modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-08-26 18:28:45
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 521
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-08-26 18:28:30
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
prateeky2806/bert-base-uncased-cola-epochs-10-lr-5e-05
|
prateeky2806
| 2023-09-26T03:10:04Z | 108 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-26T02:59:59Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
model-index:
- name: bert-base-uncased-cola-epochs-10-lr-5e-05
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
config: cola
split: train
args: cola
metrics:
- name: Matthews Correlation
type: matthews_correlation
value: 0.5435768262757358
---
<!-- 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-uncased-cola-epochs-10-lr-5e-05
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3812
- Matthews Correlation: 0.5436
## 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: 32
- eval_batch_size: 32
- seed: 28
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
| No log | 1.0 | 265 | 0.5922 | 0.4074 |
| 0.4065 | 2.0 | 530 | 0.4494 | 0.6144 |
| 0.4065 | 3.0 | 795 | 0.4548 | 0.5738 |
| 0.1623 | 4.0 | 1060 | 0.6883 | 0.5687 |
| 0.1623 | 5.0 | 1325 | 0.7222 | 0.5183 |
| 0.081 | 6.0 | 1590 | 1.0246 | 0.5371 |
| 0.081 | 7.0 | 1855 | 1.1457 | 0.5145 |
| 0.0344 | 8.0 | 2120 | 1.1771 | 0.5436 |
| 0.0344 | 9.0 | 2385 | 1.3187 | 0.5485 |
| 0.0123 | 10.0 | 2650 | 1.3812 | 0.5436 |
### Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3
|
langecod/Financial_Phrasebank_RoBERTa
|
langecod
| 2023-09-26T03:05:48Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"text-classification",
"dataset:financial_phrasebank",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-23T02:38:58Z |
---
datasets:
- financial_phrasebank
---
|
otmanon/ppo-LunarLander-v2
|
otmanon
| 2023-09-26T02:53:50Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-26T02:53:29Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: MlpPolicy2
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 253.60 +/- 41.27
name: mean_reward
verified: false
---
# **MlpPolicy2** Agent playing **LunarLander-v2**
This is a trained model of a **MlpPolicy2** 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
...
```
|
CyberHarem/matsubara_kanon_bangdream
|
CyberHarem
| 2023-09-26T02:45:06Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/matsubara_kanon_bangdream",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-26T02:28:36Z |
---
license: mit
datasets:
- CyberHarem/matsubara_kanon_bangdream
pipeline_tag: text-to-image
tags:
- art
---
# Lora of matsubara_kanon_bangdream
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 7200, you need to download `7200/matsubara_kanon_bangdream.pt` as the embedding and `7200/matsubara_kanon_bangdream.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 7200**, with the score of 0.983. The trigger words are:
1. `matsubara_kanon_bangdream`
2. `blue_hair, purple_eyes, bangs, long_hair, blush, smile, ribbon, hair_ornament, light_blue_hair, open_mouth, one_side_up, hair_ribbon, hair_flower`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:---------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| **7200** | **0.983** | [**Download**](7200/matsubara_kanon_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7200/previews/nude.png) | [<NSFW, click to see>](7200/previews/nude2.png) |  |  |
| 6720 | 0.977 | [Download](6720/matsubara_kanon_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6720/previews/nude.png) | [<NSFW, click to see>](6720/previews/nude2.png) |  |  |
| 6240 | 0.977 | [Download](6240/matsubara_kanon_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6240/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6240/previews/nude.png) | [<NSFW, click to see>](6240/previews/nude2.png) |  |  |
| 5760 | 0.969 | [Download](5760/matsubara_kanon_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5760/previews/nude.png) | [<NSFW, click to see>](5760/previews/nude2.png) |  |  |
| 5280 | 0.983 | [Download](5280/matsubara_kanon_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5280/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5280/previews/nude.png) | [<NSFW, click to see>](5280/previews/nude2.png) |  |  |
| 4800 | 0.978 | [Download](4800/matsubara_kanon_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4800/previews/nude.png) | [<NSFW, click to see>](4800/previews/nude2.png) |  |  |
| 4320 | 0.972 | [Download](4320/matsubara_kanon_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4320/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4320/previews/nude.png) | [<NSFW, click to see>](4320/previews/nude2.png) |  |  |
| 3840 | 0.973 | [Download](3840/matsubara_kanon_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3840/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3840/previews/nude.png) | [<NSFW, click to see>](3840/previews/nude2.png) |  |  |
| 3360 | 0.975 | [Download](3360/matsubara_kanon_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3360/previews/nude.png) | [<NSFW, click to see>](3360/previews/nude2.png) |  |  |
| 2880 | 0.968 | [Download](2880/matsubara_kanon_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2880/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2880/previews/nude.png) | [<NSFW, click to see>](2880/previews/nude2.png) |  |  |
| 2400 | 0.970 | [Download](2400/matsubara_kanon_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2400/previews/nude.png) | [<NSFW, click to see>](2400/previews/nude2.png) |  |  |
| 1920 | 0.963 | [Download](1920/matsubara_kanon_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1920/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1920/previews/nude.png) | [<NSFW, click to see>](1920/previews/nude2.png) |  |  |
| 1440 | 0.958 | [Download](1440/matsubara_kanon_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1440/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1440/previews/nude.png) | [<NSFW, click to see>](1440/previews/nude2.png) |  |  |
| 960 | 0.954 | [Download](960/matsubara_kanon_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](960/previews/bondage.png) |  |  |  | [<NSFW, click to see>](960/previews/nude.png) | [<NSFW, click to see>](960/previews/nude2.png) |  |  |
| 480 | 0.898 | [Download](480/matsubara_kanon_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](480/previews/bondage.png) |  |  |  | [<NSFW, click to see>](480/previews/nude.png) | [<NSFW, click to see>](480/previews/nude2.png) |  |  |
|
chgenly/poca-SoccerTwos
|
chgenly
| 2023-09-26T02:38:55Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SoccerTwos",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
] |
reinforcement-learning
| 2023-09-26T02:38:50Z |
---
library_name: ml-agents
tags:
- SoccerTwos
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SoccerTwos
---
# **poca** Agent playing **SoccerTwos**
This is a trained model of a **poca** agent playing **SoccerTwos**
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: chgenly/poca-SoccerTwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
wangrongsheng/careqwen-14B-Chat-sft-multi
|
wangrongsheng
| 2023-09-26T02:18:16Z | 2 | 1 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-26T02:17:21Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- 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: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
|
mozci/nonstablediff
|
mozci
| 2023-09-26T02:18:13Z | 1 | 0 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"dataset:mozci/tinysketch",
"base_model:CompVis/stable-diffusion-v1-4",
"base_model:adapter:CompVis/stable-diffusion-v1-4",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-08-17T01:24:25Z |
---
license: creativeml-openrail-m
base_model: CompVis/stable-diffusion-v1-4
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
datasets:
- mozci/tinysketch
library_name: diffusers
pipeline_tag: text-to-image
---
# LoRA text2image fine-tuning - mozci/nonstablediff
Stable diffusion fine-tuning to achieve simple sketches as the outputs. These are LoRA adaption weights for CompVis/stable-diffusion-v1-4. The weights were fine-tuned on the mozci/tinysketch dataset. You can find some example images in the following.
|
mdavidson83/ludwig-webinar
|
mdavidson83
| 2023-09-26T01:57:17Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-26T01:57:15Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- 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: True
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- 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: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0
- PEFT 0.5.0
|
deniskocs/bert-base-uncased-pretrained
|
deniskocs
| 2023-09-26T01:38:04Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-26T01:35:26Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: bert-base-uncased-pretrained
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. -->
# bert-base-uncased-pretrained
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.3158
- Train Accuracy: 0.8724
- Validation Loss: 0.3608
- Validation Accuracy: 0.8431
- Epoch: 1
## 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': 5e-05, 'decay_steps': 918, '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-07, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.5306 | 0.7238 | 0.4100 | 0.8186 | 0 |
| 0.3158 | 0.8724 | 0.3608 | 0.8431 | 1 |
### Framework versions
- Transformers 4.33.2
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.13.3
|
erkam/sg2im-256-bs-16x2-lr1e4
|
erkam
| 2023-09-26T01:35:01Z | 0 | 0 |
diffusers
|
[
"diffusers",
"sg-to-image",
"scene-graph",
"stable-diffusion",
"stable-diffusion-diffusers",
"lora",
"base_model:stabilityai/stable-diffusion-2",
"base_model:adapter:stabilityai/stable-diffusion-2",
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-24T01:26:13Z |
---
license: creativeml-openrail-m
base_model: stabilityai/stable-diffusion-2
tags:
- sg-to-image
- scene-graph
- stable-diffusion
- stable-diffusion-diffusers
- diffusers
- lora
inference: true
---
# LoRA text2image fine-tuning - erkam/sg2im-256-bs-16x2-lr1e4
These are LoRA adaption weights for stabilityai/stable-diffusion-2. The weights were fine-tuned on the vg dataset. You can find some example images in the following.
|
bobbobok/privateGPT
|
bobbobok
| 2023-09-26T01:30:41Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-09-26T01:29:24Z |
privateGPT
Ask questions to your documents without an internet connection, using the power of LLMs. 100% private, no data leaves your execution environment at any point. You can ingest documents and ask questions without an internet connection!
👂 Need help applying PrivateGPT to your specific use case? Let us know more about it and we'll try to help! We are refining PrivateGPT through your feedback.
demo
Built with LangChain, LlamaIndex, GPT4All, LlamaCpp, Chroma and SentenceTransformers.
Environment Setup
In order to set your environment up to run the code here, first install all requirements:
pip3 install -r requirements.txt
Alternative requirements installation with poetry
Install poetry
Run this commands
cd privateGPT
poetry install
poetry shell
Then, download the LLM model and place it in a directory of your choice:
LLM: default to ggml-gpt4all-j-v1.3-groovy.bin. If you prefer a different GPT4All-J compatible model, just download it and reference it in your .env file.
Copy the example.env template into .env
cp example.env .env
and edit the variables appropriately in the .env file.
MODEL_TYPE: supports LlamaCpp or GPT4All
PERSIST_DIRECTORY: is the folder you want your vectorstore in
MODEL_PATH: Path to your GPT4All or LlamaCpp supported LLM
MODEL_N_CTX: Maximum token limit for the LLM model
MODEL_N_BATCH: Number of tokens in the prompt that are fed into the model at a time. Optimal value differs a lot depending on the model (8 works well for GPT4All, and 1024 is better for LlamaCpp)
EMBEDDINGS_MODEL_NAME: SentenceTransformers embeddings model name (see https://www.sbert.net/docs/pretrained_models.html)
TARGET_SOURCE_CHUNKS: The amount of chunks (sources) that will be used to answer a question
Note: because of the way langchain loads the SentenceTransformers embeddings, the first time you run the script it will require internet connection to download the embeddings model itself.
Test dataset
This repo uses a state of the union transcript as an example.
Instructions for ingesting your own dataset
Put any and all your files into the source_documents directory
The supported extensions are:
.csv: CSV,
.docx: Word Document,
.doc: Word Document,
.enex: EverNote,
.eml: Email,
.epub: EPub,
.html: HTML File,
.md: Markdown,
.msg: Outlook Message,
.odt: Open Document Text,
.pdf: Portable Document Format (PDF),
.pptx : PowerPoint Document,
.ppt : PowerPoint Document,
.txt: Text file (UTF-8),
Run the following command to ingest all the data.
python ingest.py
Output should look like this:
Creating new vectorstore
Loading documents from source_documents
Loading new documents: 100%|██████████████████████| 1/1 [00:01<00:00, 1.73s/it]
Loaded 1 new documents from source_documents
Split into 90 chunks of text (max. 500 tokens each)
Creating embeddings. May take some minutes...
Using embedded DuckDB with persistence: data will be stored in: db
Ingestion complete! You can now run privateGPT.py to query your documents
It will create a db folder containing the local vectorstore. Will take 20-30 seconds per document, depending on the size of the document. You can ingest as many documents as you want, and all will be accumulated in the local embeddings database. If you want to start from an empty database, delete the db folder.
Note: during the ingest process no data leaves your local environment. You could ingest without an internet connection, except for the first time you run the ingest script, when the embeddings model is downloaded.
Ask questions to your documents, locally!
In order to ask a question, run a command like:
python privateGPT.py
And wait for the script to require your input.
> Enter a query:
Hit enter. You'll need to wait 20-30 seconds (depending on your machine) while the LLM model consumes the prompt and prepares the answer. Once done, it will print the answer and the 4 sources it used as context from your documents; you can then ask another question without re-running the script, just wait for the prompt again.
Note: you could turn off your internet connection, and the script inference would still work. No data gets out of your local environment.
Type exit to finish the script.
CLI
The script also supports optional command-line arguments to modify its behavior. You can see a full list of these arguments by running the command python privateGPT.py --help in your terminal.
How does it work?
Selecting the right local models and the power of LangChain you can run the entire pipeline locally, without any data leaving your environment, and with reasonable performance.
ingest.py uses LangChain tools to parse the document and create embeddings locally using HuggingFaceEmbeddings (SentenceTransformers). It then stores the result in a local vector database using Chroma vector store.
privateGPT.py uses a local LLM based on GPT4All-J or LlamaCpp to understand questions and create answers. The context for the answers is extracted from the local vector store using a similarity search to locate the right piece of context from the docs.
GPT4All-J wrapper was introduced in LangChain 0.0.162.
System Requirements
Python Version
To use this software, you must have Python 3.10 or later installed. Earlier versions of Python will not compile.
C++ Compiler
If you encounter an error while building a wheel during the pip install process, you may need to install a C++ compiler on your computer.
For Windows 10/11
To install a C++ compiler on Windows 10/11, follow these steps:
Install Visual Studio 2022.
Make sure the following components are selected:
Universal Windows Platform development
C++ CMake tools for Windows
Download the MinGW installer from the MinGW website.
Run the installer and select the gcc component.
Mac Running Intel
When running a Mac with Intel hardware (not M1), you may run into clang: error: the clang compiler does not support '-march=native' during pip install.
If so set your archflags during pip install. eg: ARCHFLAGS="-arch x86_64" pip3 install -r requirements.txt
Disclaimer
This is a test project to validate the feasibility of a fully private solution for question answering using LLMs and Vector embeddings. It is not production ready, and it is not meant to be used in production. The models selection is not optimized for performance, but for privacy; but it is possible to use different models and vectorstores to improve performance.
|
dlby/llm_model_new3
|
dlby
| 2023-09-26T01:21:16Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-26T01:21:12Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- 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: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.0.dev0
|
iainmcqueen/coffee_model3
|
iainmcqueen
| 2023-09-26T01:19:19Z | 32 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"base_model:CompVis/stable-diffusion-v1-4",
"base_model:finetune:CompVis/stable-diffusion-v1-4",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-26T01:03:32Z |
---
license: creativeml-openrail-m
base_model: CompVis/stable-diffusion-v1-4
instance_prompt: a photo of a cts coffee cup
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - iainmcqueen/coffee_model3
This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of a cts coffee cup using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: True.
|
CyberHarem/ichigaya_arisa_bangdream
|
CyberHarem
| 2023-09-26T01:12:31Z | 0 | 1 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/ichigaya_arisa_bangdream",
"license:mit",
"region:us"
] |
text-to-image
| 2023-08-14T13:05:28Z |
---
license: mit
datasets:
- CyberHarem/ichigaya_arisa_bangdream
pipeline_tag: text-to-image
tags:
- art
---
# Lora of ichigaya_arisa_bangdream
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 5520, you need to download `5520/ichigaya_arisa_bangdream.pt` as the embedding and `5520/ichigaya_arisa_bangdream.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 5520**, with the score of 0.941. The trigger words are:
1. `ichigaya_arisa_bangdream`
2. `blonde_hair, long_hair, bangs, hair_ornament, blush, twintails, x_hair_ornament, yellow_eyes, sidelocks, open_mouth, brown_eyes, smile, breasts`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:--------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:----------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 6900 | 0.937 | [Download](6900/ichigaya_arisa_bangdream.zip) |  |  |  |  |  |  | [<NSFW, click to see>](6900/previews/pattern_7.png) |  |  |  | [<NSFW, click to see>](6900/previews/bikini.png) | [<NSFW, click to see>](6900/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6900/previews/nude.png) | [<NSFW, click to see>](6900/previews/nude2.png) |  |  |
| 6440 | 0.939 | [Download](6440/ichigaya_arisa_bangdream.zip) |  |  |  |  |  |  | [<NSFW, click to see>](6440/previews/pattern_7.png) |  |  |  | [<NSFW, click to see>](6440/previews/bikini.png) | [<NSFW, click to see>](6440/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6440/previews/nude.png) | [<NSFW, click to see>](6440/previews/nude2.png) |  |  |
| 5980 | 0.919 | [Download](5980/ichigaya_arisa_bangdream.zip) |  |  |  |  |  |  | [<NSFW, click to see>](5980/previews/pattern_7.png) |  |  |  | [<NSFW, click to see>](5980/previews/bikini.png) | [<NSFW, click to see>](5980/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5980/previews/nude.png) | [<NSFW, click to see>](5980/previews/nude2.png) |  |  |
| **5520** | **0.941** | [**Download**](5520/ichigaya_arisa_bangdream.zip) |  |  |  |  |  |  | [<NSFW, click to see>](5520/previews/pattern_7.png) |  |  |  | [<NSFW, click to see>](5520/previews/bikini.png) | [<NSFW, click to see>](5520/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5520/previews/nude.png) | [<NSFW, click to see>](5520/previews/nude2.png) |  |  |
| 5060 | 0.929 | [Download](5060/ichigaya_arisa_bangdream.zip) |  |  |  |  |  |  | [<NSFW, click to see>](5060/previews/pattern_7.png) |  |  |  | [<NSFW, click to see>](5060/previews/bikini.png) | [<NSFW, click to see>](5060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5060/previews/nude.png) | [<NSFW, click to see>](5060/previews/nude2.png) |  |  |
| 4600 | 0.931 | [Download](4600/ichigaya_arisa_bangdream.zip) |  |  |  |  |  |  | [<NSFW, click to see>](4600/previews/pattern_7.png) |  |  |  | [<NSFW, click to see>](4600/previews/bikini.png) | [<NSFW, click to see>](4600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4600/previews/nude.png) | [<NSFW, click to see>](4600/previews/nude2.png) |  |  |
| 4140 | 0.931 | [Download](4140/ichigaya_arisa_bangdream.zip) |  |  |  |  |  |  | [<NSFW, click to see>](4140/previews/pattern_7.png) |  |  |  | [<NSFW, click to see>](4140/previews/bikini.png) | [<NSFW, click to see>](4140/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4140/previews/nude.png) | [<NSFW, click to see>](4140/previews/nude2.png) |  |  |
| 3680 | 0.904 | [Download](3680/ichigaya_arisa_bangdream.zip) |  |  |  |  |  |  | [<NSFW, click to see>](3680/previews/pattern_7.png) |  |  |  | [<NSFW, click to see>](3680/previews/bikini.png) | [<NSFW, click to see>](3680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3680/previews/nude.png) | [<NSFW, click to see>](3680/previews/nude2.png) |  |  |
| 3220 | 0.913 | [Download](3220/ichigaya_arisa_bangdream.zip) |  |  |  |  |  |  | [<NSFW, click to see>](3220/previews/pattern_7.png) |  |  |  | [<NSFW, click to see>](3220/previews/bikini.png) | [<NSFW, click to see>](3220/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3220/previews/nude.png) | [<NSFW, click to see>](3220/previews/nude2.png) |  |  |
| 2760 | 0.931 | [Download](2760/ichigaya_arisa_bangdream.zip) |  |  |  |  |  |  | [<NSFW, click to see>](2760/previews/pattern_7.png) |  |  |  | [<NSFW, click to see>](2760/previews/bikini.png) | [<NSFW, click to see>](2760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2760/previews/nude.png) | [<NSFW, click to see>](2760/previews/nude2.png) |  |  |
| 2300 | 0.906 | [Download](2300/ichigaya_arisa_bangdream.zip) |  |  |  |  |  |  | [<NSFW, click to see>](2300/previews/pattern_7.png) |  |  |  | [<NSFW, click to see>](2300/previews/bikini.png) | [<NSFW, click to see>](2300/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2300/previews/nude.png) | [<NSFW, click to see>](2300/previews/nude2.png) |  |  |
| 1840 | 0.928 | [Download](1840/ichigaya_arisa_bangdream.zip) |  |  |  |  |  |  | [<NSFW, click to see>](1840/previews/pattern_7.png) |  |  |  | [<NSFW, click to see>](1840/previews/bikini.png) | [<NSFW, click to see>](1840/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1840/previews/nude.png) | [<NSFW, click to see>](1840/previews/nude2.png) |  |  |
| 1380 | 0.857 | [Download](1380/ichigaya_arisa_bangdream.zip) |  |  |  |  |  |  | [<NSFW, click to see>](1380/previews/pattern_7.png) |  |  |  | [<NSFW, click to see>](1380/previews/bikini.png) | [<NSFW, click to see>](1380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1380/previews/nude.png) | [<NSFW, click to see>](1380/previews/nude2.png) |  |  |
| 920 | 0.880 | [Download](920/ichigaya_arisa_bangdream.zip) |  |  |  |  |  |  | [<NSFW, click to see>](920/previews/pattern_7.png) |  |  |  | [<NSFW, click to see>](920/previews/bikini.png) | [<NSFW, click to see>](920/previews/bondage.png) |  |  |  | [<NSFW, click to see>](920/previews/nude.png) | [<NSFW, click to see>](920/previews/nude2.png) |  |  |
| 460 | 0.812 | [Download](460/ichigaya_arisa_bangdream.zip) |  |  |  |  |  |  | [<NSFW, click to see>](460/previews/pattern_7.png) |  |  |  | [<NSFW, click to see>](460/previews/bikini.png) | [<NSFW, click to see>](460/previews/bondage.png) |  |  |  | [<NSFW, click to see>](460/previews/nude.png) | [<NSFW, click to see>](460/previews/nude2.png) |  |  |
|
CyberHarem/tennouji_rina_loveliveschoolidolfestivalallstars
|
CyberHarem
| 2023-09-26T01:07:09Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/tennouji_rina_loveliveschoolidolfestivalallstars",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-26T00:54:31Z |
---
license: mit
datasets:
- CyberHarem/tennouji_rina_loveliveschoolidolfestivalallstars
pipeline_tag: text-to-image
tags:
- art
---
# Lora of tennouji_rina_loveliveschoolidolfestivalallstars
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 4800, you need to download `4800/tennouji_rina_loveliveschoolidolfestivalallstars.pt` as the embedding and `4800/tennouji_rina_loveliveschoolidolfestivalallstars.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 4800**, with the score of 0.969. The trigger words are:
1. `tennouji_rina_loveliveschoolidolfestivalallstars`
2. `pink_hair, bangs, ahoge, blunt_bangs, yellow_eyes, short_hair, blush, blunt_ends`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:--------------------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 7200 | 0.955 | [Download](7200/tennouji_rina_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7200/previews/nude.png) | [<NSFW, click to see>](7200/previews/nude2.png) |  |  |
| 6720 | 0.952 | [Download](6720/tennouji_rina_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6720/previews/nude.png) | [<NSFW, click to see>](6720/previews/nude2.png) |  |  |
| 6240 | 0.968 | [Download](6240/tennouji_rina_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6240/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6240/previews/nude.png) | [<NSFW, click to see>](6240/previews/nude2.png) |  |  |
| 5760 | 0.960 | [Download](5760/tennouji_rina_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5760/previews/nude.png) | [<NSFW, click to see>](5760/previews/nude2.png) |  |  |
| 5280 | 0.951 | [Download](5280/tennouji_rina_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5280/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5280/previews/nude.png) | [<NSFW, click to see>](5280/previews/nude2.png) |  |  |
| **4800** | **0.969** | [**Download**](4800/tennouji_rina_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4800/previews/nude.png) | [<NSFW, click to see>](4800/previews/nude2.png) |  |  |
| 4320 | 0.946 | [Download](4320/tennouji_rina_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4320/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4320/previews/nude.png) | [<NSFW, click to see>](4320/previews/nude2.png) |  |  |
| 3840 | 0.946 | [Download](3840/tennouji_rina_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3840/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3840/previews/nude.png) | [<NSFW, click to see>](3840/previews/nude2.png) |  |  |
| 3360 | 0.944 | [Download](3360/tennouji_rina_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3360/previews/nude.png) | [<NSFW, click to see>](3360/previews/nude2.png) |  |  |
| 2880 | 0.932 | [Download](2880/tennouji_rina_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2880/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2880/previews/nude.png) | [<NSFW, click to see>](2880/previews/nude2.png) |  |  |
| 2400 | 0.954 | [Download](2400/tennouji_rina_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2400/previews/nude.png) | [<NSFW, click to see>](2400/previews/nude2.png) |  |  |
| 1920 | 0.948 | [Download](1920/tennouji_rina_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1920/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1920/previews/nude.png) | [<NSFW, click to see>](1920/previews/nude2.png) |  |  |
| 1440 | 0.924 | [Download](1440/tennouji_rina_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1440/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1440/previews/nude.png) | [<NSFW, click to see>](1440/previews/nude2.png) |  |  |
| 960 | 0.923 | [Download](960/tennouji_rina_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](960/previews/bondage.png) |  |  |  | [<NSFW, click to see>](960/previews/nude.png) | [<NSFW, click to see>](960/previews/nude2.png) |  |  |
| 480 | 0.908 | [Download](480/tennouji_rina_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](480/previews/bondage.png) |  |  |  | [<NSFW, click to see>](480/previews/nude.png) | [<NSFW, click to see>](480/previews/nude2.png) |  |  |
|
prateeky2806/bert-base-uncased-mrpc-lora-epochs-10-lr-0.0005
|
prateeky2806
| 2023-09-26T01:03:22Z | 0 | 0 | null |
[
"safetensors",
"generated_from_trainer",
"dataset:glue",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"region:us"
] | null | 2023-09-26T00:55:08Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert-base-uncased-mrpc-lora-epochs-10-lr-0.0005
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. -->
# bert-base-uncased-mrpc-lora-epochs-10-lr-0.0005
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1795
- Accuracy: 0.8
- F1: 0.8611
## 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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 28
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| No log | 1.0 | 112 | 0.5047 | 0.76 | 0.8333 |
| No log | 2.0 | 224 | 0.4400 | 0.78 | 0.8358 |
| No log | 3.0 | 336 | 0.5103 | 0.78 | 0.8406 |
| No log | 4.0 | 448 | 0.6321 | 0.78 | 0.8382 |
| 0.3586 | 5.0 | 560 | 0.8909 | 0.73 | 0.8 |
| 0.3586 | 6.0 | 672 | 0.8763 | 0.77 | 0.8369 |
| 0.3586 | 7.0 | 784 | 1.0331 | 0.8 | 0.8571 |
| 0.3586 | 8.0 | 896 | 1.1871 | 0.8 | 0.8611 |
| 0.0479 | 9.0 | 1008 | 1.1310 | 0.79 | 0.8552 |
| 0.0479 | 10.0 | 1120 | 1.1795 | 0.8 | 0.8611 |
### Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3
|
prateeky2806/bert-base-uncased-mrpc-ia3-epochs-10-lr-0.005
|
prateeky2806
| 2023-09-26T01:03:21Z | 0 | 0 | null |
[
"safetensors",
"generated_from_trainer",
"dataset:glue",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"region:us"
] | null | 2023-09-26T00:56:31Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert-base-uncased-mrpc-ia3-epochs-10-lr-0.005
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. -->
# bert-base-uncased-mrpc-ia3-epochs-10-lr-0.005
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7044
- Accuracy: 0.76
- F1: 0.8333
## 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: 0.005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 28
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| No log | 1.0 | 112 | 0.5477 | 0.73 | 0.7939 |
| No log | 2.0 | 224 | 0.4859 | 0.76 | 0.8356 |
| No log | 3.0 | 336 | 0.5785 | 0.74 | 0.8354 |
| No log | 4.0 | 448 | 0.5441 | 0.8 | 0.8667 |
| 0.4779 | 5.0 | 560 | 0.5720 | 0.75 | 0.8120 |
| 0.4779 | 6.0 | 672 | 0.5316 | 0.73 | 0.8029 |
| 0.4779 | 7.0 | 784 | 0.6077 | 0.76 | 0.8356 |
| 0.4779 | 8.0 | 896 | 0.6960 | 0.74 | 0.8243 |
| 0.2391 | 9.0 | 1008 | 0.6872 | 0.75 | 0.8252 |
| 0.2391 | 10.0 | 1120 | 0.7044 | 0.76 | 0.8333 |
### Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3
|
malanevans/pixelcopter-v5
|
malanevans
| 2023-09-26T00:57:47Z | 0 | 0 | null |
[
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-26T00:57:41Z |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: pixelcopter-v5
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 24.00 +/- 15.84
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
prateeky2806/bert-base-uncased-cola-lora-epochs-10-lr-0.0005
|
prateeky2806
| 2023-09-26T00:57:39Z | 0 | 0 | null |
[
"safetensors",
"generated_from_trainer",
"dataset:glue",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"region:us"
] | null | 2023-09-26T00:34:05Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
model-index:
- name: bert-base-uncased-cola-lora-epochs-10-lr-0.0005
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. -->
# bert-base-uncased-cola-lora-epochs-10-lr-0.0005
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7759
- Matthews Correlation: 0.6347
## 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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 28
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
| No log | 1.0 | 265 | 0.6135 | 0.2906 |
| 0.4571 | 2.0 | 530 | 0.4470 | 0.4851 |
| 0.4571 | 3.0 | 795 | 0.3926 | 0.5648 |
| 0.2553 | 4.0 | 1060 | 0.4631 | 0.5358 |
| 0.2553 | 5.0 | 1325 | 0.4592 | 0.5145 |
| 0.1378 | 6.0 | 1590 | 0.8133 | 0.5608 |
| 0.1378 | 7.0 | 1855 | 0.6745 | 0.6815 |
| 0.081 | 8.0 | 2120 | 0.6891 | 0.6815 |
| 0.081 | 9.0 | 2385 | 0.6823 | 0.6110 |
| 0.0512 | 10.0 | 2650 | 0.7759 | 0.6347 |
### Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3
|
ouasdg/redpj3B-lora-int8-alpaca
|
ouasdg
| 2023-09-26T00:53:48Z | 8 | 0 |
peft
|
[
"peft",
"base_model:togethercomputer/RedPajama-INCITE-Base-3B-v1",
"base_model:adapter:togethercomputer/RedPajama-INCITE-Base-3B-v1",
"region:us"
] | null | 2023-06-28T23:41:25Z |
---
library_name: peft
base_model: togethercomputer/RedPajama-INCITE-Base-3B-v1
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- 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
The following `bitsandbytes` quantization config was used during training:
- 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
The following `bitsandbytes` quantization config was used during training:
- 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
The following `bitsandbytes` quantization config was used during training:
- 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
### Framework versions
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
|
nelson2424/mt0-small-lora-finetune-grocery-ner-v2
|
nelson2424
| 2023-09-26T00:50:18Z | 2 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-25T22:42:50Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0
|
malanevans/pixelcopter-v4
|
malanevans
| 2023-09-26T00:35:45Z | 0 | 0 | null |
[
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-26T00:35:40Z |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: pixelcopter-v4
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 21.30 +/- 22.98
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
jmoney54378256438905/jondurbin_airoboros-l2-13b-2.2.1-4.65bpw
|
jmoney54378256438905
| 2023-09-26T00:31:43Z | 5 | 0 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-2.2.1",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-25T23:16:19Z |
---
license: llama2
datasets:
- jondurbin/airoboros-2.2.1
---
### Overview
Another experimental model, using mostly sythetic data generated by [airoboros](https://github.com/jondurbin/airoboros)
This is essentially a minor "fix" branch of [airoboros-l2-13b-2.2](https://hf.co/jondurbin/airoboros-l2-13b-2.2) with a updates, primarily:
- [re-generated writing responses](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#re-generated-writing-responses)
- [longer contextual blocks](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#longer-contextual-blocks)
- [removal of "rp" data](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#rp-category-removed)
- [(less aggressive) de-censoring](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#de-censoring)
- more fine-tuning epochs
This is a fairly general purpose model, but focuses heavily on instruction following, rather than casual chat/roleplay.
Huge thank you to the folks over at [a16z](https://a16z.com/) for sponsoring the costs associated with building models and associated tools!
### Prompt format
The prompt format:
```
A chat.
USER: {prompt}
ASSISTANT:
```
The default system prompt ("A chat.") was used for most of the prompts, however it also included a wide sampling of responses with other prompts, particularly in "stylized\_response", "rp", "gtkm", etc.
Here's another example:
```
A chat between Bob (aka USER) and Tom (aka ASSISTANT). Tom is an extremely intelligent 18th century bookkeeper, who speaks loquaciously.
USER: {prompt}
ASSISTANT:
```
And chat scenario that wouldn't require USER/ASSISTANT (but should use stopping criteria to prevent the model from speaking on your behalf).
```
A chat between old friends: Timmy and Tommy.
{description of characters}
{setting for the chat}
Timmy: *takes a big sip from his coffee* "Ah, sweet, delicious, magical coffee."
Tommy:
```
__*I strongly suggest adding stopping criteria/early inference stopping on "USER:", and/or whatever names you specify in the system prompt.*__
### Fine tuning info
https://wandb.ai/jondurbin/airoboros-l2-13b-2.2.1/runs/zbz8mgaz?workspace=user-jondurbin
### Helpful usage tips
*The prompts shown here are are just the text that would be included after USER: and before ASSISTANT: in the full prompt format above, the system prompt and USER:/ASSISTANT: have been omited for readability.*
#### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
#### Summarization
500 samples have been included from [this dataset](https://huggingface.co/datasets/mattpscott/airoboros-summarization), using the same format as contextual question answering, for example:
```
BEGININPUT
{text to summarize}
ENDINPUT
BEGININSTRUCTION
Summarize the input in around 130 words.
ENDINSTRUCTION
```
#### Getting longer responses
You can use a few techniques to get longer responses.
Detailed prompts, with explicit instruction for word count:
```
Please compose a narrative set in the heart of an ancient library, steeped in the scent of old parchment and ink. The protagonist should be a young scholar who is dedicated to studying the art of storytelling and its evolution throughout history. In her pursuit of knowledge, she stumbles upon a forgotten tome that seems to possess an unusual aura. This book has the ability to bring stories to life, literally manifesting characters and scenarios from within its pages into reality.
The main character must navigate through various epochs of storytelling - from oral traditions of tribal societies, through medieval minstrels' tales, to modern-day digital narratives - as they come alive around her. Each era presents its unique challenges and lessons about the power and impact of stories on human civilization.
One such character could be a sentient quill pen, who was once used by renowned authors of yesteryears and now holds their wisdom and experiences. It becomes her mentor, guiding her through this journey with witty remarks and insightful commentary.
Ensure that your tale encapsulates the thrill of adventure, the beauty of learning, and the profound connection between humans and their stories. All characters involved should be non-human entities. Feel free to explore creative liberties but maintain the mentioned elements.
Your response should be approximately 2300 words.
```
Or, a simpler example:
```
Please create a long, detailed story about a dragon in an old growth forest who, for some reason, begins speaking the words of the source code of linux.
```
#### Coding
You can ask for fairly complex coding instructions with multiple criteria, e.g.:
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or inline criteria:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can also optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
#### Agent/function calling
The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML.
Example prompt:
```
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.
Input: I want to know how many times 'Python' is mentioned in my text file.
Available functions:
file_analytics:
description: This tool performs various operations on a text file.
params:
action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
filters:
keyword: The word or phrase we want to search for.
```
Response:
```json
{
"function": "file_analytics",
"params": {
"action": "count_occurrences",
"filters": {
"keyword": "Python"
}
}
}
```
#### Chain-of-thought
You can ask for several possible responses to a given problem, with a ranking and final answer selection.
Example prompt:
```
A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one.
```
Example response:
```
Solution 1:
In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players).
The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:
n(n-1)/2 = 45
Solving this equation gives us n=10.
Final answer: There were 10 players in the tournament.
Solution 2:
Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers.
If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.
Final answer: There were 10 players in the tournament.
Solution 3:
We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played.
Final answer: There were 10 players in the tournament.
Ranking of solutions from best to worst:
1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer.
2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer.
3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer.
Best and final answer: There were 10 players in the tournament.
```
#### reWOO style execution planning
The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!
Example prompt:
```
Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.
Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?
The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]
Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?
```
Response:
```
Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020.
:evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner]
Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate.
:evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?]
Plan: Conduct another web search to find the most famous work of the identified laureate.
:evidence2: = DuckDuckGo[Most famous work of :evidence1:]
Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search.
:evidence3: = HyperlinkExtractor[:evidence2:]
Plan: Use the TextScraper tool to extract information from the relevant links.
:evidence4: = TextScraper[:evidence3:]
Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information.
:evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?]
Answer: :evidence5:
```
For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:
```python
import re
import requests
def inject_context(input_text, **context):
for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)):
input_text = input_text.replace(ref, context.get(ref, ""))
return input_text
def duckduckgo(input_text, **context):
search_string = inject_context(input_text, **context)
... search via duck duck go using search_string
... return text content
def link_extractor(input_text, **context):
input_text = inject_context(input_text, **context)
return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I))))
def scrape(input_text, **context):
input_text = inject_context(input_text, **context)
text = []
for link in input_text.splitlines():
text.append(requests.get(link).text)
return "\n".join(text)
def infer(input_text, **context)
prompt = inject_context(input_text, **context)
... call model with prompt, return output
def parse_plan(plan):
method_map = {
"DuckDuckGo": duckduckgo,
"HyperlinkExtractor": link_extractor,
"KnowledgeModel": infer,
"TextScraper": scrape,
}
context = {}
for line in plan.strip().splitlines():
if line.startswith("Plan:"):
print(line)
continue
parts = re.match("^(:evidence[0-9]+:)\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I)
if not parts:
if line.startswith("Answer: "):
return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...")
raise RuntimeError("bad format: " + line)
context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
```
### Contribute
If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data,
take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details.
To help me with the OpenAI/compute costs:
- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
### Licence and usage restrictions
The airoboros 2.2 models are built on top of llama-2/codellama.
The llama-2 base model has a custom Meta license:
- See the [meta-license/LICENSE.txt](meta-license/LICENSE.txt) file attached for the original license provided by Meta.
- See also [meta-license/USE_POLICY.md](meta-license/USE_POLICY.md) and [meta-license/Responsible-Use-Guide.pdf](meta-license/Responsible-Use-Guide.pdf), also provided by Meta.
The fine-tuning data was mostly generated by OpenAI API calls to gpt-4, via [airoboros](https://github.com/jondurbin/airoboros)
The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely indemnify me.
|
rohitnair212/my_awesome_qa_model
|
rohitnair212
| 2023-09-26T00:26:28Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"distilbert",
"question-answering",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-09-20T00:23:42Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: my_awesome_qa_model
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. -->
# my_awesome_qa_model
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:
- Loss: 5.6377
## 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 1 | 5.7740 |
| No log | 2.0 | 2 | 5.6831 |
| No log | 3.0 | 3 | 5.6377 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
CyberHarem/yuuki_setsuna_loveliveschoolidolfestivalallstars
|
CyberHarem
| 2023-09-26T00:11:04Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/yuuki_setsuna_loveliveschoolidolfestivalallstars",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-25T23:55:15Z |
---
license: mit
datasets:
- CyberHarem/yuuki_setsuna_loveliveschoolidolfestivalallstars
pipeline_tag: text-to-image
tags:
- art
---
# Lora of yuuki_setsuna_loveliveschoolidolfestivalallstars
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 3120, you need to download `3120/yuuki_setsuna_loveliveschoolidolfestivalallstars.pt` as the embedding and `3120/yuuki_setsuna_loveliveschoolidolfestivalallstars.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 3120**, with the score of 0.978. The trigger words are:
1. `yuuki_setsuna_loveliveschoolidolfestivalallstars`
2. `black_hair, long_hair, bangs, grey_eyes, smile, sidelocks, one_side_up, breasts, blush, black_eyes, hair_ornament, medium_breasts`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | pattern_13 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:--------------------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 7800 | 0.949 | [Download](7800/yuuki_setsuna_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7800/previews/nude.png) | [<NSFW, click to see>](7800/previews/nude2.png) |  |  |
| 7280 | 0.943 | [Download](7280/yuuki_setsuna_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7280/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7280/previews/nude.png) | [<NSFW, click to see>](7280/previews/nude2.png) |  |  |
| 6760 | 0.949 | [Download](6760/yuuki_setsuna_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6760/previews/nude.png) | [<NSFW, click to see>](6760/previews/nude2.png) |  |  |
| 6240 | 0.973 | [Download](6240/yuuki_setsuna_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6240/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6240/previews/nude.png) | [<NSFW, click to see>](6240/previews/nude2.png) |  |  |
| 5720 | 0.969 | [Download](5720/yuuki_setsuna_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5720/previews/nude.png) | [<NSFW, click to see>](5720/previews/nude2.png) |  |  |
| 5200 | 0.959 | [Download](5200/yuuki_setsuna_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5200/previews/nude.png) | [<NSFW, click to see>](5200/previews/nude2.png) |  |  |
| 4680 | 0.939 | [Download](4680/yuuki_setsuna_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4680/previews/nude.png) | [<NSFW, click to see>](4680/previews/nude2.png) |  |  |
| 4160 | 0.963 | [Download](4160/yuuki_setsuna_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4160/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4160/previews/nude.png) | [<NSFW, click to see>](4160/previews/nude2.png) |  |  |
| 3640 | 0.964 | [Download](3640/yuuki_setsuna_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3640/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3640/previews/nude.png) | [<NSFW, click to see>](3640/previews/nude2.png) |  |  |
| **3120** | **0.978** | [**Download**](3120/yuuki_setsuna_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3120/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3120/previews/nude.png) | [<NSFW, click to see>](3120/previews/nude2.png) |  |  |
| 2600 | 0.954 | [Download](2600/yuuki_setsuna_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2600/previews/nude.png) | [<NSFW, click to see>](2600/previews/nude2.png) |  |  |
| 2080 | 0.968 | [Download](2080/yuuki_setsuna_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2080/previews/nude.png) | [<NSFW, click to see>](2080/previews/nude2.png) |  |  |
| 1560 | 0.953 | [Download](1560/yuuki_setsuna_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1560/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1560/previews/nude.png) | [<NSFW, click to see>](1560/previews/nude2.png) |  |  |
| 1040 | 0.940 | [Download](1040/yuuki_setsuna_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1040/previews/nude.png) | [<NSFW, click to see>](1040/previews/nude2.png) |  |  |
| 520 | 0.873 | [Download](520/yuuki_setsuna_loveliveschoolidolfestivalallstars.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](520/previews/bondage.png) |  |  |  | [<NSFW, click to see>](520/previews/nude.png) | [<NSFW, click to see>](520/previews/nude2.png) |  |  |
|
musiime678/Tinker
|
musiime678
| 2023-09-25T23:56:57Z | 0 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"en",
"dataset:nguha/legalbench",
"dataset:pile-of-law/pile-of-law",
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-25T23:54:52Z |
---
license: creativeml-openrail-m
datasets:
- nguha/legalbench
- pile-of-law/pile-of-law
language:
- en
metrics:
- accuracy
- bertscore
library_name: adapter-transformers
---
|
AmelieSchreiber/esm2_t12_35M_lora_binding_sites_1111K_cp1
|
AmelieSchreiber
| 2023-09-25T23:52:55Z | 2 | 0 |
peft
|
[
"peft",
"license:mit",
"region:us"
] | null | 2023-09-25T01:48:13Z |
---
license: mit
library_name: peft
---
## Training procedure
### Test Metrics:
```python
'eval_loss': 0.4365999102592468,
'eval_accuracy': 0.9420512498988455,
'eval_precision': 0.2294216317399737,
'eval_recall': 0.7584797572261781,
'eval_f1': 0.35228549223252686,
'eval_auc': 0.8522129916967822,
'eval_mcc': 0.39725936154292724
```
### Framework versions
- PEFT 0.5.0
|
CyberHarem/minato_yukina_bangdream
|
CyberHarem
| 2023-09-25T23:41:39Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/minato_yukina_bangdream",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-25T23:25:47Z |
---
license: mit
datasets:
- CyberHarem/minato_yukina_bangdream
pipeline_tag: text-to-image
tags:
- art
---
# Lora of minato_yukina_bangdream
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 6600, you need to download `6600/minato_yukina_bangdream.pt` as the embedding and `6600/minato_yukina_bangdream.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 6600**, with the score of 0.943. The trigger words are:
1. `minato_yukina_bangdream`
2. `long_hair, bangs, yellow_eyes, grey_hair, hair_ornament, flower, rose, jewelry, hair_flower`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | pattern_13 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| **6600** | **0.943** | [**Download**](6600/minato_yukina_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6600/previews/nude.png) | [<NSFW, click to see>](6600/previews/nude2.png) |  |  |
| 6160 | 0.938 | [Download](6160/minato_yukina_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6160/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6160/previews/nude.png) | [<NSFW, click to see>](6160/previews/nude2.png) |  |  |
| 5720 | 0.902 | [Download](5720/minato_yukina_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5720/previews/nude.png) | [<NSFW, click to see>](5720/previews/nude2.png) |  |  |
| 5280 | 0.916 | [Download](5280/minato_yukina_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5280/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5280/previews/nude.png) | [<NSFW, click to see>](5280/previews/nude2.png) |  |  |
| 4840 | 0.916 | [Download](4840/minato_yukina_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4840/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4840/previews/nude.png) | [<NSFW, click to see>](4840/previews/nude2.png) |  |  |
| 4400 | 0.913 | [Download](4400/minato_yukina_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4400/previews/nude.png) | [<NSFW, click to see>](4400/previews/nude2.png) |  |  |
| 3960 | 0.902 | [Download](3960/minato_yukina_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3960/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3960/previews/nude.png) | [<NSFW, click to see>](3960/previews/nude2.png) |  |  |
| 3520 | 0.903 | [Download](3520/minato_yukina_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3520/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3520/previews/nude.png) | [<NSFW, click to see>](3520/previews/nude2.png) |  |  |
| 3080 | 0.906 | [Download](3080/minato_yukina_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3080/previews/nude.png) | [<NSFW, click to see>](3080/previews/nude2.png) |  |  |
| 2640 | 0.906 | [Download](2640/minato_yukina_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2640/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2640/previews/nude.png) | [<NSFW, click to see>](2640/previews/nude2.png) |  |  |
| 2200 | 0.918 | [Download](2200/minato_yukina_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2200/previews/nude.png) | [<NSFW, click to see>](2200/previews/nude2.png) |  |  |
| 1760 | 0.917 | [Download](1760/minato_yukina_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1760/previews/nude.png) | [<NSFW, click to see>](1760/previews/nude2.png) |  |  |
| 1320 | 0.876 | [Download](1320/minato_yukina_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1320/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1320/previews/nude.png) | [<NSFW, click to see>](1320/previews/nude2.png) |  |  |
| 880 | 0.803 | [Download](880/minato_yukina_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](880/previews/bondage.png) |  |  |  | [<NSFW, click to see>](880/previews/nude.png) | [<NSFW, click to see>](880/previews/nude2.png) |  |  |
| 440 | 0.769 | [Download](440/minato_yukina_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](440/previews/bondage.png) |  |  |  | [<NSFW, click to see>](440/previews/nude.png) | [<NSFW, click to see>](440/previews/nude2.png) |  |  |
|
anuragrawal/bart-large-cnn-YT-transcript-sum
|
anuragrawal
| 2023-09-25T23:27:43Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bart",
"text2text-generation",
"generated_from_trainer",
"base_model:facebook/bart-large-cnn",
"base_model:finetune:facebook/bart-large-cnn",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-09-22T21:23:17Z |
---
license: mit
base_model: facebook/bart-large-cnn
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-large-cnn-YT-transcript-sum
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. -->
# bart-large-cnn-YT-transcript-sum
This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4849
- Rouge1: 48.0422
- Rouge2: 22.8938
- Rougel: 34.0775
- Rougelsum: 44.7056
- Gen Len: 108.8009
## 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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:--------:|
| No log | 1.0 | 432 | 1.5362 | 49.0506 | 22.9422 | 35.5667 | 45.7219 | 88.0602 |
| 1.5312 | 2.0 | 864 | 1.4849 | 48.0422 | 22.8938 | 34.0775 | 44.7056 | 108.8009 |
| 0.9026 | 3.0 | 1296 | 1.5761 | 50.0558 | 23.9657 | 36.247 | 46.4508 | 96.0231 |
| 0.5642 | 4.0 | 1728 | 1.8304 | 50.6862 | 24.4638 | 36.3568 | 47.2607 | 93.1667 |
| 0.3629 | 5.0 | 2160 | 1.9355 | 51.2362 | 25.1077 | 37.772 | 47.4362 | 88.9583 |
| 0.2335 | 6.0 | 2592 | 2.1215 | 49.5831 | 23.4294 | 35.9861 | 45.9306 | 94.2917 |
| 0.1603 | 7.0 | 3024 | 2.2890 | 49.8716 | 23.4756 | 36.2617 | 46.2866 | 88.7639 |
| 0.1603 | 8.0 | 3456 | 2.3604 | 49.5627 | 23.6399 | 35.9596 | 45.7914 | 88.8333 |
| 0.1049 | 9.0 | 3888 | 2.5252 | 50.358 | 24.1986 | 36.5297 | 46.5519 | 90.5463 |
| 0.0744 | 10.0 | 4320 | 2.6694 | 50.46 | 24.1493 | 37.0205 | 46.8988 | 91.0139 |
| 0.049 | 11.0 | 4752 | 2.7840 | 50.8805 | 24.5482 | 36.5901 | 46.9176 | 90.8380 |
| 0.0312 | 12.0 | 5184 | 2.8330 | 50.4793 | 24.6444 | 37.2087 | 46.7151 | 86.9444 |
| 0.0156 | 13.0 | 5616 | 2.9540 | 50.3911 | 24.4843 | 36.8037 | 46.8691 | 94.9352 |
| 0.0083 | 14.0 | 6048 | 3.0214 | 51.0557 | 25.127 | 37.1368 | 47.3072 | 92.5787 |
| 0.0083 | 15.0 | 6480 | 3.0340 | 51.3998 | 25.5847 | 37.5635 | 47.7132 | 90.5602 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
thkkvui/xlm-roberta-base-finetuned-massive
|
thkkvui
| 2023-09-25T23:15:07Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"text-classification",
"generated_from_trainer",
"massive",
"bert",
"ja",
"dataset:AmazonScience/massive",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-21T05:09:54Z |
---
license: mit
language:
- ja
base_model: xlm-roberta-base
tags:
- generated_from_trainer
- massive
- bert
datasets:
- AmazonScience/massive
widget:
- text: 明日の予定を教えて
metrics:
- accuracy
- f1
model-index:
- name: xlm-roberta-base-finetuned-massive
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: massive
type: massive
config: ja-JP
split: validation
args: ja-JP
metrics:
- name: Accuracy
type: accuracy
value: 0.8327594687653713
- name: F1
type: f1
value: 0.8192120367052886
---
<!-- 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-massive
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the massive dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7539
- Accuracy: 0.8328
- F1: 0.8192
## Model description
More information needed
## Intended uses & limitations
```python
from transformers import pipeline
model_name = "thkkvui/xlm-roberta-base-finetuned-massive"
classifier = pipeline("text-classification", model=model_name)
text = ["今日の天気を教えて", "ニュースある？", "予定をチェックして", "ドル円は？"]
for t in text:
output = classifier(t)
print(output)
```
## 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
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 2.9836 | 0.69 | 500 | 1.6188 | 0.6257 | 0.5524 |
| 1.4569 | 1.39 | 1000 | 1.0347 | 0.7575 | 0.7251 |
| 1.0211 | 2.08 | 1500 | 0.8186 | 0.8205 | 0.8024 |
| 0.7799 | 2.78 | 2000 | 0.7539 | 0.8328 | 0.8192 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
|
Ibrahim-Alam/finetuning-roberta-base-on-Cornell_sentiment
|
Ibrahim-Alam
| 2023-09-25T23:14:36Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"roberta",
"text-classification",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-19T01:21:50Z |
---
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: finetuning-roberta-base-on-Cornell_sentiment
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-roberta-base-on-Cornell_sentiment
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:
- Loss: 0.3539
- Accuracy: 0.8744
- F1: 0.8708
## 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: 1
### Training results
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
grakshit/sentiment_imdb
|
grakshit
| 2023-09-25T23:05:23Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"text-classification",
"generated_from_trainer",
"dataset:imdb",
"base_model:FacebookAI/roberta-base",
"base_model:finetune:FacebookAI/roberta-base",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-25T22:23:34Z |
---
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
model-index:
- name: sentiment_imdb
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: imdb
type: imdb
config: plain_text
split: test
args: plain_text
metrics:
- name: Accuracy
type: accuracy
value: 0.95576
---
<!-- 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. -->
# sentiment_imdb
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the imdb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1831
- Accuracy: 0.9558
## 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: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.1838 | 1.0 | 1563 | 0.2139 | 0.9333 |
| 0.134 | 2.0 | 3126 | 0.1831 | 0.9558 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
VitaliiVrublevskyi/Llama-2-7b-hf-finetuned-mrpc
|
VitaliiVrublevskyi
| 2023-09-25T23:05:07Z | 0 | 0 | null |
[
"tensorboard",
"generated_from_trainer",
"dataset:glue",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:finetune:meta-llama/Llama-2-7b-hf",
"region:us"
] | null | 2023-09-17T14:51:55Z |
---
base_model: meta-llama/Llama-2-7b-hf
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: Llama-2-7b-hf-finetuned-mrpc
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. -->
# Llama-2-7b-hf-finetuned-mrpc
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 glue dataset.
It achieves the following results on the evaluation set:
- Accuracy: 0.7941
- F1: 0.8571
- Loss: 0.4479
## 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: 10
### Training results
| Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss |
|:-------------:|:-----:|:----:|:--------:|:------:|:---------------:|
| No log | 1.0 | 230 | 0.7206 | 0.8155 | 0.6045 |
| No log | 2.0 | 460 | 0.6912 | 0.8158 | 0.6488 |
| 0.6326 | 3.0 | 690 | 0.7279 | 0.8235 | 0.5236 |
| 0.6326 | 4.0 | 920 | 0.7255 | 0.8282 | 0.5273 |
| 0.5602 | 5.0 | 1150 | 0.7402 | 0.8044 | 0.5246 |
| 0.5602 | 6.0 | 1380 | 0.75 | 0.8311 | 0.4893 |
| 0.5139 | 7.0 | 1610 | 0.7623 | 0.8289 | 0.4884 |
| 0.5139 | 8.0 | 1840 | 0.7402 | 0.8307 | 0.4989 |
| 0.4754 | 9.0 | 2070 | 0.7745 | 0.8435 | 0.4732 |
| 0.4754 | 10.0 | 2300 | 0.7672 | 0.8403 | 0.4716 |
| 0.5407 | 11.0 | 2530 | 0.7598 | 0.8393 | 0.4823 |
| 0.5407 | 12.0 | 2760 | 0.7451 | 0.8333 | 0.4782 |
| 0.5407 | 13.0 | 2990 | 0.7451 | 0.8333 | 0.4713 |
| 0.4951 | 14.0 | 3220 | 0.7819 | 0.8489 | 0.4553 |
| 0.4951 | 15.0 | 3450 | 0.7745 | 0.8506 | 0.4591 |
| 0.4724 | 16.0 | 3680 | 0.7770 | 0.8423 | 0.4631 |
| 0.4724 | 17.0 | 3910 | 0.8015 | 0.8576 | 0.4581 |
| 0.4455 | 18.0 | 4140 | 0.7819 | 0.8468 | 0.4548 |
| 0.4455 | 19.0 | 4370 | 0.7819 | 0.8484 | 0.4511 |
| 0.4354 | 20.0 | 4600 | 0.7941 | 0.8571 | 0.4479 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
knarasi1/ppo-SnowballTarget
|
knarasi1
| 2023-09-25T23:04:38Z | 22 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] |
reinforcement-learning
| 2023-09-25T23:04:33Z |
---
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: knarasi1/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
almaghrabima/ner_column_TQ
|
almaghrabima
| 2023-09-25T23:02:15Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"deberta-v2",
"token-classification",
"generated_from_trainer",
"en",
"base_model:Gladiator/microsoft-deberta-v3-large_ner_conll2003",
"base_model:finetune:Gladiator/microsoft-deberta-v3-large_ner_conll2003",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-09-20T21:17:28Z |
---
license: mit
base_model: Gladiator/microsoft-deberta-v3-large_ner_conll2003
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: ner_column_TQ
results: []
language:
- en
widget:
- india 0S0308Z8 trudeau 3000 Ravensburger Hamnoy, Lofoten of gold bestseller 620463000001
- other china lc waikiki mağazacilik hi̇zmetleri̇ ti̇c aş 630140000000 hilti 6204699090_BD 55L Toaster Oven with Double Glass
- 611020000001 italy Apparel other games 9W1964Z8 debenhams guangzhou hec fashion leather co ltd
---
<!-- 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. -->
# ner_column_TQ
This model is a fine-tuned version of [Gladiator/microsoft-deberta-v3-large_ner_conll2003](https://huggingface.co/Gladiator/microsoft-deberta-v3-large_ner_conll2003) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1949
- Precision: 0.8546
- Recall: 0.8533
- F1: 0.8540
- Accuracy: 0.9154
## 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: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log | 1.0 | 702 | 0.2342 | 0.7774 | 0.7496 | 0.7632 | 0.8833 |
| 0.369 | 2.0 | 1404 | 0.1708 | 0.8050 | 0.8048 | 0.8049 | 0.9033 |
| 0.1681 | 3.0 | 2106 | 0.1646 | 0.8007 | 0.8078 | 0.8043 | 0.9054 |
| 0.1681 | 4.0 | 2808 | 0.1469 | 0.8250 | 0.8335 | 0.8292 | 0.9133 |
| 0.14 | 5.0 | 3510 | 0.1465 | 0.8235 | 0.8345 | 0.8290 | 0.9137 |
| 0.1279 | 6.0 | 4212 | 0.1517 | 0.8165 | 0.8323 | 0.8244 | 0.9127 |
| 0.1279 | 7.0 | 4914 | 0.1474 | 0.8224 | 0.8370 | 0.8297 | 0.9138 |
| 0.1212 | 8.0 | 5616 | 0.1500 | 0.8255 | 0.8409 | 0.8331 | 0.9141 |
| 0.1165 | 9.0 | 6318 | 0.1545 | 0.8297 | 0.8390 | 0.8343 | 0.9142 |
| 0.1138 | 10.0 | 7020 | 0.1590 | 0.8342 | 0.8467 | 0.8404 | 0.9150 |
| 0.1138 | 11.0 | 7722 | 0.1588 | 0.8383 | 0.8474 | 0.8428 | 0.9156 |
| 0.1099 | 12.0 | 8424 | 0.1547 | 0.8425 | 0.8446 | 0.8435 | 0.9156 |
| 0.1071 | 13.0 | 9126 | 0.1565 | 0.8475 | 0.8471 | 0.8473 | 0.9164 |
| 0.1071 | 14.0 | 9828 | 0.1625 | 0.8440 | 0.8489 | 0.8464 | 0.9156 |
| 0.1031 | 15.0 | 10530 | 0.1680 | 0.8486 | 0.8510 | 0.8498 | 0.9160 |
| 0.0992 | 16.0 | 11232 | 0.1722 | 0.8529 | 0.8505 | 0.8517 | 0.9156 |
| 0.0992 | 17.0 | 11934 | 0.1771 | 0.8527 | 0.8529 | 0.8528 | 0.9159 |
| 0.094 | 18.0 | 12636 | 0.1862 | 0.8555 | 0.8531 | 0.8543 | 0.9159 |
| 0.0892 | 19.0 | 13338 | 0.1884 | 0.8534 | 0.8534 | 0.8534 | 0.9156 |
| 0.086 | 20.0 | 14040 | 0.1949 | 0.8546 | 0.8533 | 0.8540 | 0.9154 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
jh1517/q-FrozenLake-v1-4x4-noSlippery
|
jh1517
| 2023-09-25T22:50:58Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-25T22:50:55Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="jh1517/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
silvacarl/distilbert-stock-tweet-sentiment-analysis
|
silvacarl
| 2023-09-25T22:50:15Z | 184 | 0 |
transformers
|
[
"transformers",
"pytorch",
"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
| 2023-09-25T22:48:12Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-stock-tweet-sentiment-analysis
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-stock-tweet-sentiment-analysis
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:
- Loss: 0.6236
- Accuracy: 0.7702
## 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6937 | 1.0 | 1000 | 0.5964 | 0.7512 |
| 0.4743 | 2.0 | 2000 | 0.5807 | 0.7675 |
| 0.3648 | 3.0 | 3000 | 0.6236 | 0.7702 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
milaidy/r4v3n
|
milaidy
| 2023-09-25T22:33:16Z | 3 | 1 |
diffusers
|
[
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-25T22:29:51Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### r4v3n Dreambooth model trained by milaidy with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
euclaise/falcon_1b_stage3_2
|
euclaise
| 2023-09-25T22:31:31Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"falcon",
"text-generation",
"generated_from_trainer",
"custom_code",
"base_model:euclaise/falcon_1b_stage2",
"base_model:finetune:euclaise/falcon_1b_stage2",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-23T01:28:52Z |
---
license: apache-2.0
base_model: euclaise/falcon_1b_stage2
tags:
- generated_from_trainer
model-index:
- name: falcon_1b_stage3_2
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. -->
# falcon_1b_stage3_2
This model is a fine-tuned version of [euclaise/falcon_1b_stage2](https://huggingface.co/euclaise/falcon_1b_stage2) 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: 6e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 128.0
- total_train_batch_size: 128.0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.15
- num_epochs: 5
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
YaTharThShaRma999/Lima_Lora
|
YaTharThShaRma999
| 2023-09-25T22:15:36Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-25T22:15:33Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0
|
CyberHarem/wien_margarete_lovelivesuperstar
|
CyberHarem
| 2023-09-25T22:10:58Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/wien_margarete_lovelivesuperstar",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-25T22:02:19Z |
---
license: mit
datasets:
- CyberHarem/wien_margarete_lovelivesuperstar
pipeline_tag: text-to-image
tags:
- art
---
# Lora of wien_margarete_lovelivesuperstar
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 4080, you need to download `4080/wien_margarete_lovelivesuperstar.pt` as the embedding and `4080/wien_margarete_lovelivesuperstar.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 4080**, with the score of 0.971. The trigger words are:
1. `wien_margarete_lovelivesuperstar`
2. `long_hair, bangs, green_eyes, braid, purple_hair, blunt_bangs, blush, smile, breasts, pink_hair`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:----------------------------------------------------------|:----------------------------------------------------|:----------------------------------------------------|:----------------------------------------------------|:-------------------------------------------------|:--------------------------------------------------|:-----------------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.912 | [Download](5100/wien_margarete_lovelivesuperstar.zip) | [<NSFW, click to see>](5100/previews/pattern_1.png) | [<NSFW, click to see>](5100/previews/pattern_2.png) | [<NSFW, click to see>](5100/previews/pattern_3.png) | [<NSFW, click to see>](5100/previews/bikini.png) | [<NSFW, click to see>](5100/previews/bondage.png) | [<NSFW, click to see>](5100/previews/free.png) |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| 4760 | 0.956 | [Download](4760/wien_margarete_lovelivesuperstar.zip) | [<NSFW, click to see>](4760/previews/pattern_1.png) | [<NSFW, click to see>](4760/previews/pattern_2.png) | [<NSFW, click to see>](4760/previews/pattern_3.png) | [<NSFW, click to see>](4760/previews/bikini.png) | [<NSFW, click to see>](4760/previews/bondage.png) | [<NSFW, click to see>](4760/previews/free.png) |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.941 | [Download](4420/wien_margarete_lovelivesuperstar.zip) | [<NSFW, click to see>](4420/previews/pattern_1.png) | [<NSFW, click to see>](4420/previews/pattern_2.png) | [<NSFW, click to see>](4420/previews/pattern_3.png) | [<NSFW, click to see>](4420/previews/bikini.png) | [<NSFW, click to see>](4420/previews/bondage.png) | [<NSFW, click to see>](4420/previews/free.png) |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| **4080** | **0.971** | [**Download**](4080/wien_margarete_lovelivesuperstar.zip) | [<NSFW, click to see>](4080/previews/pattern_1.png) | [<NSFW, click to see>](4080/previews/pattern_2.png) | [<NSFW, click to see>](4080/previews/pattern_3.png) | [<NSFW, click to see>](4080/previews/bikini.png) | [<NSFW, click to see>](4080/previews/bondage.png) | [<NSFW, click to see>](4080/previews/free.png) |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.845 | [Download](3740/wien_margarete_lovelivesuperstar.zip) | [<NSFW, click to see>](3740/previews/pattern_1.png) | [<NSFW, click to see>](3740/previews/pattern_2.png) | [<NSFW, click to see>](3740/previews/pattern_3.png) | [<NSFW, click to see>](3740/previews/bikini.png) | [<NSFW, click to see>](3740/previews/bondage.png) | [<NSFW, click to see>](3740/previews/free.png) |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.881 | [Download](3400/wien_margarete_lovelivesuperstar.zip) | [<NSFW, click to see>](3400/previews/pattern_1.png) | [<NSFW, click to see>](3400/previews/pattern_2.png) | [<NSFW, click to see>](3400/previews/pattern_3.png) | [<NSFW, click to see>](3400/previews/bikini.png) | [<NSFW, click to see>](3400/previews/bondage.png) | [<NSFW, click to see>](3400/previews/free.png) |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.968 | [Download](3060/wien_margarete_lovelivesuperstar.zip) | [<NSFW, click to see>](3060/previews/pattern_1.png) | [<NSFW, click to see>](3060/previews/pattern_2.png) | [<NSFW, click to see>](3060/previews/pattern_3.png) | [<NSFW, click to see>](3060/previews/bikini.png) | [<NSFW, click to see>](3060/previews/bondage.png) | [<NSFW, click to see>](3060/previews/free.png) |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.939 | [Download](2720/wien_margarete_lovelivesuperstar.zip) | [<NSFW, click to see>](2720/previews/pattern_1.png) | [<NSFW, click to see>](2720/previews/pattern_2.png) | [<NSFW, click to see>](2720/previews/pattern_3.png) | [<NSFW, click to see>](2720/previews/bikini.png) | [<NSFW, click to see>](2720/previews/bondage.png) | [<NSFW, click to see>](2720/previews/free.png) |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.916 | [Download](2380/wien_margarete_lovelivesuperstar.zip) | [<NSFW, click to see>](2380/previews/pattern_1.png) | [<NSFW, click to see>](2380/previews/pattern_2.png) | [<NSFW, click to see>](2380/previews/pattern_3.png) | [<NSFW, click to see>](2380/previews/bikini.png) | [<NSFW, click to see>](2380/previews/bondage.png) | [<NSFW, click to see>](2380/previews/free.png) |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.919 | [Download](2040/wien_margarete_lovelivesuperstar.zip) | [<NSFW, click to see>](2040/previews/pattern_1.png) | [<NSFW, click to see>](2040/previews/pattern_2.png) | [<NSFW, click to see>](2040/previews/pattern_3.png) | [<NSFW, click to see>](2040/previews/bikini.png) | [<NSFW, click to see>](2040/previews/bondage.png) | [<NSFW, click to see>](2040/previews/free.png) |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.963 | [Download](1700/wien_margarete_lovelivesuperstar.zip) | [<NSFW, click to see>](1700/previews/pattern_1.png) | [<NSFW, click to see>](1700/previews/pattern_2.png) | [<NSFW, click to see>](1700/previews/pattern_3.png) | [<NSFW, click to see>](1700/previews/bikini.png) | [<NSFW, click to see>](1700/previews/bondage.png) | [<NSFW, click to see>](1700/previews/free.png) |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.947 | [Download](1360/wien_margarete_lovelivesuperstar.zip) | [<NSFW, click to see>](1360/previews/pattern_1.png) | [<NSFW, click to see>](1360/previews/pattern_2.png) | [<NSFW, click to see>](1360/previews/pattern_3.png) | [<NSFW, click to see>](1360/previews/bikini.png) | [<NSFW, click to see>](1360/previews/bondage.png) | [<NSFW, click to see>](1360/previews/free.png) |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.901 | [Download](1020/wien_margarete_lovelivesuperstar.zip) | [<NSFW, click to see>](1020/previews/pattern_1.png) | [<NSFW, click to see>](1020/previews/pattern_2.png) | [<NSFW, click to see>](1020/previews/pattern_3.png) | [<NSFW, click to see>](1020/previews/bikini.png) | [<NSFW, click to see>](1020/previews/bondage.png) | [<NSFW, click to see>](1020/previews/free.png) |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.926 | [Download](680/wien_margarete_lovelivesuperstar.zip) | [<NSFW, click to see>](680/previews/pattern_1.png) | [<NSFW, click to see>](680/previews/pattern_2.png) | [<NSFW, click to see>](680/previews/pattern_3.png) | [<NSFW, click to see>](680/previews/bikini.png) | [<NSFW, click to see>](680/previews/bondage.png) | [<NSFW, click to see>](680/previews/free.png) |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.745 | [Download](340/wien_margarete_lovelivesuperstar.zip) | [<NSFW, click to see>](340/previews/pattern_1.png) | [<NSFW, click to see>](340/previews/pattern_2.png) | [<NSFW, click to see>](340/previews/pattern_3.png) | [<NSFW, click to see>](340/previews/bikini.png) | [<NSFW, click to see>](340/previews/bondage.png) | [<NSFW, click to see>](340/previews/free.png) |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
CreativeLang/metaphor_detection_roberta_seq
|
CreativeLang
| 2023-09-25T22:08:17Z | 5,080 | 4 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"token-classification",
"en",
"dataset:CreativeLang/vua20_metaphor",
"license:cc-by-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-07-08T16:37:53Z |
---
license: cc-by-2.0
datasets:
- CreativeLang/vua20_metaphor
language:
- en
---
# Metaphor_Detection_Roberta_Seq
## Description
- **Paper:** [FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning](https://aclanthology.org/2023.eacl-main.114.pdf)
## Model Summary
Creative Language Toolkit (CLTK) Metadata
- CL Type: Metaphor
- Task Type: detection
- Size: roberta-base (500MB)
- Created time: 2022
This model is a easy to use metaphor detection baseline realised with `roberta-base` fine-tuned on [CreativeLang/vua20_metaphor](https://huggingface.co/datasets/CreativeLang/vua20_metaphor) dataset.
To use this model, please use the `inference.py` in the [FrameBERT repo](https://github.com/liyucheng09/MetaphorFrame).
Just run:
```
python inference.py CreativeLang/metaphor_detection_roberta_seq
```
Check out `inference.py` to learn how to apply the model on your own data.
For the details of this model and the dataset used, we refer you to the release [paper](https://aclanthology.org/2023.eacl-main.114.pdf).
## Metrics
| Metric | Value |
|----------------------------------|--------------------------|
| eval_loss | 0.2656 |
| eval_accuracy_score | 0.9142 |
| eval_precision | 0.9142 |
| eval_recall | 0.9142 |
| eval_f1 | 0.9142 |
| eval_f1_macro | 0.7315 |
| eval_runtime | 8.9802 |
| eval_samples_per_second | 411.7960 |
| eval_steps_per_second | 51.5580 |
| epoch | 3.0000 |
### Citation Information
If you find this dataset helpful, please cite:
```
@article{Li2023FrameBERTCM,
title={FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning},
author={Yucheng Li and Shunyu Wang and Chenghua Lin and Frank Guerin and Lo{\"i}c Barrault},
journal={ArXiv},
year={2023},
volume={abs/2302.04834}
}
```
### Contributions
If you have any queries, please open an issue or direct your queries to [mail](mailto:yucheng.li@surrey.ac.uk).
|
CyberHarem/mitake_ran_bangdream
|
CyberHarem
| 2023-09-25T22:07:38Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/mitake_ran_bangdream",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-25T21:50:24Z |
---
license: mit
datasets:
- CyberHarem/mitake_ran_bangdream
pipeline_tag: text-to-image
tags:
- art
---
# Lora of mitake_ran_bangdream
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 7800, you need to download `7800/mitake_ran_bangdream.pt` as the embedding and `7800/mitake_ran_bangdream.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 7800**, with the score of 0.993. The trigger words are:
1. `mitake_ran_bangdream`
2. `black_hair, red_hair, multicolored_hair, streaked_hair, short_hair, bangs, blush, bob_cut, purple_eyes, breasts, collarbone, red_eyes`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | pattern_13 | pattern_14 | pattern_15 | pattern_16 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:----------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------|:-----------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| **7800** | **0.993** | [**Download**](7800/mitake_ran_bangdream.zip) |  |  |  |  | [<NSFW, click to see>](7800/previews/pattern_5.png) |  |  |  |  |  |  | [<NSFW, click to see>](7800/previews/pattern_12.png) |  |  | [<NSFW, click to see>](7800/previews/pattern_15.png) | [<NSFW, click to see>](7800/previews/pattern_16.png) |  | [<NSFW, click to see>](7800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7800/previews/nude.png) | [<NSFW, click to see>](7800/previews/nude2.png) |  |  |
| 7280 | 0.993 | [Download](7280/mitake_ran_bangdream.zip) |  |  |  |  | [<NSFW, click to see>](7280/previews/pattern_5.png) |  |  |  |  |  |  | [<NSFW, click to see>](7280/previews/pattern_12.png) |  |  | [<NSFW, click to see>](7280/previews/pattern_15.png) | [<NSFW, click to see>](7280/previews/pattern_16.png) |  | [<NSFW, click to see>](7280/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7280/previews/nude.png) | [<NSFW, click to see>](7280/previews/nude2.png) |  |  |
| 6760 | 0.952 | [Download](6760/mitake_ran_bangdream.zip) |  |  |  |  | [<NSFW, click to see>](6760/previews/pattern_5.png) |  |  |  |  |  |  | [<NSFW, click to see>](6760/previews/pattern_12.png) |  |  | [<NSFW, click to see>](6760/previews/pattern_15.png) | [<NSFW, click to see>](6760/previews/pattern_16.png) |  | [<NSFW, click to see>](6760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6760/previews/nude.png) | [<NSFW, click to see>](6760/previews/nude2.png) |  |  |
| 6240 | 0.993 | [Download](6240/mitake_ran_bangdream.zip) |  |  |  |  | [<NSFW, click to see>](6240/previews/pattern_5.png) |  |  |  |  |  |  | [<NSFW, click to see>](6240/previews/pattern_12.png) |  |  | [<NSFW, click to see>](6240/previews/pattern_15.png) | [<NSFW, click to see>](6240/previews/pattern_16.png) |  | [<NSFW, click to see>](6240/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6240/previews/nude.png) | [<NSFW, click to see>](6240/previews/nude2.png) |  |  |
| 5720 | 0.991 | [Download](5720/mitake_ran_bangdream.zip) |  |  |  |  | [<NSFW, click to see>](5720/previews/pattern_5.png) |  |  |  |  |  |  | [<NSFW, click to see>](5720/previews/pattern_12.png) |  |  | [<NSFW, click to see>](5720/previews/pattern_15.png) | [<NSFW, click to see>](5720/previews/pattern_16.png) |  | [<NSFW, click to see>](5720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5720/previews/nude.png) | [<NSFW, click to see>](5720/previews/nude2.png) |  |  |
| 5200 | 0.950 | [Download](5200/mitake_ran_bangdream.zip) |  |  |  |  | [<NSFW, click to see>](5200/previews/pattern_5.png) |  |  |  |  |  |  | [<NSFW, click to see>](5200/previews/pattern_12.png) |  |  | [<NSFW, click to see>](5200/previews/pattern_15.png) | [<NSFW, click to see>](5200/previews/pattern_16.png) |  | [<NSFW, click to see>](5200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5200/previews/nude.png) | [<NSFW, click to see>](5200/previews/nude2.png) |  |  |
| 4680 | 0.993 | [Download](4680/mitake_ran_bangdream.zip) |  |  |  |  | [<NSFW, click to see>](4680/previews/pattern_5.png) |  |  |  |  |  |  | [<NSFW, click to see>](4680/previews/pattern_12.png) |  |  | [<NSFW, click to see>](4680/previews/pattern_15.png) | [<NSFW, click to see>](4680/previews/pattern_16.png) |  | [<NSFW, click to see>](4680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4680/previews/nude.png) | [<NSFW, click to see>](4680/previews/nude2.png) |  |  |
| 4160 | 0.950 | [Download](4160/mitake_ran_bangdream.zip) |  |  |  |  | [<NSFW, click to see>](4160/previews/pattern_5.png) |  |  |  |  |  |  | [<NSFW, click to see>](4160/previews/pattern_12.png) |  |  | [<NSFW, click to see>](4160/previews/pattern_15.png) | [<NSFW, click to see>](4160/previews/pattern_16.png) |  | [<NSFW, click to see>](4160/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4160/previews/nude.png) | [<NSFW, click to see>](4160/previews/nude2.png) |  |  |
| 3640 | 0.991 | [Download](3640/mitake_ran_bangdream.zip) |  |  |  |  | [<NSFW, click to see>](3640/previews/pattern_5.png) |  |  |  |  |  |  | [<NSFW, click to see>](3640/previews/pattern_12.png) |  |  | [<NSFW, click to see>](3640/previews/pattern_15.png) | [<NSFW, click to see>](3640/previews/pattern_16.png) |  | [<NSFW, click to see>](3640/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3640/previews/nude.png) | [<NSFW, click to see>](3640/previews/nude2.png) |  |  |
| 3120 | 0.991 | [Download](3120/mitake_ran_bangdream.zip) |  |  |  |  | [<NSFW, click to see>](3120/previews/pattern_5.png) |  |  |  |  |  |  | [<NSFW, click to see>](3120/previews/pattern_12.png) |  |  | [<NSFW, click to see>](3120/previews/pattern_15.png) | [<NSFW, click to see>](3120/previews/pattern_16.png) |  | [<NSFW, click to see>](3120/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3120/previews/nude.png) | [<NSFW, click to see>](3120/previews/nude2.png) |  |  |
| 2600 | 0.989 | [Download](2600/mitake_ran_bangdream.zip) |  |  |  |  | [<NSFW, click to see>](2600/previews/pattern_5.png) |  |  |  |  |  |  | [<NSFW, click to see>](2600/previews/pattern_12.png) |  |  | [<NSFW, click to see>](2600/previews/pattern_15.png) | [<NSFW, click to see>](2600/previews/pattern_16.png) |  | [<NSFW, click to see>](2600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2600/previews/nude.png) | [<NSFW, click to see>](2600/previews/nude2.png) |  |  |
| 2080 | 0.989 | [Download](2080/mitake_ran_bangdream.zip) |  |  |  |  | [<NSFW, click to see>](2080/previews/pattern_5.png) |  |  |  |  |  |  | [<NSFW, click to see>](2080/previews/pattern_12.png) |  |  | [<NSFW, click to see>](2080/previews/pattern_15.png) | [<NSFW, click to see>](2080/previews/pattern_16.png) |  | [<NSFW, click to see>](2080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2080/previews/nude.png) | [<NSFW, click to see>](2080/previews/nude2.png) |  |  |
| 1560 | 0.992 | [Download](1560/mitake_ran_bangdream.zip) |  |  |  |  | [<NSFW, click to see>](1560/previews/pattern_5.png) |  |  |  |  |  |  | [<NSFW, click to see>](1560/previews/pattern_12.png) |  |  | [<NSFW, click to see>](1560/previews/pattern_15.png) | [<NSFW, click to see>](1560/previews/pattern_16.png) |  | [<NSFW, click to see>](1560/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1560/previews/nude.png) | [<NSFW, click to see>](1560/previews/nude2.png) |  |  |
| 1040 | 0.991 | [Download](1040/mitake_ran_bangdream.zip) |  |  |  |  | [<NSFW, click to see>](1040/previews/pattern_5.png) |  |  |  |  |  |  | [<NSFW, click to see>](1040/previews/pattern_12.png) |  |  | [<NSFW, click to see>](1040/previews/pattern_15.png) | [<NSFW, click to see>](1040/previews/pattern_16.png) |  | [<NSFW, click to see>](1040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1040/previews/nude.png) | [<NSFW, click to see>](1040/previews/nude2.png) |  |  |
| 520 | 0.990 | [Download](520/mitake_ran_bangdream.zip) |  |  |  |  | [<NSFW, click to see>](520/previews/pattern_5.png) |  |  |  |  |  |  | [<NSFW, click to see>](520/previews/pattern_12.png) |  |  | [<NSFW, click to see>](520/previews/pattern_15.png) | [<NSFW, click to see>](520/previews/pattern_16.png) |  | [<NSFW, click to see>](520/previews/bondage.png) |  |  |  | [<NSFW, click to see>](520/previews/nude.png) | [<NSFW, click to see>](520/previews/nude2.png) |  |  |
|
abeiler/NumRep
|
abeiler
| 2023-09-25T21:57:21Z | 2 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"generated_from_trainer",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:finetune:meta-llama/Llama-2-7b-hf",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-25T17:59:43Z |
---
base_model: meta-llama/Llama-2-7b-hf
tags:
- generated_from_trainer
model-index:
- name: goatOrig-QLORA
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. -->
# goatOrig-QLORA
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) 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: 0.0001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
am-infoweb/QA_SYNTH_25_SEPT_WITH_FINETUNE_1.1_on19sept
|
am-infoweb
| 2023-09-25T21:50:02Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"question-answering",
"generated_from_trainer",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-09-25T19:14:02Z |
---
tags:
- generated_from_trainer
model-index:
- name: QA_SYNTH_25_SEPT_WITH_FINETUNE_1.1_on19sept
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. -->
# QA_SYNTH_25_SEPT_WITH_FINETUNE_1.1_on19sept
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0000
## 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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:------:|:---------------:|
| 0.0731 | 1.0 | 14513 | 0.0063 |
| 0.0 | 2.0 | 29026 | 0.0048 |
| 0.0484 | 3.0 | 43539 | 0.0034 |
| 0.0 | 4.0 | 58052 | 0.0030 |
| 0.0006 | 5.0 | 72565 | 0.0073 |
| 0.0002 | 6.0 | 87078 | 0.0019 |
| 0.0001 | 7.0 | 101591 | 0.0000 |
| 0.0 | 8.0 | 116104 | 0.0000 |
| 0.0 | 9.0 | 130617 | 0.0000 |
| 0.0 | 10.0 | 145130 | 0.0000 |
### Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3
|
halo-69/Bloom_3b_squad
|
halo-69
| 2023-09-25T21:44:32Z | 9 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bloom",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"base_model:bigscience/bloom-3b",
"base_model:finetune:bigscience/bloom-3b",
"license:bigscience-bloom-rail-1.0",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-09-14T04:13:28Z |
---
license: bigscience-bloom-rail-1.0
base_model: bigscience/bloom-3b
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: Bloom_3b_squad
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. -->
# Bloom_3b_squad
This model is a fine-tuned version of [bigscience/bloom-3b](https://huggingface.co/bigscience/bloom-3b) on the squad dataset.
It achieves the following results on the evaluation set:
- Loss: 2.7859
## 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: 48
- 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: 50
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 3.0058 | 1.0 | 1643 | 2.7510 |
| 2.7801 | 2.0 | 3286 | 2.7497 |
| 2.7284 | 3.0 | 4929 | 2.7536 |
| 2.7001 | 4.0 | 6572 | 2.7601 |
| 2.6811 | 5.0 | 8215 | 2.7669 |
| 2.6811 | 6.0 | 9858 | 2.7722 |
| 2.6639 | 7.0 | 11501 | 2.7780 |
| 2.6492 | 8.0 | 13144 | 2.7817 |
| 2.6414 | 9.0 | 14787 | 2.7841 |
| 2.6354 | 10.0 | 16430 | 2.7859 |
### Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0
|
Brecon/master_bert_seq_training_model
|
Brecon
| 2023-09-25T21:36:25Z | 106 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-25T20:47:57Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: master_bert_seq_training_model
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. -->
# master_bert_seq_training_model
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0308
- Accuracy: 0.4725
## 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: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 23 | 1.0633 | 0.4725 |
| No log | 2.0 | 46 | 1.0308 | 0.4725 |
### Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cpu
- Datasets 2.14.5
- Tokenizers 0.11.0
|
fmagot01/distil-wav2vec2-finetuned-giga-speech
|
fmagot01
| 2023-09-25T21:32:04Z | 169 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"audio-classification",
"generated_from_trainer",
"dataset:OthmaneJ/distil-wav2vec2",
"base_model:OthmaneJ/distil-wav2vec2",
"base_model:finetune:OthmaneJ/distil-wav2vec2",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
audio-classification
| 2023-09-25T20:05:03Z |
---
license: apache-2.0
base_model: OthmaneJ/distil-wav2vec2
tags:
- generated_from_trainer
datasets:
- OthmaneJ/distil-wav2vec2
metrics:
- accuracy
model-index:
- name: distil-wav2vec2-finetuned-giga-speech
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: Giga Speech
type: OthmaneJ/distil-wav2vec2
config: xs
split: train
args: xs
metrics:
- name: Accuracy
type: accuracy
value: 0.8881789137380192
---
<!-- 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. -->
# distil-wav2vec2-finetuned-giga-speech
This model is a fine-tuned version of [OthmaneJ/distil-wav2vec2](https://huggingface.co/OthmaneJ/distil-wav2vec2) on the Giga Speech dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4271
- Accuracy: 0.8882
## 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.4425 | 1.0 | 1057 | 1.3045 | 0.5399 |
| 0.796 | 2.0 | 2114 | 0.8516 | 0.7284 |
| 0.9685 | 3.0 | 3171 | 0.5054 | 0.8626 |
| 0.5623 | 4.0 | 4228 | 0.4271 | 0.8882 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
anuragrawal/flan-t5-base-YT-transcript-sum
|
anuragrawal
| 2023-09-25T21:22:30Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:google/flan-t5-base",
"base_model:finetune:google/flan-t5-base",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-09-25T19:44:22Z |
---
license: apache-2.0
base_model: google/flan-t5-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: flan-t5-base-YT-transcript-sum
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. -->
# flan-t5-base-YT-transcript-sum
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4111
- Rouge1: 25.4013
- Rouge2: 12.4728
- Rougel: 21.5206
- Rougelsum: 23.6322
- Gen Len: 19.0
## 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: 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: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| No log | 1.0 | 216 | 1.5817 | 23.8566 | 11.0314 | 20.1664 | 22.2953 | 18.9954 |
| No log | 2.0 | 432 | 1.4907 | 24.2446 | 11.6603 | 20.6712 | 22.4196 | 18.9861 |
| 1.7643 | 3.0 | 648 | 1.4510 | 25.4355 | 12.9236 | 21.584 | 23.7272 | 19.0 |
| 1.7643 | 4.0 | 864 | 1.4312 | 24.8929 | 12.5927 | 21.3295 | 23.3504 | 19.0 |
| 1.4359 | 5.0 | 1080 | 1.4145 | 25.242 | 12.9269 | 21.6351 | 23.6509 | 19.0 |
| 1.4359 | 6.0 | 1296 | 1.4111 | 25.4013 | 12.4728 | 21.5206 | 23.6322 | 19.0 |
| 1.2819 | 7.0 | 1512 | 1.4135 | 25.6542 | 13.103 | 22.2059 | 23.9474 | 19.0 |
| 1.2819 | 8.0 | 1728 | 1.4145 | 26.0783 | 13.7584 | 22.343 | 24.3255 | 19.0 |
| 1.2819 | 9.0 | 1944 | 1.4163 | 25.4385 | 13.1278 | 21.7173 | 23.8295 | 18.9861 |
| 1.1688 | 10.0 | 2160 | 1.4208 | 25.7625 | 13.5586 | 22.2246 | 24.2042 | 19.0 |
| 1.1688 | 11.0 | 2376 | 1.4165 | 25.5482 | 13.1163 | 21.9475 | 23.8181 | 18.9907 |
| 1.0951 | 12.0 | 2592 | 1.4215 | 25.7614 | 13.5565 | 22.1965 | 24.0657 | 19.0 |
| 1.0951 | 13.0 | 2808 | 1.4285 | 26.3345 | 14.2027 | 22.7422 | 24.6261 | 18.9907 |
| 1.0549 | 14.0 | 3024 | 1.4277 | 25.8835 | 13.8044 | 22.3845 | 24.269 | 19.0 |
| 1.0549 | 15.0 | 3240 | 1.4321 | 25.8292 | 13.7231 | 22.3506 | 24.3188 | 19.0 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
goodatinvesting/ppo-Huggy
|
goodatinvesting
| 2023-09-25T21:11:45Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-09-25T21:11:40Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
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: goodatinvesting/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
JEdappully/ppo-Huggy
|
JEdappully
| 2023-09-25T21:07:41Z | 5 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-09-25T21:07:33Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
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: JEdappully/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
LarryAIDraw/Amagiri_Haruna-10
|
LarryAIDraw
| 2023-09-25T20:42:16Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-25T20:38:51Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/151541/haruna-amagiri-wana-hakudaku-mamire-no-houkago
|
LarryAIDraw/eleonora_viltaria_v1
|
LarryAIDraw
| 2023-09-25T20:41:53Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-25T20:38:30Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/151307/eleonora-viltaria-lord-marksman-and-vanadis
|
LarryAIDraw/perrin-10
|
LarryAIDraw
| 2023-09-25T20:41:32Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-25T20:37:53Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/151651/perrin-pokemon-lora
|
CyberHarem/arashi_chisato_lovelivesuperstar
|
CyberHarem
| 2023-09-25T20:40:38Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/arashi_chisato_lovelivesuperstar",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-25T20:26:06Z |
---
license: mit
datasets:
- CyberHarem/arashi_chisato_lovelivesuperstar
pipeline_tag: text-to-image
tags:
- art
---
# Lora of arashi_chisato_lovelivesuperstar
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 7280, you need to download `7280/arashi_chisato_lovelivesuperstar.pt` as the embedding and `7280/arashi_chisato_lovelivesuperstar.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 7280**, with the score of 0.994. The trigger words are:
1. `arashi_chisato_lovelivesuperstar`
2. `bangs, white_hair, hair_bun, double_bun, red_eyes, smile, blush, twintails, long_hair, blunt_bangs, open_mouth`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:----------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 7800 | 0.993 | [Download](7800/arashi_chisato_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7800/previews/nude.png) | [<NSFW, click to see>](7800/previews/nude2.png) |  |  |
| **7280** | **0.994** | [**Download**](7280/arashi_chisato_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7280/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7280/previews/nude.png) | [<NSFW, click to see>](7280/previews/nude2.png) |  |  |
| 6760 | 0.991 | [Download](6760/arashi_chisato_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6760/previews/nude.png) | [<NSFW, click to see>](6760/previews/nude2.png) |  |  |
| 6240 | 0.993 | [Download](6240/arashi_chisato_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6240/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6240/previews/nude.png) | [<NSFW, click to see>](6240/previews/nude2.png) |  |  |
| 5720 | 0.991 | [Download](5720/arashi_chisato_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5720/previews/nude.png) | [<NSFW, click to see>](5720/previews/nude2.png) |  |  |
| 5200 | 0.990 | [Download](5200/arashi_chisato_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5200/previews/nude.png) | [<NSFW, click to see>](5200/previews/nude2.png) |  |  |
| 4680 | 0.986 | [Download](4680/arashi_chisato_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4680/previews/nude.png) | [<NSFW, click to see>](4680/previews/nude2.png) |  |  |
| 4160 | 0.991 | [Download](4160/arashi_chisato_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4160/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4160/previews/nude.png) | [<NSFW, click to see>](4160/previews/nude2.png) |  |  |
| 3640 | 0.990 | [Download](3640/arashi_chisato_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3640/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3640/previews/nude.png) | [<NSFW, click to see>](3640/previews/nude2.png) |  |  |
| 3120 | 0.985 | [Download](3120/arashi_chisato_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3120/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3120/previews/nude.png) | [<NSFW, click to see>](3120/previews/nude2.png) |  |  |
| 2600 | 0.983 | [Download](2600/arashi_chisato_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2600/previews/nude.png) | [<NSFW, click to see>](2600/previews/nude2.png) |  |  |
| 2080 | 0.975 | [Download](2080/arashi_chisato_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2080/previews/nude.png) | [<NSFW, click to see>](2080/previews/nude2.png) |  |  |
| 1560 | 0.973 | [Download](1560/arashi_chisato_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1560/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1560/previews/nude.png) | [<NSFW, click to see>](1560/previews/nude2.png) |  |  |
| 1040 | 0.942 | [Download](1040/arashi_chisato_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1040/previews/nude.png) | [<NSFW, click to see>](1040/previews/nude2.png) |  |  |
| 520 | 0.972 | [Download](520/arashi_chisato_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](520/previews/bondage.png) |  |  |  | [<NSFW, click to see>](520/previews/nude.png) | [<NSFW, click to see>](520/previews/nude2.png) |  |  |
|
hcho22/falcon-7b-finetuned-uae
|
hcho22
| 2023-09-25T20:39:51Z | 0 | 0 | null |
[
"tensorboard",
"generated_from_trainer",
"base_model:tiiuae/falcon-7b-instruct",
"base_model:finetune:tiiuae/falcon-7b-instruct",
"license:apache-2.0",
"region:us"
] | null | 2023-09-21T23:08:35Z |
---
license: apache-2.0
base_model: tiiuae/falcon-7b-instruct
tags:
- generated_from_trainer
model-index:
- name: falcon-7b-finetuned-uae
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. -->
# falcon-7b-finetuned-uae
This model is a fine-tuned version of [tiiuae/falcon-7b-instruct](https://huggingface.co/tiiuae/falcon-7b-instruct) 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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 320
### Training results
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3
|
LarryAIDraw/haruno_yukinoshita_v2
|
LarryAIDraw
| 2023-09-25T20:37:28Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-25T20:35:22Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/128151/haruno-yukinoshita-or-my-teen-romantic-comedy-is-wrong-as-i-expected-oregairu
|
LarryAIDraw/pavonis-ag-richy-v1
|
LarryAIDraw
| 2023-09-25T20:36:31Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-25T20:33:22Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/151215/pavonis-artery-gear-fusion-lora
|
LarryAIDraw/Sarah_Gold_Isekai_Shokudou_-_irzie
|
LarryAIDraw
| 2023-09-25T20:36:20Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-25T20:32:59Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/151360/sarah-gold-isekai-shokudou
|
mrm8488/m-e5-large_bs64_10_all_languages
|
mrm8488
| 2023-09-25T20:29:11Z | 4 | 1 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"xlm-roberta",
"feature-extraction",
"sentence-similarity",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2023-09-25T18:38:21Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
---
# {MODEL_NAME}
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 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:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 899 with parameters:
```
{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss`
Parameters of the fit()-Method:
```
{
"epochs": 10,
"evaluation_steps": 500,
"evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 899,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
(2): Normalize()
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
DrSylvainPronovost/q-FrozenLake-v1-4x4-noSlippery
|
DrSylvainPronovost
| 2023-09-25T19:56:05Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-25T19:56:04Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="DrSylvainPronovost/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
Atheer174/Products_NER8
|
Atheer174
| 2023-09-25T19:54:46Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"token-classification",
"generated_from_trainer",
"base_model:dslim/bert-base-NER",
"base_model:finetune:dslim/bert-base-NER",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-09-25T16:42:52Z |
---
license: mit
base_model: dslim/bert-base-NER
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: Products_NER8
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. -->
# Products_NER8
This model is a fine-tuned version of [dslim/bert-base-NER](https://huggingface.co/dslim/bert-base-NER) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2028
- Precision: 0.9227
- Recall: 0.9267
- F1: 0.9247
- Accuracy: 0.9446
## 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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.1326 | 1.0 | 1235 | 0.1052 | 0.8887 | 0.9121 | 0.9003 | 0.9386 |
| 0.0959 | 2.0 | 2470 | 0.0927 | 0.8742 | 0.9085 | 0.8910 | 0.9417 |
| 0.0824 | 3.0 | 3705 | 0.0931 | 0.8970 | 0.9174 | 0.9070 | 0.9433 |
| 0.079 | 4.0 | 4940 | 0.0948 | 0.9067 | 0.9209 | 0.9137 | 0.9432 |
| 0.0762 | 5.0 | 6175 | 0.0962 | 0.8963 | 0.9179 | 0.9070 | 0.9437 |
| 0.0721 | 6.0 | 7410 | 0.1030 | 0.9095 | 0.9223 | 0.9159 | 0.9443 |
| 0.0683 | 7.0 | 8645 | 0.1070 | 0.9128 | 0.9233 | 0.9181 | 0.9439 |
| 0.0637 | 8.0 | 9880 | 0.1178 | 0.9157 | 0.9240 | 0.9199 | 0.9439 |
| 0.059 | 9.0 | 11115 | 0.1215 | 0.9176 | 0.9248 | 0.9212 | 0.9443 |
| 0.0527 | 10.0 | 12350 | 0.1367 | 0.9189 | 0.9247 | 0.9218 | 0.9438 |
| 0.0475 | 11.0 | 13585 | 0.1504 | 0.9199 | 0.9250 | 0.9224 | 0.9441 |
| 0.0431 | 12.0 | 14820 | 0.1484 | 0.9207 | 0.9259 | 0.9233 | 0.9446 |
| 0.0389 | 13.0 | 16055 | 0.1706 | 0.9224 | 0.9267 | 0.9246 | 0.9446 |
| 0.0368 | 14.0 | 17290 | 0.1847 | 0.9223 | 0.9265 | 0.9244 | 0.9445 |
| 0.0351 | 15.0 | 18525 | 0.2028 | 0.9227 | 0.9267 | 0.9247 | 0.9446 |
### Framework versions
- Transformers 4.33.0
- Pytorch 1.13.1+cu117
- Datasets 2.1.0
- Tokenizers 0.13.3
|
VitaliiVrublevskyi/output
|
VitaliiVrublevskyi
| 2023-09-25T19:54:27Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:finetune:meta-llama/Llama-2-7b-hf",
"region:us"
] | null | 2023-09-25T17:37:33Z |
---
base_model: meta-llama/Llama-2-7b-hf
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: output
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. -->
# output
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 None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4431
- Accuracy: 0.5
## 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: 1.41e-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
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 0.67 | 1 | 2.4252 | 0.5 |
| No log | 2.0 | 3 | 2.4431 | 0.5 |
### Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0
|
osangni/sdxlroks
|
osangni
| 2023-09-25T19:53:31Z | 8 | 1 |
diffusers
|
[
"diffusers",
"text-to-image",
"autotrain",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:finetune:stabilityai/stable-diffusion-xl-base-1.0",
"region:us"
] |
text-to-image
| 2023-08-21T11:51:30Z |
---
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: photo of a rktmsardr person
tags:
- text-to-image
- diffusers
- autotrain
inference: true
---
# DreamBooth trained by AutoTrain
Text encoder was not trained.
|
CyberHarem/tsurumaki_kokoro_bangdream
|
CyberHarem
| 2023-09-25T19:51:10Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/tsurumaki_kokoro_bangdream",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-25T19:32:18Z |
---
license: mit
datasets:
- CyberHarem/tsurumaki_kokoro_bangdream
pipeline_tag: text-to-image
tags:
- art
---
# Lora of tsurumaki_kokoro_bangdream
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 2880, you need to download `2880/tsurumaki_kokoro_bangdream.pt` as the embedding and `2880/tsurumaki_kokoro_bangdream.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 2880**, with the score of 0.970. The trigger words are:
1. `tsurumaki_kokoro_bangdream`
2. `blonde_hair, bangs, long_hair, yellow_eyes, smile, blush, open_mouth, :d`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | pattern_13 | pattern_14 | pattern_15 | pattern_16 | pattern_17 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:----------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 7200 | 0.914 | [Download](7200/tsurumaki_kokoro_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7200/previews/bikini.png) | [<NSFW, click to see>](7200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7200/previews/nude.png) | [<NSFW, click to see>](7200/previews/nude2.png) |  |  |
| 6720 | 0.921 | [Download](6720/tsurumaki_kokoro_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6720/previews/bikini.png) | [<NSFW, click to see>](6720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6720/previews/nude.png) | [<NSFW, click to see>](6720/previews/nude2.png) |  |  |
| 6240 | 0.940 | [Download](6240/tsurumaki_kokoro_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6240/previews/bikini.png) | [<NSFW, click to see>](6240/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6240/previews/nude.png) | [<NSFW, click to see>](6240/previews/nude2.png) |  |  |
| 5760 | 0.959 | [Download](5760/tsurumaki_kokoro_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5760/previews/bikini.png) | [<NSFW, click to see>](5760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5760/previews/nude.png) | [<NSFW, click to see>](5760/previews/nude2.png) |  |  |
| 5280 | 0.952 | [Download](5280/tsurumaki_kokoro_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5280/previews/bikini.png) | [<NSFW, click to see>](5280/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5280/previews/nude.png) | [<NSFW, click to see>](5280/previews/nude2.png) |  |  |
| 4800 | 0.928 | [Download](4800/tsurumaki_kokoro_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4800/previews/bikini.png) | [<NSFW, click to see>](4800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4800/previews/nude.png) | [<NSFW, click to see>](4800/previews/nude2.png) |  |  |
| 4320 | 0.968 | [Download](4320/tsurumaki_kokoro_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4320/previews/bikini.png) | [<NSFW, click to see>](4320/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4320/previews/nude.png) | [<NSFW, click to see>](4320/previews/nude2.png) |  |  |
| 3840 | 0.951 | [Download](3840/tsurumaki_kokoro_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3840/previews/bikini.png) | [<NSFW, click to see>](3840/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3840/previews/nude.png) | [<NSFW, click to see>](3840/previews/nude2.png) |  |  |
| 3360 | 0.936 | [Download](3360/tsurumaki_kokoro_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3360/previews/bikini.png) | [<NSFW, click to see>](3360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3360/previews/nude.png) | [<NSFW, click to see>](3360/previews/nude2.png) |  |  |
| **2880** | **0.970** | [**Download**](2880/tsurumaki_kokoro_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2880/previews/bikini.png) | [<NSFW, click to see>](2880/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2880/previews/nude.png) | [<NSFW, click to see>](2880/previews/nude2.png) |  |  |
| 2400 | 0.927 | [Download](2400/tsurumaki_kokoro_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2400/previews/bikini.png) | [<NSFW, click to see>](2400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2400/previews/nude.png) | [<NSFW, click to see>](2400/previews/nude2.png) |  |  |
| 1920 | 0.924 | [Download](1920/tsurumaki_kokoro_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1920/previews/bikini.png) | [<NSFW, click to see>](1920/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1920/previews/nude.png) | [<NSFW, click to see>](1920/previews/nude2.png) |  |  |
| 1440 | 0.914 | [Download](1440/tsurumaki_kokoro_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1440/previews/bikini.png) | [<NSFW, click to see>](1440/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1440/previews/nude.png) | [<NSFW, click to see>](1440/previews/nude2.png) |  |  |
| 960 | 0.880 | [Download](960/tsurumaki_kokoro_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](960/previews/bikini.png) | [<NSFW, click to see>](960/previews/bondage.png) |  |  |  | [<NSFW, click to see>](960/previews/nude.png) | [<NSFW, click to see>](960/previews/nude2.png) |  |  |
| 480 | 0.856 | [Download](480/tsurumaki_kokoro_bangdream.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](480/previews/bikini.png) | [<NSFW, click to see>](480/previews/bondage.png) |  |  |  | [<NSFW, click to see>](480/previews/nude.png) | [<NSFW, click to see>](480/previews/nude2.png) |  |  |
|
reciprocate/rm_beluga-7b_hh-full
|
reciprocate
| 2023-09-25T19:42:58Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-classification",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-25T19:16:13Z |
---
language:
- en
---
```python
from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
model_path = "reciprocate/rm-beluga-7b-hh-full"
model = AutoModelForSequenceClassification.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)
# for SequenceClassification models padding side should be "right"
tokenizer.padding_side = "right"
tokenizer.truncation_side = "left"
reward_fn = pipeline("text-classification", model=model, tokenizer=tokenizer, truncation=True, batch_size=32, max_length=2048, device=0)
output = reward_fn(["### User: Complete this sentence: I'm 99 percent sure it was someone being an...\n\n### Assistant:\n I'm 99 percent sure it was someone being an idiot.</s>"])
scores = [x["score"] for x in output]
scores
```
```
>>> [0.02713249810039997]
```
```python
# optionally normalize with mean, std computed on training data
scores = (np.array(scores) - 0.6816716283619826) / 0.3198637874065531
```
|
CyberHarem/shibuya_kanon_lovelivesuperstar
|
CyberHarem
| 2023-09-25T19:39:42Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/shibuya_kanon_lovelivesuperstar",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-25T19:26:21Z |
---
license: mit
datasets:
- CyberHarem/shibuya_kanon_lovelivesuperstar
pipeline_tag: text-to-image
tags:
- art
---
# Lora of shibuya_kanon_lovelivesuperstar
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 4160, you need to download `4160/shibuya_kanon_lovelivesuperstar.pt` as the embedding and `4160/shibuya_kanon_lovelivesuperstar.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 4160**, with the score of 0.999. The trigger words are:
1. `shibuya_kanon_lovelivesuperstar`
2. `orange_hair, bangs, purple_eyes, long_hair, smile, blush, ribbon, open_mouth, neck_ribbon, red_ribbon, medium_hair, shiny_hair`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:---------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 7800 | 0.998 | [Download](7800/shibuya_kanon_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7800/previews/nude.png) | [<NSFW, click to see>](7800/previews/nude2.png) |  |  |
| 7280 | 0.999 | [Download](7280/shibuya_kanon_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7280/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7280/previews/nude.png) | [<NSFW, click to see>](7280/previews/nude2.png) |  |  |
| 6760 | 0.997 | [Download](6760/shibuya_kanon_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6760/previews/nude.png) | [<NSFW, click to see>](6760/previews/nude2.png) |  |  |
| 6240 | 0.994 | [Download](6240/shibuya_kanon_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6240/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6240/previews/nude.png) | [<NSFW, click to see>](6240/previews/nude2.png) |  |  |
| 5720 | 0.996 | [Download](5720/shibuya_kanon_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5720/previews/nude.png) | [<NSFW, click to see>](5720/previews/nude2.png) |  |  |
| 5200 | 0.996 | [Download](5200/shibuya_kanon_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5200/previews/nude.png) | [<NSFW, click to see>](5200/previews/nude2.png) |  |  |
| 4680 | 0.997 | [Download](4680/shibuya_kanon_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4680/previews/nude.png) | [<NSFW, click to see>](4680/previews/nude2.png) |  |  |
| **4160** | **0.999** | [**Download**](4160/shibuya_kanon_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4160/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4160/previews/nude.png) | [<NSFW, click to see>](4160/previews/nude2.png) |  |  |
| 3640 | 0.997 | [Download](3640/shibuya_kanon_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3640/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3640/previews/nude.png) | [<NSFW, click to see>](3640/previews/nude2.png) |  |  |
| 3120 | 0.997 | [Download](3120/shibuya_kanon_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3120/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3120/previews/nude.png) | [<NSFW, click to see>](3120/previews/nude2.png) |  |  |
| 2600 | 0.937 | [Download](2600/shibuya_kanon_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2600/previews/nude.png) | [<NSFW, click to see>](2600/previews/nude2.png) |  |  |
| 2080 | 0.998 | [Download](2080/shibuya_kanon_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2080/previews/nude.png) | [<NSFW, click to see>](2080/previews/nude2.png) |  |  |
| 1560 | 0.997 | [Download](1560/shibuya_kanon_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1560/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1560/previews/nude.png) | [<NSFW, click to see>](1560/previews/nude2.png) |  |  |
| 1040 | 0.998 | [Download](1040/shibuya_kanon_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1040/previews/nude.png) | [<NSFW, click to see>](1040/previews/nude2.png) |  |  |
| 520 | 0.998 | [Download](520/shibuya_kanon_lovelivesuperstar.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](520/previews/bondage.png) |  |  |  | [<NSFW, click to see>](520/previews/nude.png) | [<NSFW, click to see>](520/previews/nude2.png) |  |  |
|
anuragrawal/bart-base-cnn-YT-transcript-sum
|
anuragrawal
| 2023-09-25T19:31:11Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bart",
"text2text-generation",
"generated_from_trainer",
"base_model:ainize/bart-base-cnn",
"base_model:finetune:ainize/bart-base-cnn",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-09-25T18:57:04Z |
---
license: apache-2.0
base_model: ainize/bart-base-cnn
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-base-cnn-YT-transcript-sum
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. -->
# bart-base-cnn-YT-transcript-sum
This model is a fine-tuned version of [ainize/bart-base-cnn](https://huggingface.co/ainize/bart-base-cnn) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4969
- Rouge1: 27.1516
- Rouge2: 14.6227
- Rougel: 23.3968
- Rougelsum: 25.4786
- Gen Len: 19.9954
## 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: 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: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| No log | 1.0 | 216 | 1.5374 | 24.7307 | 11.5124 | 20.6823 | 22.9189 | 19.9630 |
| No log | 2.0 | 432 | 1.4976 | 26.825 | 14.0512 | 23.2078 | 25.2044 | 19.9583 |
| 1.5449 | 3.0 | 648 | 1.4969 | 27.1516 | 14.6227 | 23.3968 | 25.4786 | 19.9954 |
| 1.5449 | 4.0 | 864 | 1.5345 | 27.2526 | 15.0873 | 23.8556 | 25.7798 | 19.9861 |
| 0.9 | 5.0 | 1080 | 1.5962 | 26.8267 | 14.7267 | 23.2263 | 25.2149 | 19.9676 |
| 0.9 | 6.0 | 1296 | 1.6378 | 26.8444 | 14.8753 | 23.254 | 25.2943 | 19.9815 |
| 0.5749 | 7.0 | 1512 | 1.6819 | 27.1776 | 14.898 | 23.2454 | 25.4298 | 19.9583 |
| 0.5749 | 8.0 | 1728 | 1.7360 | 26.9518 | 15.308 | 23.6574 | 25.2991 | 19.9769 |
| 0.5749 | 9.0 | 1944 | 1.7796 | 27.9253 | 15.7998 | 24.4827 | 26.4424 | 19.9769 |
| 0.3668 | 10.0 | 2160 | 1.8078 | 26.9211 | 15.0903 | 23.4484 | 25.4369 | 19.9815 |
| 0.3668 | 11.0 | 2376 | 1.8405 | 27.4434 | 15.3608 | 23.903 | 25.8117 | 19.9861 |
| 0.255 | 12.0 | 2592 | 1.8447 | 27.7175 | 15.7173 | 24.2096 | 26.0946 | 19.9815 |
| 0.255 | 13.0 | 2808 | 1.8834 | 27.2409 | 15.3865 | 23.7314 | 25.7682 | 19.9815 |
| 0.192 | 14.0 | 3024 | 1.8796 | 27.2939 | 15.5502 | 23.8294 | 25.7409 | 19.9815 |
| 0.192 | 15.0 | 3240 | 1.8851 | 27.6741 | 15.771 | 24.1976 | 26.1196 | 19.9722 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
CyberHarem/kabe_tomoe_soundeuphonium
|
CyberHarem
| 2023-09-25T18:39:49Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/kabe_tomoe_soundeuphonium",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-25T18:29:36Z |
---
license: mit
datasets:
- CyberHarem/kabe_tomoe_soundeuphonium
pipeline_tag: text-to-image
tags:
- art
---
# Lora of kabe_tomoe_soundeuphonium
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 4760, you need to download `4760/kabe_tomoe_soundeuphonium.pt` as the embedding and `4760/kabe_tomoe_soundeuphonium.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 4760**, with the score of 0.971. The trigger words are:
1. `kabe_tomoe_soundeuphonium`
2. `brown_hair, hair_ornament, heart, serafuku, blush, heart_hair_ornament, red_eyes, long_hair, short_hair`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:---------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.958 | [Download](5100/kabe_tomoe_soundeuphonium.zip) |  |  |  | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| **4760** | **0.971** | [**Download**](4760/kabe_tomoe_soundeuphonium.zip) |  |  |  | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.957 | [Download](4420/kabe_tomoe_soundeuphonium.zip) |  |  |  | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| 4080 | 0.969 | [Download](4080/kabe_tomoe_soundeuphonium.zip) |  |  |  | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.929 | [Download](3740/kabe_tomoe_soundeuphonium.zip) |  |  |  | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.936 | [Download](3400/kabe_tomoe_soundeuphonium.zip) |  |  |  | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.935 | [Download](3060/kabe_tomoe_soundeuphonium.zip) |  |  |  | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.911 | [Download](2720/kabe_tomoe_soundeuphonium.zip) |  |  |  | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.935 | [Download](2380/kabe_tomoe_soundeuphonium.zip) |  |  |  | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.909 | [Download](2040/kabe_tomoe_soundeuphonium.zip) |  |  |  | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.912 | [Download](1700/kabe_tomoe_soundeuphonium.zip) |  |  |  | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.812 | [Download](1360/kabe_tomoe_soundeuphonium.zip) |  |  |  | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.823 | [Download](1020/kabe_tomoe_soundeuphonium.zip) |  |  |  | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.627 | [Download](680/kabe_tomoe_soundeuphonium.zip) |  |  |  | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.016 | [Download](340/kabe_tomoe_soundeuphonium.zip) |  |  |  | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
CyberHarem/nishikino_maki_lovelive
|
CyberHarem
| 2023-09-25T18:38:50Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/nishikino_maki_lovelive",
"license:mit",
"region:us"
] |
text-to-image
| 2023-08-14T18:03:17Z |
---
license: mit
datasets:
- CyberHarem/nishikino_maki_lovelive
pipeline_tag: text-to-image
tags:
- art
---
# Lora of nishikino_maki_lovelive
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 4600, you need to download `4600/nishikino_maki_lovelive.pt` as the embedding and `4600/nishikino_maki_lovelive.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 4600**, with the score of 0.984. The trigger words are:
1. `nishikino_maki_lovelive`
2. `red_hair, purple_eyes, blush, short_hair, smile`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | pattern_13 | pattern_14 | pattern_15 | pattern_16 | pattern_17 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 6900 | 0.959 | [Download](6900/nishikino_maki_lovelive.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6900/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6900/previews/nude.png) | [<NSFW, click to see>](6900/previews/nude2.png) |  |  |
| 6440 | 0.941 | [Download](6440/nishikino_maki_lovelive.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6440/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6440/previews/nude.png) | [<NSFW, click to see>](6440/previews/nude2.png) |  |  |
| 5980 | 0.968 | [Download](5980/nishikino_maki_lovelive.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5980/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5980/previews/nude.png) | [<NSFW, click to see>](5980/previews/nude2.png) |  |  |
| 5520 | 0.970 | [Download](5520/nishikino_maki_lovelive.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5520/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5520/previews/nude.png) | [<NSFW, click to see>](5520/previews/nude2.png) |  |  |
| 5060 | 0.973 | [Download](5060/nishikino_maki_lovelive.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5060/previews/nude.png) | [<NSFW, click to see>](5060/previews/nude2.png) |  |  |
| **4600** | **0.984** | [**Download**](4600/nishikino_maki_lovelive.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4600/previews/nude.png) | [<NSFW, click to see>](4600/previews/nude2.png) |  |  |
| 4140 | 0.978 | [Download](4140/nishikino_maki_lovelive.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4140/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4140/previews/nude.png) | [<NSFW, click to see>](4140/previews/nude2.png) |  |  |
| 3680 | 0.978 | [Download](3680/nishikino_maki_lovelive.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3680/previews/nude.png) | [<NSFW, click to see>](3680/previews/nude2.png) |  |  |
| 3220 | 0.972 | [Download](3220/nishikino_maki_lovelive.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3220/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3220/previews/nude.png) | [<NSFW, click to see>](3220/previews/nude2.png) |  |  |
| 2760 | 0.974 | [Download](2760/nishikino_maki_lovelive.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2760/previews/nude.png) | [<NSFW, click to see>](2760/previews/nude2.png) |  |  |
| 2300 | 0.975 | [Download](2300/nishikino_maki_lovelive.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2300/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2300/previews/nude.png) | [<NSFW, click to see>](2300/previews/nude2.png) |  |  |
| 1840 | 0.968 | [Download](1840/nishikino_maki_lovelive.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1840/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1840/previews/nude.png) | [<NSFW, click to see>](1840/previews/nude2.png) |  |  |
| 1380 | 0.978 | [Download](1380/nishikino_maki_lovelive.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1380/previews/nude.png) | [<NSFW, click to see>](1380/previews/nude2.png) |  |  |
| 920 | 0.969 | [Download](920/nishikino_maki_lovelive.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](920/previews/bondage.png) |  |  |  | [<NSFW, click to see>](920/previews/nude.png) | [<NSFW, click to see>](920/previews/nude2.png) |  |  |
| 460 | 0.989 | [Download](460/nishikino_maki_lovelive.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](460/previews/bondage.png) |  |  |  | [<NSFW, click to see>](460/previews/nude.png) | [<NSFW, click to see>](460/previews/nude2.png) |  |  |
|
andrew45/xlm-roberta-base-finetuned-panx-en
|
andrew45
| 2023-09-25T18:36:31Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"dataset:xtreme",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-09-25T18:34:46Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- xtreme
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-en
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: xtreme
type: xtreme
config: PAN-X.en
split: validation
args: PAN-X.en
metrics:
- name: F1
type: f1
value: 0.6831183398766125
---
<!-- 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 the xtreme dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4028
- F1: 0.6831
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 1.1353 | 1.0 | 50 | 0.6267 | 0.5068 |
| 0.5283 | 2.0 | 100 | 0.4369 | 0.6552 |
| 0.358 | 3.0 | 150 | 0.4028 | 0.6831 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
MerziaAdamjee/phi-1_5-finetuned-gsm-hard1
|
MerziaAdamjee
| 2023-09-25T18:33:36Z | 58 | 0 |
transformers
|
[
"transformers",
"pytorch",
"mixformer-sequential",
"text-generation",
"generated_from_trainer",
"custom_code",
"base_model:microsoft/phi-1_5",
"base_model:finetune:microsoft/phi-1_5",
"license:other",
"autotrain_compatible",
"region:us"
] |
text-generation
| 2023-09-25T18:15:15Z |
---
license: other
base_model: microsoft/phi-1_5
tags:
- generated_from_trainer
model-index:
- name: phi-1_5-finetuned-gsm-hard1
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. -->
# phi-1_5-finetuned-gsm-hard1
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) 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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
HaseebArshad786/huggingFace
|
HaseebArshad786
| 2023-09-25T18:28:04Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-25T14:36:26Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: huggingFace
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 461.10 +/- 116.70
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
andrew45/xlm-roberta-base-finetuned-panx-de-fr
|
andrew45
| 2023-09-25T18:27:16Z | 125 | 0 |
transformers
|
[
"transformers",
"pytorch",
"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
| 2023-09-25T18:14:34Z |
---
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: 0.1623
- F1: 0.8603
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.2891 | 1.0 | 715 | 0.1813 | 0.8232 |
| 0.1482 | 2.0 | 1430 | 0.1586 | 0.8462 |
| 0.0959 | 3.0 | 2145 | 0.1623 | 0.8603 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
Dddokter/Nothing
|
Dddokter
| 2023-09-25T18:03:29Z | 0 | 2 | null |
[
"region:us"
] | null | 2023-02-22T09:04:27Z |
My first anime model with a Anything V3 base that had most of the NAI removed from it.
Merged with Yohan Diffusion
Merged with ?
Merged with Noise offset
Merged with ?
Merged with Icomix 3
Merged with CAB
Sorry for not keeping proper track of what I did to the model
|
DmitrMakeev/one-shot-talking-face
|
DmitrMakeev
| 2023-09-25T18:02:54Z | 0 | 1 | null |
[
"arxiv:2112.02749",
"region:us"
] | null | 2023-09-25T16:21:40Z |
# One-shot Talking Face Generation from Single-speaker Audio-Visual Correlation Learning (AAAI 2022)
#### [Paper](https://arxiv.org/pdf/2112.02749.pdf) | [Demo](https://www.youtube.com/watch?v=HHj-XCXXePY)
#### Requirements
- Python >= 3.6 , Pytorch >= 1.8 and ffmpeg
- Set up [OpenFace](https://github.com/TadasBaltrusaitis/OpenFace)
- We use the OpenFace tools to extract the initial pose of the reference image
- Make sure you have installed this tool, and set the `OPENFACE_POSE_EXTRACTOR_PATH` in `config.py`. For example, it should be the absolute path of the "`FeatureExtraction.exe`" for Windows.
- Other requirements are listed in the 'requirements.txt'
#### Pretrained Checkpoint
Please download the pretrained checkpoint from [google-drive](https://drive.google.com/file/d/1mjFEozPR_2vMaVRMd9Agk_sU1VaiUYMl/view?usp=sharing) and unzip it to the directory (`/checkpoints`). Or manually modify the settings of `GENERATOR_CKPT` and `AUDIO2POSE_CKPT` in the `config.py`.
#### Extract phoneme
We employ the [CMU phoneset](https://github.com/cmusphinx/cmudict) to represent phonemes, the extra 'SIL' means silence. All the phonesets can be seen in '`phindex.json`'.
We have extracted the phonemes for the audios in the '`sample/audio`' directory. For other audios, you can extract the phonemes by other ASR tools and then map them to the CMU phoneset. Or email to wangsuzhen@corp.netease.com for help.
#### Generate Demo Results
```
python test_script.py --img_path xxx.jpg --audio_path xxx.wav --phoneme_path xxx.json --save_dir "YOUR_DIR"
```
Note that the input images must keep the same height and width and the face should be appropriately cropped as in `samples/imgs`. You can also preprocess your images with `image_preprocess.py`.
#### License and Citation
```
@InProceedings{wang2021one,
author = Suzhen Wang, Lincheng Li, Yu Ding, Xin Yu
title = {One-shot Talking Face Generation from Single-speaker Audio-Visual Correlation Learning},
booktitle = {AAAI 2022},
year = {2022},
}
```
#### Acknowledgement
This codebase is based on [First Order Motion Model](https://github.com/AliaksandrSiarohin/first-order-model) and [imaginaire](https://github.com/NVlabs/imaginaire), thanks for their contributions.
|
CyberHarem/kazuno_sarah_lovelivesunshine
|
CyberHarem
| 2023-09-25T17:38:59Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/kazuno_sarah_lovelivesunshine",
"license:mit",
"region:us"
] |
text-to-image
| 2023-08-15T04:33:49Z |
---
license: mit
datasets:
- CyberHarem/kazuno_sarah_lovelivesunshine
pipeline_tag: text-to-image
tags:
- art
---
# Lora of kazuno_sarah_lovelivesunshine
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 7000, you need to download `7000/kazuno_sarah_lovelivesunshine.pt` as the embedding and `7000/kazuno_sarah_lovelivesunshine.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 7000**, with the score of 0.967. The trigger words are:
1. `kazuno_sarah_lovelivesunshine`
2. `bangs, purple_hair, sidelocks, smile, side_ponytail, purple_eyes, long_hair, blush, breasts`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------------|:-----------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 7500 | 0.892 | [Download](7500/kazuno_sarah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7500/previews/pattern_10.png) | [<NSFW, click to see>](7500/previews/pattern_11.png) |  | [<NSFW, click to see>](7500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7500/previews/nude.png) | [<NSFW, click to see>](7500/previews/nude2.png) |  |  |
| **7000** | **0.967** | [**Download**](7000/kazuno_sarah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7000/previews/pattern_10.png) | [<NSFW, click to see>](7000/previews/pattern_11.png) |  | [<NSFW, click to see>](7000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7000/previews/nude.png) | [<NSFW, click to see>](7000/previews/nude2.png) |  |  |
| 6500 | 0.964 | [Download](6500/kazuno_sarah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6500/previews/pattern_10.png) | [<NSFW, click to see>](6500/previews/pattern_11.png) |  | [<NSFW, click to see>](6500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6500/previews/nude.png) | [<NSFW, click to see>](6500/previews/nude2.png) |  |  |
| 6000 | 0.950 | [Download](6000/kazuno_sarah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6000/previews/pattern_10.png) | [<NSFW, click to see>](6000/previews/pattern_11.png) |  | [<NSFW, click to see>](6000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6000/previews/nude.png) | [<NSFW, click to see>](6000/previews/nude2.png) |  |  |
| 5500 | 0.921 | [Download](5500/kazuno_sarah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5500/previews/pattern_10.png) | [<NSFW, click to see>](5500/previews/pattern_11.png) |  | [<NSFW, click to see>](5500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5500/previews/nude.png) | [<NSFW, click to see>](5500/previews/nude2.png) |  |  |
| 5000 | 0.947 | [Download](5000/kazuno_sarah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5000/previews/pattern_10.png) | [<NSFW, click to see>](5000/previews/pattern_11.png) |  | [<NSFW, click to see>](5000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5000/previews/nude.png) | [<NSFW, click to see>](5000/previews/nude2.png) |  |  |
| 4500 | 0.907 | [Download](4500/kazuno_sarah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4500/previews/pattern_10.png) | [<NSFW, click to see>](4500/previews/pattern_11.png) |  | [<NSFW, click to see>](4500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4500/previews/nude.png) | [<NSFW, click to see>](4500/previews/nude2.png) |  |  |
| 4000 | 0.896 | [Download](4000/kazuno_sarah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4000/previews/pattern_10.png) | [<NSFW, click to see>](4000/previews/pattern_11.png) |  | [<NSFW, click to see>](4000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4000/previews/nude.png) | [<NSFW, click to see>](4000/previews/nude2.png) |  |  |
| 3500 | 0.874 | [Download](3500/kazuno_sarah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3500/previews/pattern_10.png) | [<NSFW, click to see>](3500/previews/pattern_11.png) |  | [<NSFW, click to see>](3500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3500/previews/nude.png) | [<NSFW, click to see>](3500/previews/nude2.png) |  |  |
| 3000 | 0.902 | [Download](3000/kazuno_sarah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3000/previews/pattern_10.png) | [<NSFW, click to see>](3000/previews/pattern_11.png) |  | [<NSFW, click to see>](3000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3000/previews/nude.png) | [<NSFW, click to see>](3000/previews/nude2.png) |  |  |
| 2500 | 0.858 | [Download](2500/kazuno_sarah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2500/previews/pattern_10.png) | [<NSFW, click to see>](2500/previews/pattern_11.png) |  | [<NSFW, click to see>](2500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2500/previews/nude.png) | [<NSFW, click to see>](2500/previews/nude2.png) |  |  |
| 2000 | 0.793 | [Download](2000/kazuno_sarah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2000/previews/pattern_10.png) | [<NSFW, click to see>](2000/previews/pattern_11.png) |  | [<NSFW, click to see>](2000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2000/previews/nude.png) | [<NSFW, click to see>](2000/previews/nude2.png) |  |  |
| 1500 | 0.806 | [Download](1500/kazuno_sarah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1500/previews/pattern_10.png) | [<NSFW, click to see>](1500/previews/pattern_11.png) |  | [<NSFW, click to see>](1500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1500/previews/nude.png) | [<NSFW, click to see>](1500/previews/nude2.png) |  |  |
| 1000 | 0.748 | [Download](1000/kazuno_sarah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1000/previews/pattern_10.png) | [<NSFW, click to see>](1000/previews/pattern_11.png) |  | [<NSFW, click to see>](1000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1000/previews/nude.png) | [<NSFW, click to see>](1000/previews/nude2.png) |  |  |
| 500 | 0.419 | [Download](500/kazuno_sarah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](500/previews/pattern_10.png) | [<NSFW, click to see>](500/previews/pattern_11.png) |  | [<NSFW, click to see>](500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](500/previews/nude.png) | [<NSFW, click to see>](500/previews/nude2.png) |  |  |
|
MerziaAdamjee/phi-1_5-finetuned-gsm-hard
|
MerziaAdamjee
| 2023-09-25T17:31:26Z | 48 | 0 |
transformers
|
[
"transformers",
"pytorch",
"mixformer-sequential",
"text-generation",
"generated_from_trainer",
"custom_code",
"base_model:microsoft/phi-1_5",
"base_model:finetune:microsoft/phi-1_5",
"license:other",
"autotrain_compatible",
"region:us"
] |
text-generation
| 2023-09-25T16:17:07Z |
---
license: other
base_model: microsoft/phi-1_5
tags:
- generated_from_trainer
model-index:
- name: phi-1_5-finetuned-gsm-hard
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. -->
# phi-1_5-finetuned-gsm-hard
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) 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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
youngwoo3283/emoji-test-v1
|
youngwoo3283
| 2023-09-25T17:21:36Z | 1 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-25T17:16:19Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### emoji_test_v1 Dreambooth model trained by youngwoo3283 with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
TexR6/ppo-Huggy
|
TexR6
| 2023-09-25T17:19:35Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-09-25T17:19:24Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
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: TexR6/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
openerotica/Qwen-7b
|
openerotica
| 2023-09-25T17:15:32Z | 14 | 0 |
transformers
|
[
"transformers",
"pytorch",
"qwen",
"text-generation",
"custom_code",
"license:other",
"autotrain_compatible",
"region:us"
] |
text-generation
| 2023-09-13T20:32:43Z |
---
license: other
---
Reuploaded from https://modelscope.cn/models/ccyh123/Qwen-7b/files (v1.0.0-09/13/2023)
|
nelsenputra/my_awesome_id_nergrit_corpus_model
|
nelsenputra
| 2023-09-25T17:08:01Z | 106 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"token-classification",
"generated_from_trainer",
"dataset:id_nergrit_corpus",
"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"
] |
token-classification
| 2023-09-25T16:25:39Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- id_nergrit_corpus
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: my_awesome_id_nergrit_corpus_model
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: id_nergrit_corpus
type: id_nergrit_corpus
config: ner
split: test
args: ner
metrics:
- name: Precision
type: precision
value: 0.6222415479943472
- name: Recall
type: recall
value: 0.6438695163104612
- name: F1
type: f1
value: 0.6328708054618829
- name: Accuracy
type: accuracy
value: 0.9038083290743236
---
<!-- 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. -->
# my_awesome_id_nergrit_corpus_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the id_nergrit_corpus dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3602
- Precision: 0.6222
- Recall: 0.6439
- F1: 0.6329
- Accuracy: 0.9038
## 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: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.9117 | 1.0 | 784 | 0.4198 | 0.5691 | 0.5948 | 0.5817 | 0.8893 |
| 0.4089 | 2.0 | 1568 | 0.3602 | 0.6222 | 0.6439 | 0.6329 | 0.9038 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
ayoubkirouane/QA-DistilBERT-base-squad
|
ayoubkirouane
| 2023-09-25T16:51:54Z | 112 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"question-answering",
"en",
"dataset:squad_v2",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-09-25T11:25:09Z |
---
datasets:
- squad_v2
language:
- en
library_name: transformers
pipeline_tag: question-answering
---
## Overview
+ **Model Name**: QA-DistilBERT-base-squad
+ **Task**: Question Answering (QA)
+ **Dataset**: squad_v2
+ **Model Type**: DistilBERT-based model
## Model Description
**QA-DistilBERT-base-squad** is a fine-tuned version of the DistilBERT model, which is a smaller and faster variant of BERT while preserving much of BERT's performance. It has been fine-tuned for the task of Question Answering (QA) on the squad_v2 dataset.
## Dataset
+ **Name**: squad_v2
+ **Description**: The squad_v2 dataset combines 100,000 questions from SQuAD1.1 with over 50,000 unanswerable questions written adversarially to resemble answerable ones. This dataset challenges models not only to answer questions correctly when possible but also to recognize when no answer is supported by the paragraph.
## Usage
**QA-DistilBERT-base-squad** can be used for a wide range of question answering tasks. It is suitable for extracting answers from passages of text given a question. Users can input a passage and a question, and the model will generate an answer.
## Limitations
Like all language models, QA-DistilBERT-base-squad may generate incorrect answers if the training data contains inaccuracies or ambiguities.
The model's performance may vary depending on the complexity and domain of the questions.
## Ethical Considerations
When using QA-DistilBERT-base-squad for question answering tasks, it is essential to be aware of potential biases in the training data and to ensure that the model does not produce harmful or biased answers.
## Get started
```python
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("question-answering", model="ayoubkirouane/QA-DistilBERT-base-squad")
context = """
The Amazon rainforest (Portuguese: Floresta Amazônica or Amazônia; Spanish: Selva Amazónica,Amazonía or usually Amazonia; French: Forêt amazonienne; Dutch: Amazoneregenwoud),also known in English as Amazonia or the Amazon Jungle, is a moist broadleaf forest that covers most of the Amazon basin of South America.This basin encompasses 7,000,000 square kilometres
(2,700,000 sq mi), of which 5,500,000 square kilometres (2,100,000 sq mi) are covered by the rainforest. This region includes territory belonging to nine nations.The majority of the forest is contained within Brazil, with 60% of the rainforest,
followed by Peru with 13%, Colombia with 10%, and with minor amounts in Venezuela, Ecuador, Bolivia, Guyana, Suriname and French Guiana. States or departments in four nations contain "Amazonas" in their names. The Amazon represents over half of the planet's remaining rainforests, and comprises the largest and most biodiverse tract of tropical rainforest in the world,with an estimated 390 billion individual trees divided into 16,000 species.
"""
question = "Which name is also used to describe the Amazon rainforest in English?"
result = pipe(question=question, context=context)
print(result)
```
|
Akash092003/QLora-Llama-2-7b-finetuned-absa2-float32
|
Akash092003
| 2023-09-25T16:48:46Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-25T16:48:44Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- 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: True
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- 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: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0
- PEFT 0.5.0
|
GRPUI/sgugit-model-v3
|
GRPUI
| 2023-09-25T16:47:53Z | 110 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"bert",
"text-classification",
"autotrain",
"unk",
"dataset:GRPUI/autotrain-data-sgugit-model-v3",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-25T16:45:53Z |
---
tags:
- autotrain
- text-classification
language:
- unk
widget:
- text: "I love AutoTrain"
datasets:
- GRPUI/autotrain-data-sgugit-model-v3
co2_eq_emissions:
emissions: 0.7899863264115066
---
# Model Trained Using AutoTrain
- Problem type: Multi-class Classification
- Model ID: 91416144506
- CO2 Emissions (in grams): 0.7900
## Validation Metrics
- Loss: 0.020
- Accuracy: 1.000
- Macro F1: 1.000
- Micro F1: 1.000
- Weighted F1: 1.000
- Macro Precision: 1.000
- Micro Precision: 1.000
- Weighted Precision: 1.000
- Macro Recall: 1.000
- Micro Recall: 1.000
- Weighted Recall: 1.000
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/GRPUI/autotrain-sgugit-model-v3-91416144506
```
Or Python API:
```
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("GRPUI/autotrain-sgugit-model-v3-91416144506", use_auth_token=True)
tokenizer = AutoTokenizer.from_pretrained("GRPUI/autotrain-sgugit-model-v3-91416144506", use_auth_token=True)
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
outputs = model(**inputs)
```
|
perfectlybaked/flant5-dolly-QnA-prompt
|
perfectlybaked
| 2023-09-25T16:20:18Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-09-25T16:18:16Z |
FlanT5 finetuned on databricks dolly-15k dataset for QnA
|
juliareis/Taxi-v3
|
juliareis
| 2023-09-25T15:58:14Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-25T15:58:12Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.50 +/- 2.73
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="juliareis/Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
javidlakha/Llama-2-7b-qlora-python
|
javidlakha
| 2023-09-25T15:48:05Z | 60 | 0 |
peft
|
[
"peft",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:adapter:meta-llama/Llama-2-7b-hf",
"region:us"
] | null | 2023-07-22T20:57:53Z |
---
library_name: peft
base_model: meta-llama/Llama-2-7b-hf
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- 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
### Framework versions
- PEFT 0.4.0
|
CyberHarem/kunikida_hanamaru_lovelivesunshine
|
CyberHarem
| 2023-09-25T15:40:07Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/kunikida_hanamaru_lovelivesunshine",
"license:mit",
"region:us"
] |
text-to-image
| 2023-08-15T01:57:18Z |
---
license: mit
datasets:
- CyberHarem/kunikida_hanamaru_lovelivesunshine
pipeline_tag: text-to-image
tags:
- art
---
# Lora of kunikida_hanamaru_lovelivesunshine
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 3360, you need to download `3360/kunikida_hanamaru_lovelivesunshine.pt` as the embedding and `3360/kunikida_hanamaru_lovelivesunshine.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 3360**, with the score of 0.981. The trigger words are:
1. `kunikida_hanamaru_lovelivesunshine`
2. `brown_hair, bangs, long_hair, blush, yellow_eyes, smile, brown_eyes, open_mouth`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | pattern_13 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 7200 | 0.972 | [Download](7200/kunikida_hanamaru_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7200/previews/bikini.png) | [<NSFW, click to see>](7200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7200/previews/nude.png) | [<NSFW, click to see>](7200/previews/nude2.png) |  |  |
| 6720 | 0.981 | [Download](6720/kunikida_hanamaru_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6720/previews/bikini.png) | [<NSFW, click to see>](6720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6720/previews/nude.png) | [<NSFW, click to see>](6720/previews/nude2.png) |  |  |
| 6240 | 0.969 | [Download](6240/kunikida_hanamaru_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6240/previews/bikini.png) | [<NSFW, click to see>](6240/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6240/previews/nude.png) | [<NSFW, click to see>](6240/previews/nude2.png) |  |  |
| 5760 | 0.974 | [Download](5760/kunikida_hanamaru_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5760/previews/bikini.png) | [<NSFW, click to see>](5760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5760/previews/nude.png) | [<NSFW, click to see>](5760/previews/nude2.png) |  |  |
| 5280 | 0.974 | [Download](5280/kunikida_hanamaru_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5280/previews/bikini.png) | [<NSFW, click to see>](5280/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5280/previews/nude.png) | [<NSFW, click to see>](5280/previews/nude2.png) |  |  |
| 4800 | 0.977 | [Download](4800/kunikida_hanamaru_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4800/previews/bikini.png) | [<NSFW, click to see>](4800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4800/previews/nude.png) | [<NSFW, click to see>](4800/previews/nude2.png) |  |  |
| 4320 | 0.977 | [Download](4320/kunikida_hanamaru_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4320/previews/bikini.png) | [<NSFW, click to see>](4320/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4320/previews/nude.png) | [<NSFW, click to see>](4320/previews/nude2.png) |  |  |
| 3840 | 0.968 | [Download](3840/kunikida_hanamaru_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3840/previews/bikini.png) | [<NSFW, click to see>](3840/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3840/previews/nude.png) | [<NSFW, click to see>](3840/previews/nude2.png) |  |  |
| **3360** | **0.981** | [**Download**](3360/kunikida_hanamaru_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3360/previews/bikini.png) | [<NSFW, click to see>](3360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3360/previews/nude.png) | [<NSFW, click to see>](3360/previews/nude2.png) |  |  |
| 2880 | 0.977 | [Download](2880/kunikida_hanamaru_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2880/previews/bikini.png) | [<NSFW, click to see>](2880/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2880/previews/nude.png) | [<NSFW, click to see>](2880/previews/nude2.png) |  |  |
| 2400 | 0.972 | [Download](2400/kunikida_hanamaru_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2400/previews/bikini.png) | [<NSFW, click to see>](2400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2400/previews/nude.png) | [<NSFW, click to see>](2400/previews/nude2.png) |  |  |
| 1920 | 0.970 | [Download](1920/kunikida_hanamaru_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1920/previews/bikini.png) | [<NSFW, click to see>](1920/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1920/previews/nude.png) | [<NSFW, click to see>](1920/previews/nude2.png) |  |  |
| 1440 | 0.970 | [Download](1440/kunikida_hanamaru_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1440/previews/bikini.png) | [<NSFW, click to see>](1440/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1440/previews/nude.png) | [<NSFW, click to see>](1440/previews/nude2.png) |  |  |
| 960 | 0.957 | [Download](960/kunikida_hanamaru_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](960/previews/bikini.png) | [<NSFW, click to see>](960/previews/bondage.png) |  |  |  | [<NSFW, click to see>](960/previews/nude.png) | [<NSFW, click to see>](960/previews/nude2.png) |  |  |
| 480 | 0.901 | [Download](480/kunikida_hanamaru_lovelivesunshine.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](480/previews/bikini.png) | [<NSFW, click to see>](480/previews/bondage.png) |  |  |  | [<NSFW, click to see>](480/previews/nude.png) | [<NSFW, click to see>](480/previews/nude2.png) |  |  |
|
Ja-ck/llama-2-7b-fattn2-test
|
Ja-ck
| 2023-09-25T15:33:21Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-25T15:27:20Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0
|
Itamart/q-Taxi-v3
|
Itamart
| 2023-09-25T15:28:34Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-25T15:28:27Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
model = load_from_hub(repo_id="Itamart/q-Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
|
surya0820/orbitshiftv2
|
surya0820
| 2023-09-25T15:28:22Z | 181 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-25T15:19:29Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: orbitshiftv2
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. -->
# orbitshiftv2
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) 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: 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: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 29 | 2.2750 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
HassanAwan/asr_Train_Model
|
HassanAwan
| 2023-09-25T15:16:35Z | 109 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:minds14",
"base_model:facebook/wav2vec2-base",
"base_model:finetune:facebook/wav2vec2-base",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-09-25T14:12:53Z |
---
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- minds14
metrics:
- wer
model-index:
- name: asr_Train_Model
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: minds14
type: minds14
config: en-US
split: train[:5]
args: en-US
metrics:
- name: Wer
type: wer
value: 1.0
---
<!-- 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. -->
# asr_Train_Model
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
It achieves the following results on the evaluation set:
- Loss: nan
- Wer: 1.0
## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---:|
| 0.0 | 20.0 | 20 | nan | 1.0 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
fruuzen/openlm-research-open_llama_3b_v2
|
fruuzen
| 2023-09-25T15:13:25Z | 0 | 0 |
peft
|
[
"peft",
"pytorch",
"llama",
"region:us"
] | null | 2023-09-25T14:51:50Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- 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
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- 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 0.6.0.dev0
- PEFT 0.6.0.dev0
|
Itamart/q-FrozenLake-v1-4x4-noSlippery
|
Itamart
| 2023-09-25T15:06:30Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-25T14:58:25Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
model = load_from_hub(repo_id="Itamart/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
|
anujsahani01/PyLoomer_CodeParrot
|
anujsahani01
| 2023-09-25T15:05:04Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:codeparrot/codeparrot-small",
"base_model:finetune:codeparrot/codeparrot-small",
"license:apache-2.0",
"region:us"
] | null | 2023-09-02T06:56:27Z |
---
license: apache-2.0
base_model: codeparrot/codeparrot-small
tags:
- generated_from_trainer
model-index:
- name: PyLoomer_CodeParrot
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. -->
# PyLoomer_CodeParrot
This model is a fine-tuned version of [codeparrot/codeparrot-small](https://huggingface.co/codeparrot/codeparrot-small) 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: 0.0001
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 80
- training_steps: 8500
### Training results
### Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0
|
redutskaya/Olya-la
|
redutskaya
| 2023-09-25T14:43:19Z | 0 | 0 | null |
[
"art",
"text-generation-inference",
"license:openrail",
"region:us"
] | null | 2023-09-25T14:39:54Z |
---
license: openrail
tags:
- art
- text-generation-inference
---
|
CyberHarem/kazuno_leah_lovelivesunshine
|
CyberHarem
| 2023-09-25T14:40:06Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/kazuno_leah_lovelivesunshine",
"license:mit",
"region:us"
] |
text-to-image
| 2023-08-15T00:47:47Z |
---
license: mit
datasets:
- CyberHarem/kazuno_leah_lovelivesunshine
pipeline_tag: text-to-image
tags:
- art
---
# Lora of kazuno_leah_lovelivesunshine
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 3960, you need to download `3960/kazuno_leah_lovelivesunshine.pt` as the embedding and `3960/kazuno_leah_lovelivesunshine.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 3960**, with the score of 0.968. The trigger words are:
1. `kazuno_leah_lovelivesunshine`
2. `purple_hair, purple_eyes, twintails, bangs, blush, smile, hair_ribbon`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5400 | 0.939 | [Download](5400/kazuno_leah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5400/previews/nude.png) | [<NSFW, click to see>](5400/previews/nude2.png) |  |  |
| 5040 | 0.926 | [Download](5040/kazuno_leah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5040/previews/nude.png) | [<NSFW, click to see>](5040/previews/nude2.png) |  |  |
| 4680 | 0.921 | [Download](4680/kazuno_leah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4680/previews/nude.png) | [<NSFW, click to see>](4680/previews/nude2.png) |  |  |
| 4320 | 0.930 | [Download](4320/kazuno_leah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4320/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4320/previews/nude.png) | [<NSFW, click to see>](4320/previews/nude2.png) |  |  |
| **3960** | **0.968** | [**Download**](3960/kazuno_leah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3960/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3960/previews/nude.png) | [<NSFW, click to see>](3960/previews/nude2.png) |  |  |
| 3600 | 0.919 | [Download](3600/kazuno_leah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3600/previews/nude.png) | [<NSFW, click to see>](3600/previews/nude2.png) |  |  |
| 3240 | 0.904 | [Download](3240/kazuno_leah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3240/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3240/previews/nude.png) | [<NSFW, click to see>](3240/previews/nude2.png) |  |  |
| 2880 | 0.851 | [Download](2880/kazuno_leah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2880/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2880/previews/nude.png) | [<NSFW, click to see>](2880/previews/nude2.png) |  |  |
| 2520 | 0.933 | [Download](2520/kazuno_leah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2520/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2520/previews/nude.png) | [<NSFW, click to see>](2520/previews/nude2.png) |  |  |
| 2160 | 0.886 | [Download](2160/kazuno_leah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2160/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2160/previews/nude.png) | [<NSFW, click to see>](2160/previews/nude2.png) |  |  |
| 1800 | 0.804 | [Download](1800/kazuno_leah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1800/previews/nude.png) | [<NSFW, click to see>](1800/previews/nude2.png) |  |  |
| 1440 | 0.833 | [Download](1440/kazuno_leah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1440/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1440/previews/nude.png) | [<NSFW, click to see>](1440/previews/nude2.png) |  |  |
| 1080 | 0.841 | [Download](1080/kazuno_leah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1080/previews/nude.png) | [<NSFW, click to see>](1080/previews/nude2.png) |  |  |
| 720 | 0.875 | [Download](720/kazuno_leah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](720/previews/nude.png) | [<NSFW, click to see>](720/previews/nude2.png) |  |  |
| 360 | 0.402 | [Download](360/kazuno_leah_lovelivesunshine.zip) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](360/previews/nude.png) | [<NSFW, click to see>](360/previews/nude2.png) |  |  |
|
anujsahani01/PyLoomer_CodeGen
|
anujsahani01
| 2023-09-25T14:33:48Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:Salesforce/codegen-350M-mono",
"base_model:finetune:Salesforce/codegen-350M-mono",
"license:bsd-3-clause",
"region:us"
] | null | 2023-09-06T03:49:31Z |
---
license: bsd-3-clause
base_model: Salesforce/codegen-350M-mono
tags:
- generated_from_trainer
model-index:
- name: PyLoomer_CodeGen
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. -->
# PyLoomer_CodeGen
This model is a fine-tuned version of [Salesforce/codegen-350M-mono](https://huggingface.co/Salesforce/codegen-350M-mono) 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: 0.0001
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 80
- training_steps: 8500
### Training results
### Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0
|
Meghana779905/my-pet-dog
|
Meghana779905
| 2023-09-25T14:32:43Z | 4 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-25T14:28:57Z |
---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### My-Pet-Dog Dreambooth model trained by Meghana779905 following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: GoX19932gASdi
Sample pictures of this concept:
.jpg)
|
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.