Q3_K_M.gguf) | Q3_K_M | 3 | 16.65 GB| 19.15 GB | very small, high quality loss |
| [yi-34b-200k-dare-megamerge-v8.Q3_K_L.gguf](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF/blob/main/yi-34b-200k-dare-megamerge-v8.Q3_K_L.gguf) | Q3_K_L | 3 | 18.14 GB| 20.64 GB | small, substantial quality loss |
| [yi-34b-200k-dare-megamerge-v8.Q4_0.gguf](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF/blob/main/yi-34b-200k-dare-megamerge-v8.Q4_0.gguf) | Q4_0 | 4 | 19.47 GB| 21.97 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [yi-34b-200k-dare-megamerge-v8.Q4_K_S.gguf](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF/blob/main/yi-34b-200k-dare-megamerge-v8.Q4_K_S.gguf) | Q4_K_S | 4 | 19.60 GB| 22.10 GB | small, greater quality loss |
| [yi-34b-200k-dare-megamerge-v8.Q4_K_M.gguf](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF/blob/main/yi-34b-200k-dare-megamerge-v8.Q4_K_M.gguf) | Q4_K_M | 4 | 20.66 GB| 23.16 GB | medium, balanced quality - recommended |
| [yi-34b-200k-dare-megamerge-v8.Q5_0.gguf](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF/blob/main/yi-34b-200k-dare-megamerge-v8.Q5_0.gguf) | Q5_0 | 5 | 23.71 GB| 26.21 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [yi-34b-200k-dare-megamerge-v8.Q5_K_S.gguf](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF/blob/main/yi-34b-200k-dare-megamerge-v8.Q5_K_S.gguf) | Q5_K_S | 5 | 23.71 GB| 26.21 GB | large, low quality loss - recommended |
| [yi-34b-200k-dare-megamerge-v8.Q5_K_M.gguf](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF/blob/main/yi-34b-200k-dare-megamerge-v8.Q5_K_M.gguf) | Q5_K_M | 5 | 24.32 GB| 26.82 GB | large, very low quality loss - recommended |
| [yi-34b-200k-dare-megamerge-v8.Q6_K.gguf](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF/blob/main/yi-34b-200k-dare-megamerge-v8.Q6_K.gguf) | Q6_K | 6 | 28.21 GB| 30.71 GB | very large, extremely low quality loss |
| [yi-34b-200k-dare-megamerge-v8.Q8_0.gguf](https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF/blob/main/yi-34b-200k-dare-megamerge-v8.Q8_0.gguf) | Q8_0 | 8 | 36.54 GB| 39.04 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF and below it, a specific filename to download, such as: yi-34b-200k-dare-megamerge-v8.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF yi-34b-200k-dare-megamerge-v8.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF yi-34b-200k-dare-megamerge-v8.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m yi-34b-200k-dare-megamerge-v8.Q4_K_M.gguf --color -c 200000 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "SYSTEM: {system_message}\nUSER: {prompt}\nASSISTANT:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 200000` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./yi-34b-200k-dare-megamerge-v8.Q4_K_M.gguf", # Download the model file first
n_ctx=200000, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"SYSTEM: {system_message}\nUSER: {prompt}\nASSISTANT:", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./yi-34b-200k-dare-megamerge-v8.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: brucethemoose's Yi 34B 200K DARE MegaMerge V8
# Yi 34B 200K DARE Merge v8
A merge of many Yi 34B 200K models using the new DARE Ties method via mergekit. The goal is to create a merge model that excels at 32K+ context performance, without any additional finetuning.
## Prompt template: Orca-Vicuna
```
SYSTEM: {system_message}
USER: {prompt}
ASSISTANT:
```
It might recognize ChatML, and possibly Alpaca-like formats. Raw prompting as described here is also effective: https://old.reddit.com/r/LocalLLaMA/comments/18zqy4s/the_secret_to_writing_quality_stories_with_llms/
## Running
Being a Yi model, run a lower temperature with 0.05 or higher MinP, a little repetition penalty, maybe mirostat with a low tau, and no other samplers. Yi tends to run "hot" by default, and it really needs a low temperature + MinP to cull Yi's huge vocabulary. See the explanation here: https://github.com/ggerganov/llama.cpp/pull/3841
24GB GPUs can efficiently run Yi-34B-200K models at **40K-90K context** with exllamav2, and performant UIs like [exui](https://github.com/turboderp/exui). I go into more detail in this [post](https://old.reddit.com/r/LocalLLaMA/comments/1896igc/how_i_run_34b_models_at_75k_context_on_24gb_fast/). 16GB GPUs can still run the high context with aggressive quantization.
I recommend exl2 quantizations profiled on data similar to the desired task. It is especially sensitive to the quantization data at low bpw. I've upload my own fiction-oriented quantizations here: https://huggingface.co/collections/brucethemoose/most-recent-merge-65742644ca03b6c514afa204
Lonestriker has also uploaded more general purpose quantizations here: https://huggingface.co/models?sort=trending&search=LoneStriker+Yi-34B-200K-DARE-megamerge-v8
To load/train this in full-context backends like transformers, you *must* change `max_position_embeddings` in config.json to a lower value than 200,000, otherwise you will OOM! I do not recommend running high context without context-efficient backends like exllamav2, litellm or unsloth.
## Testing Notes
See: https://huggingface.co/brucethemoose/Yi-34B-200K-DARE-merge-v5#testing-notes
An intermediate merge model was created to try and extend the context of several 4k models before adding them to the main merge, as seen in the "megamerge" recipe below. I can upload this upon request
In addition, the weight gradients are biased towards Vicuna-format models in the first few layers to try and "emphasize" the Orca-Vicuna prompt template. How sucessful this is remains to be seen.
## Merge Details
### Merge Method
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama as a base.
### Models Merged
The following models were included in the merge:
* https://huggingface.co/kyujinpy/PlatYi-34B-200k-Q-FastChat
* https://huggingface.co/jondurbin/bagel-34b-v0.2
* https://huggingface.co/migtissera/Tess-M-Creative-v1.0
* https://huggingface.co/brucethemoose/SUS-Bagel-200K-DARE-Test
* https://huggingface.co/Mihaiii/Pallas-0.5
* https://huggingface.co/bhenrym14/airoboros-3_1-yi-34b-200k
* https://huggingface.co/adamo1139/Yi-34B-200K-AEZAKMI-v2
* https://huggingface.co/migtissera/Tess-34B-v1.4
* https://huggingface.co/SUSTech/SUS-Chat-34B
* https://huggingface.co/jondurbin/bagel-dpo-34b-v0.2
* https://huggingface.co/bhenrym14/platypus-yi-34b
* https://huggingface.co/Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp
* https://huggingface.co/TriadParty/deepsex-34b
* https://huggingface.co/TriadParty/deepmoney-34b-200k-base
* https://huggingface.co/chargoddard/Yi-34B-200K-Llama
* https://huggingface.co/chargoddard/Yi-34B-Llama
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: /home/alpha/Models/Raw/chargoddard_Yi-34B-Llama
# No parameters necessary for base model
- model: /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama
#200K base to extend the context of 4K models, max density as we *want* it to 'interfere'
parameters:
weight: 0.33
density: 1
- model: /home/alpha/Models/Raw/Weyaxi_Nous-Hermes-2-SUS-Chat-34B-Slerp
parameters:
weight: 0.15
density: 0.36
- model: /home/alpha/Models/Raw/jondurbin_bagel-dpo-34b-v0.2
#Mix dpo with sft to tone down dpo
parameters:
weight: 0.06
density: 0.36
- model: /home/alpha/Models/Raw/jondurbin_bagel-34b-v0.2
parameters:
weight: 0.06
density: 0.41
- model: /home/alpha/Models/Raw/bhenrym14_platypus-yi-34b
#Vicuna format
parameters:
weight: 0.19
density: 0.41
# - model: /home/alpha/Models/Raw/01-ai_Yi-34B-Chat #+/home/alpha/Models/Raw/Doctor-Shotgun_limarpv3-yi-llama-34b-lora
# #Can't get lora OR base model to work without erroring out?
# parameters:
# weight: 0.04
# density: 0.36
- model: /home/alpha/Models/Raw/TriadParty_deepsex-34b
#Base model with no prompt
parameters:
weight: 0.21
density: 0.39
merge_method: dare_ties
tokenizer_source: union
base_model: /home/alpha/Models/Raw/chargoddard_Yi-34B-Llama
parameters:
int8_mask: true
dtype: bfloat16
name: 4kmerge-v2
---
models:
- model: /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama
# No parameters necessary for base model
- model: /home/alpha/Storage/Models/Raw/migtissera_Tess-34B-v1.4
#Emphasize the beginning of Vicuna format models
parameters:
weight: [0.22, 0.113, 0.113, 0.113, 0.113, 0.113]
density: 0.61
- model: /home/alpha/Models/Raw/Mihaiii_Pallas-0.5
# Vicuna format
parameters:
weight: [0.22, 0.113, 0.113, 0.113, 0.113, 0.113]
density: 0.61
- model: /home/alpha//Storage/Models/Raw/bhenrym14_airoboros-3_1-yi-34b-200k
parameters:
weight: [0.02, 0.081, 0.081, 0.081, 0.081, 0.081]
density: 0.59
- model: /home/alpha/Storage/Models/Raw/jondurbin_bagel-34b-v0.2
#Only the SFT in the main merge since the DPO version seems to have no long context ability at all, and some overfitting(?) issues
parameters:
weight: [0.02, 0.093, 0.093, 0.093, 0.093, 0.093]
density: 0.4
- model: /home/alpha/Storage/Models/Raw/kyujinpy_PlatYi-34B-200k-Q-FastChat
parameters:
weight: [0.02, 0.081, 0.081, 0.081, 0.081, 0.081]
density: 0.59
#- model: /home/alpha/Storage/Models/Raw/ehartford_dolphin-2.2-yi-34b-200k
# Dolphin 200K seems to be funky according to multiple leaderboards and perplexity tests?
# parameters:
# weight: 0.15
# density: 0.6
- model: /home/alpha/Models/Raw/adamo1139_Yi-34B-200K-AEZAKMI-v2
parameters:
weight: [0.02, 0.096, 0.096, 0.096, 0.096, 0.096]
density: 0.59
- model: /home/alpha/Storage/Models/Raw/Nous-Capybara-34B
parameters:
weight: [0.21, 0.115, 0.115, 0.115, 0.115, 0.115]
density: 0.59
- model: 4kmerge-v2
#Previous merge
parameters:
weight: [0.02, 0.115, 0.115, 0.115, 0.115, 0.115]
density: 0.4
- model: /home/alpha/Models/Raw/migtissera_Tess-M-Creative-v1.0
# Vicuna format
parameters:
weight: [0.21, 0.09, 0.09, 0.09, 0.09, 0.09]
density: 0.61
- model: /home/alpha/Models/Raw/TriadParty_deepmoney-34b-200k-base
# No prompt format, native long context full finetune
parameters:
weight: [0.04, 0.103, 0.103, 0.103, 0.103, 0.103]
density: 0.61
merge_method: dare_ties
tokenizer_source: union
base_model: /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama
parameters:
int8_mask: true
dtype: bfloat16
```
<!-- original-model-card end -->
|
ianporada/link-append-xxl
|
ianporada
| 2024-01-15T20:30:28Z | 40 | 4 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-11-30T21:06:29Z |
---
license: apache-2.0
language:
- en
---
The "Coref-mT5-XXL model" from https://github.com/google-research/google-research/tree/master/coref_mt5 converted to HuggingFace Transformers.
See https://github.com/ianporada/mt5_coref_pytorch for details.
|
TheBloke/phi-2-orange-GPTQ
|
TheBloke
| 2024-01-15T20:18:06Z | 20 | 4 |
transformers
|
[
"transformers",
"safetensors",
"phi-msft",
"text-generation",
"custom_code",
"dataset:Open-Orca/SlimOrca-Dedup",
"dataset:migtissera/Synthia-v1.3",
"dataset:LDJnr/Verified-Camel",
"dataset:LDJnr/Pure-Dove",
"dataset:LDJnr/Capybara",
"dataset:meta-math/MetaMathQA",
"dataset:Intel/orca_dpo_pairs",
"dataset:argilla/ultrafeedback-binarized-preferences-cleaned",
"base_model:rhysjones/phi-2-orange",
"base_model:quantized:rhysjones/phi-2-orange",
"license:mit",
"autotrain_compatible",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2024-01-15T19:52:15Z |
---
base_model: rhysjones/phi-2-orange
datasets:
- Open-Orca/SlimOrca-Dedup
- migtissera/Synthia-v1.3
- LDJnr/Verified-Camel
- LDJnr/Pure-Dove
- LDJnr/Capybara
- meta-math/MetaMathQA
- Intel/orca_dpo_pairs
- argilla/ultrafeedback-binarized-preferences-cleaned
inference: false
license: mit
model_creator: Rhys Jones
model_name: Phi 2 Orange
model_type: phi-msft
prompt_template: '{prompt}
'
quantized_by: TheBloke
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Phi 2 Orange - GPTQ
- Model creator: [Rhys Jones](https://huggingface.co/rhysjones)
- Original model: [Phi 2 Orange](https://huggingface.co/rhysjones/phi-2-orange)
<!-- description start -->
# Description
This repo contains GPTQ model files for [Rhys Jones's Phi 2 Orange](https://huggingface.co/rhysjones/phi-2-orange).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/phi-2-orange-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/phi-2-orange-GGUF)
* [Rhys Jones's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/rhysjones/phi-2-orange)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Unknown
```
{prompt}
```
<!-- prompt-template end -->
<!-- README_GPTQ.md-compatible clients start -->
## Known compatible clients / servers
GPTQ models are currently supported on Linux (NVidia/AMD) and Windows (NVidia only). macOS users: please use GGUF models.
These GPTQ models are known to work in the following inference servers/webuis.
- [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
- [KoboldAI United](https://github.com/henk717/koboldai)
- [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
This may not be a complete list; if you know of others, please let me know!
<!-- README_GPTQ.md-compatible clients end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama and Mistral models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/phi-2-orange-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 2048 | 1.84 GB | No | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/phi-2-orange-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 2048 | 1.98 GB | No | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/phi-2-orange-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 2048 | 3.05 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/phi-2-orange-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 2048 | 3.10 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/phi-2-orange-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 2048 | 3.28 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/phi-2-orange-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 2048 | 1.89 GB | No | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download, including from branches
### In text-generation-webui
To download from the `main` branch, enter `TheBloke/phi-2-orange-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/phi-2-orange-GPTQ:gptq-4bit-32g-actorder_True`
### From the command line
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `phi-2-orange-GPTQ`:
```shell
mkdir phi-2-orange-GPTQ
huggingface-cli download TheBloke/phi-2-orange-GPTQ --local-dir phi-2-orange-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir phi-2-orange-GPTQ
huggingface-cli download TheBloke/phi-2-orange-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir phi-2-orange-GPTQ --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
mkdir phi-2-orange-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/phi-2-orange-GPTQ --local-dir phi-2-orange-GPTQ --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
### With `git` (**not** recommended)
To clone a specific branch with `git`, use a command like this:
```shell
git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/phi-2-orange-GPTQ
```
Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/phi-2-orange-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/phi-2-orange-GPTQ:gptq-4bit-32g-actorder_True`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `phi-2-orange-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
- Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-tgi start -->
## Serving this model from Text Generation Inference (TGI)
It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/phi-2-orange-GPTQ --port 3000 --quantize gptq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''{prompt}
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(
prompt_template,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(f"Model output: {response}")
```
<!-- README_GPTQ.md-use-from-tgi end -->
<!-- README_GPTQ.md-use-from-python start -->
## Python code example: inference from this GPTQ model
### Install the necessary packages
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install --upgrade transformers optimum
# If using PyTorch 2.1 + CUDA 12.x:
pip3 install --upgrade auto-gptq
# or, if using PyTorch 2.1 + CUDA 11.x:
pip3 install --upgrade auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
```
If you are using PyTorch 2.0, you will need to install AutoGPTQ from source. Likewise if you have problems with the pre-built wheels, you should try building from source:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.5.1
pip3 install .
```
### Example Python code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/phi-2-orange-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-32g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=True,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Write a story about llamas"
system_message = "You are a story writing assistant"
prompt_template=f'''{prompt}
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with Transformers. For non-Mistral models, AutoGPTQ can also be used directly.
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama architecture models (including Mistral, Yi, DeepSeek, SOLAR, etc) in 4-bit. Please see the Provided Files table above for per-file compatibility.
For a list of clients/servers, please see "Known compatible clients / servers", above.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Rhys Jones's Phi 2 Orange
# Phi-2 Orange
A two-step finetune of Phi-2, with a bit of zest.
First using a collection of broad training data:
- [Open-Orca/SlimOrca-Dedup](https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup)
- [migtissera/Synthia-v1.3](https://huggingface.co/datasets/migtissera/Synthia-v1.3)
- [LDJnr/Verified-Camel](https://huggingface.co/datasets/LDJnr/Verified-Camel)
- [LDJnr/Pure-Dove](https://huggingface.co/datasets/LDJnr/Pure-Dove)
- [LDJnr/Capybara](https://huggingface.co/datasets/LDJnr/Capybara)
- [meta-math/MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA)
And then a DPO finetune using:
- [Intel/orca_dpo_pairs](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
- [argilla/ultrafeedback-binarized-preferences-cleaned](https://huggingface.co/datasets/argilla/ultrafeedback-binarized-preferences-cleaned)
# Evaluations
Evaluations done using mlabonne's usefull [Colab notebook llm-autoeval](https://github.com/mlabonne/llm-autoeval).
Also check out the alternative leaderboard at [Yet_Another_LLM_Leaderboard](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard)
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|----------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[phi-2-orange](https://huggingface.co/rhysjones/phi-2-orange)| **33.37**| 71.33| 49.87| **37.3**| **47.97**|
|[phi-2-dpo](https://huggingface.co/lxuechen/phi-2-dpo)| 30.39| **71.68**| **50.75**| 34.9| 46.93|
|[dolphin-2_6-phi-2](https://huggingface.co/cognitivecomputations/dolphin-2_6-phi-2)| 33.12| 69.85| 47.39| 37.2| 46.89|
|[phi-2](https://huggingface.co/microsoft/phi-2)| 27.98| 70.8| 44.43| 35.21| 44.61|
|
TheBloke/phi-2-orange-GGUF
|
TheBloke
| 2024-01-15T20:11:46Z | 275 | 20 |
transformers
|
[
"transformers",
"gguf",
"phi-msft",
"dataset:Open-Orca/SlimOrca-Dedup",
"dataset:migtissera/Synthia-v1.3",
"dataset:LDJnr/Verified-Camel",
"dataset:LDJnr/Pure-Dove",
"dataset:LDJnr/Capybara",
"dataset:meta-math/MetaMathQA",
"dataset:Intel/orca_dpo_pairs",
"dataset:argilla/ultrafeedback-binarized-preferences-cleaned",
"base_model:rhysjones/phi-2-orange",
"base_model:quantized:rhysjones/phi-2-orange",
"license:mit",
"region:us"
] | null | 2024-01-15T19:52:15Z |
---
base_model: rhysjones/phi-2-orange
datasets:
- Open-Orca/SlimOrca-Dedup
- migtissera/Synthia-v1.3
- LDJnr/Verified-Camel
- LDJnr/Pure-Dove
- LDJnr/Capybara
- meta-math/MetaMathQA
- Intel/orca_dpo_pairs
- argilla/ultrafeedback-binarized-preferences-cleaned
inference: false
license: mit
model_creator: Rhys Jones
model_name: Phi 2 Orange
model_type: phi-msft
prompt_template: '{prompt}
'
quantized_by: TheBloke
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Phi 2 Orange - GGUF
- Model creator: [Rhys Jones](https://huggingface.co/rhysjones)
- Original model: [Phi 2 Orange](https://huggingface.co/rhysjones/phi-2-orange)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Rhys Jones's Phi 2 Orange](https://huggingface.co/rhysjones/phi-2-orange).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/phi-2-orange-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/phi-2-orange-GGUF)
* [Rhys Jones's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/rhysjones/phi-2-orange)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Unknown
```
{prompt}
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [phi-2-orange.Q2_K.gguf](https://huggingface.co/TheBloke/phi-2-orange-GGUF/blob/main/phi-2-orange.Q2_K.gguf) | Q2_K | 2 | 1.09 GB| 3.59 GB | smallest, significant quality loss - not recommended for most purposes |
| [phi-2-orange.Q3_K_S.gguf](https://huggingface.co/TheBloke/phi-2-orange-GGUF/blob/main/phi-2-orange.Q3_K_S.gguf) | Q3_K_S | 3 | 1.25 GB| 3.75 GB | very small, high quality loss |
| [phi-2-orange.Q3_K_M.gguf](https://huggingface.co/TheBloke/phi-2-orange-GGUF/blob/main/phi-2-orange.Q3_K_M.gguf) | Q3_K_M | 3 | 1.49 GB| 3.99 GB | very small, high quality loss |
| [phi-2-orange.Q4_0.gguf](https://huggingface.co/TheBloke/phi-2-orange-GGUF/blob/main/phi-2-orange.Q4_0.gguf) | Q4_0 | 4 | 1.60 GB| 4.10 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [phi-2-orange.Q3_K_L.gguf](https://huggingface.co/TheBloke/phi-2-orange-GGUF/blob/main/phi-2-orange.Q3_K_L.gguf) | Q3_K_L | 3 | 1.60 GB| 4.10 GB | small, substantial quality loss |
| [phi-2-orange.Q4_K_S.gguf](https://huggingface.co/TheBloke/phi-2-orange-GGUF/blob/main/phi-2-orange.Q4_K_S.gguf) | Q4_K_S | 4 | 1.63 GB| 4.13 GB | small, greater quality loss |
| [phi-2-orange.Q4_K_M.gguf](https://huggingface.co/TheBloke/phi-2-orange-GGUF/blob/main/phi-2-orange.Q4_K_M.gguf) | Q4_K_M | 4 | 1.79 GB| 4.29 GB | medium, balanced quality - recommended |
| [phi-2-orange.Q5_0.gguf](https://huggingface.co/TheBloke/phi-2-orange-GGUF/blob/main/phi-2-orange.Q5_0.gguf) | Q5_0 | 5 | 1.93 GB| 4.43 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [phi-2-orange.Q5_K_S.gguf](https://huggingface.co/TheBloke/phi-2-orange-GGUF/blob/main/phi-2-orange.Q5_K_S.gguf) | Q5_K_S | 5 | 1.93 GB| 4.43 GB | large, low quality loss - recommended |
| [phi-2-orange.Q5_K_M.gguf](https://huggingface.co/TheBloke/phi-2-orange-GGUF/blob/main/phi-2-orange.Q5_K_M.gguf) | Q5_K_M | 5 | 2.07 GB| 4.57 GB | large, very low quality loss - recommended |
| [phi-2-orange.Q6_K.gguf](https://huggingface.co/TheBloke/phi-2-orange-GGUF/blob/main/phi-2-orange.Q6_K.gguf) | Q6_K | 6 | 2.29 GB| 4.79 GB | very large, extremely low quality loss |
| [phi-2-orange.Q8_0.gguf](https://huggingface.co/TheBloke/phi-2-orange-GGUF/blob/main/phi-2-orange.Q8_0.gguf) | Q8_0 | 8 | 2.96 GB| 5.46 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/phi-2-orange-GGUF and below it, a specific filename to download, such as: phi-2-orange.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/phi-2-orange-GGUF phi-2-orange.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/phi-2-orange-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/phi-2-orange-GGUF phi-2-orange.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m phi-2-orange.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "{prompt}"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./phi-2-orange.Q4_K_M.gguf", # Download the model file first
n_ctx=2048, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"{prompt}", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./phi-2-orange.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Rhys Jones's Phi 2 Orange
# Phi-2 Orange
A two-step finetune of Phi-2, with a bit of zest.
First using a collection of broad training data:
- [Open-Orca/SlimOrca-Dedup](https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup)
- [migtissera/Synthia-v1.3](https://huggingface.co/datasets/migtissera/Synthia-v1.3)
- [LDJnr/Verified-Camel](https://huggingface.co/datasets/LDJnr/Verified-Camel)
- [LDJnr/Pure-Dove](https://huggingface.co/datasets/LDJnr/Pure-Dove)
- [LDJnr/Capybara](https://huggingface.co/datasets/LDJnr/Capybara)
- [meta-math/MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA)
And then a DPO finetune using:
- [Intel/orca_dpo_pairs](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
- [argilla/ultrafeedback-binarized-preferences-cleaned](https://huggingface.co/datasets/argilla/ultrafeedback-binarized-preferences-cleaned)
# Evaluations
Evaluations done using mlabonne's usefull [Colab notebook llm-autoeval](https://github.com/mlabonne/llm-autoeval).
Also check out the alternative leaderboard at [Yet_Another_LLM_Leaderboard](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard)
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|----------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[phi-2-orange](https://huggingface.co/rhysjones/phi-2-orange)| **33.37**| 71.33| 49.87| **37.3**| **47.97**|
|[phi-2-dpo](https://huggingface.co/lxuechen/phi-2-dpo)| 30.39| **71.68**| **50.75**| 34.9| 46.93|
|[dolphin-2_6-phi-2](https://huggingface.co/cognitivecomputations/dolphin-2_6-phi-2)| 33.12| 69.85| 47.39| 37.2| 46.89|
|[phi-2](https://huggingface.co/microsoft/phi-2)| 27.98| 70.8| 44.43| 35.21| 44.61|
<!-- original-model-card end -->
|
Weni/WeniGPT-2.0.1-phi-2-2B-BitsandBytes-dataset-2.0.1
|
Weni
| 2024-01-15T20:11:31Z | 3 | 0 |
peft
|
[
"peft",
"safetensors",
"phi",
"custom_code",
"arxiv:1910.09700",
"base_model:microsoft/phi-2",
"base_model:adapter:microsoft/phi-2",
"region:us"
] | null | 2024-01-15T17:39:08Z |
---
library_name: peft
base_model: microsoft/phi-2
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.1
|
wooseok0303/distilbert-base-uncased-finetuned-emotion
|
wooseok0303
| 2024-01-15T20:05:37Z | 5 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-12-25T01:04:49Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2172
- Accuracy: 0.929
- F1: 0.9289
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8369 | 1.0 | 250 | 0.3116 | 0.9075 | 0.9076 |
| 0.2489 | 2.0 | 500 | 0.2172 | 0.929 | 0.9289 |
### Framework versions
- Transformers 4.36.2
- Pytorch 1.13.1+cu116
- Datasets 2.16.1
- Tokenizers 0.15.0
|
mharsch/ppo-LunarLander-v2
|
mharsch
| 2024-01-15T20:00:39Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-15T19:52:56Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 282.95 +/- 15.29
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
lambdavi/ppo-SnowballTarget
|
lambdavi
| 2024-01-15T20:00:37Z | 54 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] |
reinforcement-learning
| 2024-01-15T19:55:43Z |
---
library_name: ml-agents
tags:
- SnowballTarget
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SnowballTarget
---
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: lambdavi/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
### Hyperparams used:
```
SnowballTarget:
trainer_type: ppo
hyperparameters:
batch_size: 128
buffer_size: 2048
learning_rate: 0.005
beta: 0.005
epsilon: 0.2
lambd: 0.95
num_epoch: 5
shared_critic: False
learning_rate_schedule: linear
beta_schedule: linear
epsilon_schedule: linear
checkpoint_interval: 50000
network_settings:
normalize: False
hidden_units: 256
num_layers: 2
vis_encode_type: simple
memory: None
goal_conditioning_type: hyper
deterministic: False
reward_signals:
extrinsic:
gamma: 0.99
strength: 1.0
network_settings:
normalize: False
hidden_units: 128
num_layers: 2
vis_encode_type: simple
memory: None
goal_conditioning_type: hyper
deterministic: False
init_path: None
keep_checkpoints: 10
even_checkpoints: False
max_steps: 500000
time_horizon: 64
summary_freq: 10000
threaded: True
self_play: None
behavioral_cloning: None
```
|
Subsets and Splits
Filtered Qwen2.5 Distill Models
Identifies specific configurations of models by filtering cards that contain 'distill', 'qwen2.5', '7b' while excluding certain base models and incorrect model ID patterns, uncovering unique model variants.
Filtered Model Cards Count
Finds the count of entries with specific card details that include 'distill', 'qwen2.5', '7b' but exclude certain base models, revealing valuable insights about the dataset's content distribution.
Filtered Distill Qwen 7B Models
Filters for specific card entries containing 'distill', 'qwen', and '7b', excluding certain strings and patterns, to identify relevant model configurations.
Filtered Qwen-7b Model Cards
The query performs a detailed filtering based on specific keywords and excludes certain entries, which could be useful for identifying a specific subset of cards but does not provide deeper insights or trends.
Filtered Qwen 7B Model Cards
The query filters for specific terms related to "distilled" or "distill", "qwen", and "7b" in the 'card' column but excludes certain base models, providing a limited set of entries for further inspection.
Qwen 7B Distilled Models
The query provides a basic filtering of records to find specific card names that include keywords related to distilled Qwen 7b models, excluding a particular base model, which gives limited insight but helps in focusing on relevant entries.
Qwen 7B Distilled Model Cards
The query filters data based on specific keywords in the modelId and card fields, providing limited insight primarily useful for locating specific entries rather than revealing broad patterns or trends.
Qwen 7B Distilled Models
Finds all entries containing the terms 'distilled', 'qwen', and '7b' in a case-insensitive manner, providing a filtered set of records but without deeper analysis.
Distilled Qwen 7B Models
The query filters for specific model IDs containing 'distilled', 'qwen', and '7b', providing a basic retrieval of relevant entries but without deeper analysis or insight.
Filtered Model Cards with Distill Qwen2.
Filters and retrieves records containing specific keywords in the card description while excluding certain phrases, providing a basic count of relevant entries.
Filtered Model Cards with Distill Qwen 7
The query filters specific variations of card descriptions containing 'distill', 'qwen', and '7b' while excluding a particular base model, providing limited but specific data retrieval.
Distill Qwen 7B Model Cards
The query filters and retrieves rows where the 'card' column contains specific keywords ('distill', 'qwen', and '7b'), providing a basic filter result that can help in identifying specific entries.