Datasets:
librarian-bots
/
model_cards_with_metadata

Dataset card Data Studio Files
xet
Community
3
modelId
stringlengths
5
139
author
stringlengths
2
42
last_modified
timestamp[us, tz=UTC]date
2020-02-15 11:33:14
2025-09-09 12:33:01
downloads
int64
0
223M
likes
int64
0
11.7k
library_name
stringclasses
550 values
tags
listlengths
1
4.05k
pipeline_tag
stringclasses
55 values
createdAt
timestamp[us, tz=UTC]date
2022-03-02 23:29:04
2025-09-09 12:32:40
card
stringlengths
11
1.01M
InriaValda/cc_math_roberta_ep01
InriaValda
2023-06-28T13:49:10Z
71
0
transformers
[ "transformers", "tf", "roberta", "text-classification", "fill-mask", "license:openrail", "autotrain_compatible", "endpoints_compatible", "region:us" ]
fill-mask
2023-06-28T13:16:33Z
--- license: openrail pipeline_tag: fill-mask ---
SHENMU007/neunit_BASE_V10.11
SHENMU007
2023-06-28T13:47:53Z
75
0
transformers
[ "transformers", "pytorch", "tensorboard", "speecht5", "text-to-audio", "1.1.0", "generated_from_trainer", "zh", "dataset:facebook/voxpopuli", "license:mit", "endpoints_compatible", "region:us" ]
text-to-audio
2023-06-28T10:49:37Z
--- language: - zh license: mit tags: - 1.1.0 - generated_from_trainer datasets: - facebook/voxpopuli model-index: - name: SpeechT5 TTS Dutch neunit 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. --> # SpeechT5 TTS Dutch neunit This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the VoxPopuli 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: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.29.2 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
YakovElm/Hyperledger_20_BERT_Over_Sampling
YakovElm
2023-06-28T13:44:48Z
61
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T13:44:12Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Hyperledger_20_BERT_Over_Sampling 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. --> # Hyperledger_20_BERT_Over_Sampling 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: 0.0420 - Train Accuracy: 0.9866 - Validation Loss: 0.7502 - Validation Accuracy: 0.8444 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.4566 | 0.7724 | 0.5710 | 0.7376 | 0 | | 0.0873 | 0.9735 | 0.6176 | 0.8662 | 1 | | 0.0420 | 0.9866 | 0.7502 | 0.8444 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
sleepynlp/q-Taxi-v3-v1-leo
sleepynlp
2023-06-28T13:26:47Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T13:26:43Z
--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-Taxi-v3-v1-leo 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 ```python model = load_from_hub(repo_id="sleepynlp/q-Taxi-v3-v1-leo", 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"]) ```
dev-senolys/camembert_base_finetunned_one_thema_balanced_6_epochs
dev-senolys
2023-06-28T13:22:20Z
105
0
transformers
[ "transformers", "pytorch", "tensorboard", "camembert", "text-classification", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T11:52:40Z
--- license: mit tags: - generated_from_trainer model-index: - name: camembert_base_finetunned_one_thema_balanced_6_epochs 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. --> # camembert_base_finetunned_one_thema_balanced_6_epochs This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.7237 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 6 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | No log | 1.0 | 116 | 2.3397 | | No log | 2.0 | 232 | 2.0559 | | No log | 3.0 | 348 | 1.8209 | | No log | 4.0 | 464 | 1.7804 | | 1.9817 | 5.0 | 580 | 1.7323 | | 1.9817 | 6.0 | 696 | 1.7237 | ### Framework versions - Transformers 4.29.2 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
sleepynlp/q-FrozenLake-v1-4x4-noSlippery-leo
sleepynlp
2023-06-28T13:20:09Z
0
0
null
[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T13:20:05Z
--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery-leo 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="sleepynlp/q-FrozenLake-v1-4x4-noSlippery-leo", 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"]) ```
ryo1443/2ch_rinna_1k
ryo1443
2023-06-28T13:15:56Z
0
0
peft
[ "peft", "region:us" ]
null
2023-06-28T13:15:08Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
kvarnalidis/LunarLander-v2-PPO
kvarnalidis
2023-06-28T13:07:14Z
0
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T13:06:52Z
--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 227.29 +/- 50.90 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
catrabbitbear/pyramids2
catrabbitbear
2023-06-28T12:51:21Z
3
0
ml-agents
[ "ml-agents", "tensorboard", "onnx", "Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids", "region:us" ]
reinforcement-learning
2023-06-28T12:51:20Z
--- library_name: ml-agents tags: - Pyramids - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Pyramids --- # **ppo** Agent playing **Pyramids** This is a trained model of a **ppo** agent playing **Pyramids** 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: catrabbitbear/pyramids2 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
YakovElm/Qt_20_BERT_Under_Sampling
YakovElm
2023-06-28T12:49:09Z
61
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T12:48:33Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Qt_20_BERT_Under_Sampling 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. --> # Qt_20_BERT_Under_Sampling 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: 0.0003 - Train Accuracy: 1.0 - Validation Loss: 0.3606 - Validation Accuracy: 0.9586 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.0366 | 0.9886 | 0.2979 | 0.9586 | 0 | | 0.0006 | 1.0 | 0.3361 | 0.9586 | 1 | | 0.0003 | 1.0 | 0.3606 | 0.9586 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
jensvw/taxi-v3
jensvw
2023-06-28T12:47:36Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T12:47:32Z
--- 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: 7.54 +/- 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="jensvw/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"]) ```
robrecht/taxi_v1
robrecht
2023-06-28T12:44:10Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T12:36:05Z
--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: taxi_v1 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 ```python model = load_from_hub(repo_id="robrecht/taxi_v1", 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"]) ```
jensvw/q-FrozenLake-v1-4x4-noSlippery
jensvw
2023-06-28T12:38:03Z
0
0
null
[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T12:37:59Z
--- 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="jensvw/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"]) ```
lordpepe/ppo-LunarLander-v2
lordpepe
2023-06-28T12:36:31Z
1
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T12:36:07Z
--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 252.07 +/- 15.38 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
ryo1443/2ch_rinna
ryo1443
2023-06-28T12:35:31Z
0
0
peft
[ "peft", "region:us" ]
null
2023-06-28T12:20:39Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
Michailo1324/TI-mobilenetv3-imagenet-v2
Michailo1324
2023-06-28T12:28:36Z
4
0
tf-keras
[ "tf-keras", "mobilenet", "image-classification", "region:us" ]
image-classification
2023-05-15T10:46:21Z
--- pipeline_tag: image-classification ---
Deepamparmar/Bloom3B-LORA
Deepamparmar
2023-06-28T12:25:46Z
0
0
peft
[ "peft", "region:us" ]
null
2023-06-28T12:25:41Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
Raizel123/Vbabylora
Raizel123
2023-06-28T12:25:37Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-28T12:22:00Z
--- license: creativeml-openrail-m ---
trustvare/trustvare-pst-to-eml
trustvare
2023-06-28T12:18:10Z
0
0
null
[ "region:us" ]
null
2023-06-28T12:14:23Z
A trustworthy program for converting Outlook PST files to EML format is TrustVare PST to EML Converter. With the help of this utility, users can extract certain emails from PST files and save them as independent EML files. Users can concurrently convert many PST files to EML thanks to its bulk conversion functionality. Throughout the conversion process, the converter preserves the original email layout, attachments, metadata, and folder structure. Additionally, it offers filters that let users choose only the emails they want to convert based on predetermined criteria. The PST to EML Converter is a useful tool for users and businesses looking to move their Outlook emails to EML format, compatible with a variety of email clients and platforms, thanks to its user-friendly interface and effective conversion capabilities. Read More: https://www.trustvare.com/pst/eml/
gurjotsaggu/Gurjot
gurjotsaggu
2023-06-28T12:09:05Z
0
0
null
[ "license:bigcode-openrail-m", "region:us" ]
null
2023-06-28T12:09:05Z
--- license: bigcode-openrail-m ---
mahsa-gh/my_awesome_model
mahsa-gh
2023-06-28T11:55:49Z
61
0
transformers
[ "transformers", "tf", "distilbert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-27T04:12:07Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: mahsa-gh/my_awesome_model 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. --> # mahsa-gh/my_awesome_model This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.0625 - Validation Loss: 0.2113 - Train Accuracy: 0.9318 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 7810, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Validation Loss | Train Accuracy | Epoch | |:----------:|:---------------:|:--------------:|:-----:| | 0.2532 | 0.1893 | 0.9288 | 0 | | 0.1336 | 0.1840 | 0.9321 | 1 | | 0.0625 | 0.2113 | 0.9318 | 2 | ### Framework versions - Transformers 4.28.1 - TensorFlow 2.11.0 - Datasets 2.12.0 - Tokenizers 0.13.3
catrabbitbear/pyramids1
catrabbitbear
2023-06-28T11:51:08Z
2
0
ml-agents
[ "ml-agents", "tensorboard", "onnx", "Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids", "region:us" ]
reinforcement-learning
2023-06-28T11:51:06Z
--- library_name: ml-agents tags: - Pyramids - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Pyramids --- # **ppo** Agent playing **Pyramids** This is a trained model of a **ppo** agent playing **Pyramids** 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: catrabbitbear/pyramids1 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
NickyNicky/MPT-7b-instruct-QLora-8Bits-Peft-h2ogpt_oig_oasst1_instruct_cleaned_v3-0.2_Epoch-V1
NickyNicky
2023-06-28T11:48:19Z
1
0
peft
[ "peft", "region:us" ]
null
2023-06-28T11:48:16Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
czz23/SplitStatement-setfit-model
czz23
2023-06-28T11:47:11Z
3
0
sentence-transformers
[ "sentence-transformers", "pytorch", "albert", "setfit", "text-classification", "arxiv:2209.11055", "license:apache-2.0", "region:us" ]
text-classification
2023-06-28T11:47:08Z
--- license: apache-2.0 tags: - setfit - sentence-transformers - text-classification pipeline_tag: text-classification --- # czz23/SplitStatement-setfit-model This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. ## Usage To use this model for inference, first install the SetFit library: ```bash python -m pip install setfit ``` You can then run inference as follows: ```python from setfit import SetFitModel # Download from Hub and run inference model = SetFitModel.from_pretrained("czz23/SplitStatement-setfit-model") # Run inference preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"]) ``` ## BibTeX entry and citation info ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ```
RayTracerGC/RVCModels
RayTracerGC
2023-06-28T11:46:11Z
0
1
null
[ "license:openrail", "region:us" ]
null
2023-06-27T15:56:50Z
--- license: openrail --- RVC models: - Hal Jordan Green Lantern (From Injustice 2) (RVC v2) (76 Epochs) - Trained on `mangio-crepe` using 6 minutes of audio - Batch size: 16 - Crepe hop length: 64 - File: GreenLantern.zip - Wonder Woman (From Injustice 2) (RVC v2) (150 Epochs) - Trained on `mangio-crepe` using 9 minutes of audio - Batch size: 16 - Crepe hop length: 64 - File: WonderWoman.zip
BerserkerMother/Reinforce-Pixelcopter-PLE-v0
BerserkerMother
2023-06-28T11:45:36Z
0
0
null
[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T11:45:35Z
--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-Pixelcopter-PLE-v0 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 11.90 +/- 8.77 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
YakovElm/Hyperledger_15_BERT_Over_Sampling
YakovElm
2023-06-28T11:44:13Z
58
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T11:43:37Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Hyperledger_15_BERT_Over_Sampling 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. --> # Hyperledger_15_BERT_Over_Sampling 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: 0.0278 - Train Accuracy: 0.9920 - Validation Loss: 0.8934 - Validation Accuracy: 0.8278 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.4883 | 0.7456 | 0.5933 | 0.7749 | 0 | | 0.1029 | 0.9652 | 0.7254 | 0.8683 | 1 | | 0.0278 | 0.9920 | 0.8934 | 0.8278 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
androadi/ppo-LunarLander-v2
androadi
2023-06-28T11:36:53Z
0
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T11:36:31Z
--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 253.66 +/- 18.76 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
YakovElm/Qt_15_BERT_Under_Sampling
YakovElm
2023-06-28T11:35:53Z
61
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T11:35:18Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Qt_15_BERT_Under_Sampling 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. --> # Qt_15_BERT_Under_Sampling 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: 0.0002 - Train Accuracy: 1.0 - Validation Loss: 0.4444 - Validation Accuracy: 0.9505 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.0261 | 0.9997 | 0.3635 | 0.9505 | 0 | | 0.0005 | 1.0 | 0.4156 | 0.9505 | 1 | | 0.0002 | 1.0 | 0.4444 | 0.9505 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
hztang/t5-small-base-custom
hztang
2023-06-28T11:18:41Z
103
0
transformers
[ "transformers", "pytorch", "t5", "text2text-generation", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text2text-generation
2023-06-28T09:29:18Z
--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: t5-large-base-custom 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. --> # t5-large-base-custom This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) 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: 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: 1 ### Training results | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| | No log | 1.0 | 238 | 1.0463 | 25.3323 | 19.1916 | 23.8957 | 24.792 | 19.0 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.12.1 - Datasets 2.13.1 - Tokenizers 0.11.0
NickyNicky/MPT-7b-instruct-QLora-8Bits-Peft-train_eli5-1_Epoch-V8
NickyNicky
2023-06-28T11:09:07Z
2
0
peft
[ "peft", "region:us" ]
null
2023-06-28T11:09:03Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
wyklq/falcon-40b-gptq
wyklq
2023-06-28T11:08:48Z
9
2
transformers
[ "transformers", "safetensors", "RefinedWeb", "text-generation", "custom_code", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-28T10:58:03Z
Strict copy of https://huggingface.co/tiiuae/falcon-40b but quantized with GPTQ (on wikitext-2, 4bits, groupsize=128). Intended to be used with https://github.com/huggingface/text-generation-inference ``` model=huggingface/falcon-40b-gptq num_shard=2 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:0.8 --model-id $model --num-shard $num_shard --quantize gptq ``` For full configuration and usage outside docker, please refer to https://github.com/huggingface/text-generation-inference
robrecht/ppo-Huggy
robrecht
2023-06-28T11:08:26Z
11
0
ml-agents
[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]
reinforcement-learning
2023-06-28T09:32:24Z
--- 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: robrecht/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
fatcat22/a2c-PandaReachDense-v2
fatcat22
2023-06-28T11:00:08Z
2
0
stable-baselines3
[ "stable-baselines3", "PandaReachDense-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T10:59:08Z
--- library_name: stable-baselines3 tags: - PandaReachDense-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: A2C results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: PandaReachDense-v2 type: PandaReachDense-v2 metrics: - type: mean_reward value: -0.70 +/- 0.20 name: mean_reward verified: false --- # **A2C** Agent playing **PandaReachDense-v2** This is a trained model of a **A2C** agent playing **PandaReachDense-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 ... ```
nayralabs/test
nayralabs
2023-06-28T10:51:33Z
0
0
diffusers
[ "diffusers", "code", "text-to-image", "en", "dataset:fka/awesome-chatgpt-prompts", "dataset:GAIR/lima", "arxiv:1910.09700", "license:bsd", "region:us" ]
text-to-image
2023-06-28T10:49:16Z
--- license: bsd datasets: - fka/awesome-chatgpt-prompts - GAIR/lima language: - en metrics: - accuracy library_name: diffusers pipeline_tag: text-to-image tags: - code --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
NickyNicky/MPT-7b-instruct-QLora-8Bits-Peft-train_eli5-1_Epoch-V7
NickyNicky
2023-06-28T10:50:38Z
5
0
peft
[ "peft", "region:us" ]
null
2023-06-28T10:50:35Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
BaoKien/albert_squadv2
BaoKien
2023-06-28T10:34:57Z
106
0
transformers
[ "transformers", "pytorch", "tensorboard", "albert", "question-answering", "generated_from_trainer", "dataset:squad_v2", "license:apache-2.0", "endpoints_compatible", "region:us" ]
question-answering
2023-06-28T09:52:52Z
--- license: apache-2.0 tags: - generated_from_trainer datasets: - squad_v2 model-index: - name: albert_squadv2 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. --> # albert_squadv2 This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the squad_v2 dataset. It achieves the following results on the evaluation set: - Loss: 4.1889 ## 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 | 5 | 4.7365 | | No log | 2.0 | 10 | 4.3391 | | No log | 3.0 | 15 | 4.1889 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
mnavas/bert-finetuned-token-reqsolvgencat
mnavas
2023-06-28T10:34:36Z
5
0
transformers
[ "transformers", "pytorch", "tensorboard", "bert", "token-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
token-classification
2023-06-28T09:43:30Z
--- license: apache-2.0 tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: beto-finetuned-token-reqsolvgencat 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. --> # beto-finetuned-token-reqsolvgencat This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.0573 - Precision: 0.1111 - Recall: 0.5 - F1: 0.1818 - Accuracy: 0.7765 ## 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: 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: 200 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.8551 | 1.0 | 3 | 1.1478 | 0.0 | 0.0 | 0.0 | 0.4696 | | 1.4354 | 2.0 | 6 | 0.7403 | 0.0 | 0.0 | 0.0 | 0.6088 | | 0.6532 | 3.0 | 9 | 0.6900 | 0.0 | 0.0 | 0.0 | 0.6010 | | 0.406 | 4.0 | 12 | 2.0318 | 0.0 | 0.0 | 0.0 | 0.5284 | | 1.3514 | 5.0 | 15 | 1.3364 | 0.0 | 0.0 | 0.0 | 0.6186 | | 0.419 | 6.0 | 18 | 0.9463 | 0.0 | 0.0 | 0.0 | 0.6 | | 0.4816 | 7.0 | 21 | 0.9409 | 0.0 | 0.0 | 0.0 | 0.6314 | | 0.8621 | 8.0 | 24 | 0.9034 | 0.0 | 0.0 | 0.0 | 0.7010 | | 0.2981 | 9.0 | 27 | 0.9617 | 0.0 | 0.0 | 0.0 | 0.6039 | | 0.5882 | 10.0 | 30 | 0.5289 | 0.0 | 0.0 | 0.0 | 0.8 | | 0.4327 | 11.0 | 33 | 0.6573 | 0.2 | 0.5 | 0.2857 | 0.7882 | | 0.2076 | 12.0 | 36 | 0.9207 | 0.0 | 0.0 | 0.0 | 0.6784 | | 0.1454 | 13.0 | 39 | 0.7729 | 0.0 | 0.0 | 0.0 | 0.7882 | | 0.2339 | 14.0 | 42 | 0.9067 | 0.0 | 0.0 | 0.0 | 0.7608 | | 0.2281 | 15.0 | 45 | 0.4732 | 0.0 | 0.0 | 0.0 | 0.7892 | | 0.1058 | 16.0 | 48 | 0.8219 | 0.0667 | 0.5 | 0.1176 | 0.7961 | | 0.0577 | 17.0 | 51 | 0.9698 | 0.1429 | 0.5 | 0.2222 | 0.8147 | | 0.0354 | 18.0 | 54 | 1.3158 | 0.0714 | 0.5 | 0.125 | 0.7549 | | 0.0258 | 19.0 | 57 | 2.2414 | 0.1667 | 0.5 | 0.25 | 0.6941 | | 0.0456 | 20.0 | 60 | 1.2596 | 0.0667 | 0.5 | 0.1176 | 0.7520 | | 0.0339 | 21.0 | 63 | 1.8941 | 0.1667 | 0.5 | 0.25 | 0.7069 | | 0.02 | 22.0 | 66 | 1.0201 | 0.1 | 0.5 | 0.1667 | 0.7941 | | 0.0257 | 23.0 | 69 | 1.4716 | 0.0909 | 0.5 | 0.1538 | 0.7716 | | 0.0148 | 24.0 | 72 | 2.6551 | 0.0 | 0.0 | 0.0 | 0.6853 | | 0.0257 | 25.0 | 75 | 1.7904 | 0.125 | 0.5 | 0.2 | 0.7324 | | 0.0183 | 26.0 | 78 | 2.2579 | 0.2 | 0.5 | 0.2857 | 0.7078 | | 0.0218 | 27.0 | 81 | 1.3332 | 0.1667 | 0.5 | 0.25 | 0.7137 | | 0.0148 | 28.0 | 84 | 0.7506 | 0.0769 | 0.5 | 0.1333 | 0.8696 | | 0.0081 | 29.0 | 87 | 2.2165 | 0.1667 | 0.5 | 0.25 | 0.7059 | | 0.0098 | 30.0 | 90 | 2.5291 | 0.2 | 0.5 | 0.2857 | 0.7 | | 0.0072 | 31.0 | 93 | 2.5877 | 0.25 | 0.5 | 0.3333 | 0.6990 | | 0.0162 | 32.0 | 96 | 2.7463 | 0.1667 | 0.5 | 0.25 | 0.6941 | | 0.0073 | 33.0 | 99 | 2.2100 | 0.1429 | 0.5 | 0.2222 | 0.7176 | | 0.0057 | 34.0 | 102 | 1.5509 | 0.0769 | 0.5 | 0.1333 | 0.7814 | | 0.0077 | 35.0 | 105 | 1.8449 | 0.1111 | 0.5 | 0.1818 | 0.7578 | | 0.0071 | 36.0 | 108 | 2.3808 | 0.3333 | 0.5 | 0.4 | 0.7127 | | 0.0063 | 37.0 | 111 | 1.1188 | 0.125 | 0.5 | 0.2 | 0.8598 | | 0.0067 | 38.0 | 114 | 1.7108 | 0.0 | 0.0 | 0.0 | 0.7892 | | 0.0063 | 39.0 | 117 | 1.8995 | 0.1 | 0.5 | 0.1667 | 0.7363 | | 0.0086 | 40.0 | 120 | 2.0472 | 0.1667 | 0.5 | 0.25 | 0.7137 | | 0.0028 | 41.0 | 123 | 1.8879 | 0.1111 | 0.5 | 0.1818 | 0.7245 | | 0.0084 | 42.0 | 126 | 1.9545 | 0.1667 | 0.5 | 0.25 | 0.7157 | | 0.0018 | 43.0 | 129 | 2.5274 | 0.0 | 0.0 | 0.0 | 0.6922 | | 0.0031 | 44.0 | 132 | 2.0330 | 0.0909 | 0.5 | 0.1538 | 0.7245 | | 0.0034 | 45.0 | 135 | 0.9381 | 0.1 | 0.5 | 0.1667 | 0.8569 | | 0.0016 | 46.0 | 138 | 0.6307 | 0.1111 | 0.5 | 0.1818 | 0.8980 | | 0.0011 | 47.0 | 141 | 0.7823 | 0.0667 | 0.5 | 0.1176 | 0.8676 | | 0.0021 | 48.0 | 144 | 1.1034 | 0.0909 | 0.5 | 0.1538 | 0.8373 | | 0.0025 | 49.0 | 147 | 1.4482 | 0.2 | 0.5 | 0.2857 | 0.8108 | | 0.0023 | 50.0 | 150 | 1.5541 | 0.1667 | 0.5 | 0.25 | 0.8069 | | 0.0007 | 51.0 | 153 | 1.7164 | 0.1667 | 0.5 | 0.25 | 0.8010 | | 0.0002 | 52.0 | 156 | 1.8291 | 0.1667 | 0.5 | 0.25 | 0.7941 | | 0.0002 | 53.0 | 159 | 1.8918 | 0.1429 | 0.5 | 0.2222 | 0.7892 | | 0.0016 | 54.0 | 162 | 1.8814 | 0.2 | 0.5 | 0.2857 | 0.7961 | | 0.0013 | 55.0 | 165 | 1.8920 | 0.1 | 0.5 | 0.1667 | 0.7873 | | 0.0009 | 56.0 | 168 | 1.8802 | 0.1 | 0.5 | 0.1667 | 0.7843 | | 0.0017 | 57.0 | 171 | 1.7839 | 0.1111 | 0.5 | 0.1818 | 0.8 | | 0.0028 | 58.0 | 174 | 1.7409 | 0.1 | 0.5 | 0.1667 | 0.7961 | | 0.0029 | 59.0 | 177 | 2.1381 | 0.1 | 0.5 | 0.1667 | 0.7196 | | 0.0008 | 60.0 | 180 | 2.4554 | 0.125 | 0.5 | 0.2 | 0.6922 | | 0.0012 | 61.0 | 183 | 2.7071 | 0.125 | 0.5 | 0.2 | 0.6676 | | 0.0011 | 62.0 | 186 | 2.5624 | 0.125 | 0.5 | 0.2 | 0.6814 | | 0.0009 | 63.0 | 189 | 2.1029 | 0.2 | 0.5 | 0.2857 | 0.7363 | | 0.0011 | 64.0 | 192 | 1.5984 | 0.125 | 0.5 | 0.2 | 0.7804 | | 0.0005 | 65.0 | 195 | 1.4155 | 0.0909 | 0.5 | 0.1538 | 0.8088 | | 0.001 | 66.0 | 198 | 1.3276 | 0.1111 | 0.5 | 0.1818 | 0.8225 | | 0.0002 | 67.0 | 201 | 1.2844 | 0.1429 | 0.5 | 0.2222 | 0.8255 | | 0.0076 | 68.0 | 204 | 1.2601 | 0.1667 | 0.5 | 0.25 | 0.8275 | | 0.0003 | 69.0 | 207 | 1.3359 | 0.1429 | 0.5 | 0.2222 | 0.8343 | | 0.0027 | 70.0 | 210 | 1.2452 | 0.25 | 0.5 | 0.3333 | 0.8363 | | 0.004 | 71.0 | 213 | 1.7228 | 0.1 | 0.5 | 0.1667 | 0.7775 | | 0.0004 | 72.0 | 216 | 2.7878 | 0.5 | 0.5 | 0.5 | 0.6804 | | 1.1257 | 73.0 | 219 | 2.5785 | 0.5 | 0.5 | 0.5 | 0.6804 | | 0.0209 | 74.0 | 222 | 0.1081 | 0.1111 | 0.5 | 0.1818 | 0.9775 | | 0.0486 | 75.0 | 225 | 1.5039 | 0.0667 | 0.5 | 0.1176 | 0.7784 | | 0.0012 | 76.0 | 228 | 3.2975 | 0.0 | 0.0 | 0.0 | 0.6098 | | 0.0929 | 77.0 | 231 | 2.4796 | 0.3333 | 0.5 | 0.4 | 0.6618 | | 0.0006 | 78.0 | 234 | 1.6117 | 0.125 | 0.5 | 0.2 | 0.7951 | | 0.0077 | 79.0 | 237 | 1.8651 | 0.125 | 0.5 | 0.2 | 0.7127 | | 0.0032 | 80.0 | 240 | 2.0187 | 0.1667 | 0.5 | 0.25 | 0.6873 | | 0.0007 | 81.0 | 243 | 1.9540 | 0.1 | 0.5 | 0.1667 | 0.6902 | | 0.0011 | 82.0 | 246 | 1.8161 | 0.0714 | 0.5 | 0.125 | 0.7275 | | 0.0009 | 83.0 | 249 | 1.7688 | 0.1111 | 0.5 | 0.1818 | 0.7657 | | 0.0006 | 84.0 | 252 | 1.7025 | 0.1667 | 0.5 | 0.25 | 0.7912 | | 0.0003 | 85.0 | 255 | 1.6924 | 0.2 | 0.5 | 0.2857 | 0.7980 | | 0.0004 | 86.0 | 258 | 1.7019 | 0.1667 | 0.5 | 0.25 | 0.7980 | | 0.0008 | 87.0 | 261 | 1.7386 | 0.2 | 0.5 | 0.2857 | 0.7971 | | 0.0002 | 88.0 | 264 | 1.7882 | 0.1667 | 0.5 | 0.25 | 0.7961 | | 0.0001 | 89.0 | 267 | 1.8405 | 0.0833 | 0.5 | 0.1429 | 0.7833 | | 0.0004 | 90.0 | 270 | 1.8319 | 0.125 | 0.5 | 0.2 | 0.7931 | | 0.0003 | 91.0 | 273 | 1.8520 | 0.125 | 0.5 | 0.2 | 0.7931 | | 0.0001 | 92.0 | 276 | 1.8876 | 0.0909 | 0.5 | 0.1538 | 0.7873 | | 0.0001 | 93.0 | 279 | 1.9220 | 0.1 | 0.5 | 0.1667 | 0.7814 | | 0.0004 | 94.0 | 282 | 2.0870 | 0.1 | 0.5 | 0.1667 | 0.7333 | | 0.0004 | 95.0 | 285 | 2.1469 | 0.1111 | 0.5 | 0.1818 | 0.7225 | | 0.0009 | 96.0 | 288 | 2.1726 | 0.1429 | 0.5 | 0.2222 | 0.7196 | | 0.0007 | 97.0 | 291 | 1.9247 | 0.1 | 0.5 | 0.1667 | 0.7667 | | 0.0012 | 98.0 | 294 | 1.8172 | 0.1111 | 0.5 | 0.1818 | 0.7902 | | 0.0002 | 99.0 | 297 | 1.7789 | 0.1 | 0.5 | 0.1667 | 0.7980 | | 0.0109 | 100.0 | 300 | 1.8386 | 0.0909 | 0.5 | 0.1538 | 0.7843 | | 0.0008 | 101.0 | 303 | 2.0800 | 0.1 | 0.5 | 0.1667 | 0.7314 | | 0.0002 | 102.0 | 306 | 2.5253 | 0.3333 | 0.5 | 0.4 | 0.6804 | | 0.001 | 103.0 | 309 | 2.2149 | 0.1 | 0.5 | 0.1667 | 0.7118 | | 0.0001 | 104.0 | 312 | 1.8607 | 0.1 | 0.5 | 0.1667 | 0.8020 | | 0.0002 | 105.0 | 315 | 1.7786 | 0.1 | 0.5 | 0.1667 | 0.8127 | | 0.0009 | 106.0 | 318 | 1.8432 | 0.125 | 0.5 | 0.2 | 0.8078 | | 0.0001 | 107.0 | 321 | 2.0339 | 0.1111 | 0.5 | 0.1818 | 0.7784 | | 0.0001 | 108.0 | 324 | 2.2628 | 0.0769 | 0.5 | 0.1333 | 0.7392 | | 0.0007 | 109.0 | 327 | 2.3649 | 0.0714 | 0.5 | 0.125 | 0.7265 | | 0.0001 | 110.0 | 330 | 2.4330 | 0.0714 | 0.5 | 0.125 | 0.7137 | | 0.0001 | 111.0 | 333 | 2.4918 | 0.1 | 0.5 | 0.1667 | 0.7059 | | 0.0002 | 112.0 | 336 | 2.2853 | 0.0909 | 0.5 | 0.1538 | 0.7647 | | 0.0001 | 113.0 | 339 | 2.1945 | 0.1 | 0.5 | 0.1667 | 0.7765 | | 0.0001 | 114.0 | 342 | 2.1446 | 0.1111 | 0.5 | 0.1818 | 0.7824 | | 0.0008 | 115.0 | 345 | 2.1037 | 0.1111 | 0.5 | 0.1818 | 0.7863 | | 0.0001 | 116.0 | 348 | 2.0753 | 0.1 | 0.5 | 0.1667 | 0.7902 | | 0.0001 | 117.0 | 351 | 2.0617 | 0.1 | 0.5 | 0.1667 | 0.7902 | | 0.0014 | 118.0 | 354 | 1.9908 | 0.1111 | 0.5 | 0.1818 | 0.7961 | | 0.0009 | 119.0 | 357 | 1.9134 | 0.1111 | 0.5 | 0.1818 | 0.8 | | 0.0009 | 120.0 | 360 | 1.8651 | 0.1111 | 0.5 | 0.1818 | 0.8020 | | 0.0002 | 121.0 | 363 | 1.8480 | 0.1111 | 0.5 | 0.1818 | 0.8 | | 0.0001 | 122.0 | 366 | 1.8558 | 0.0909 | 0.5 | 0.1538 | 0.7961 | | 0.0001 | 123.0 | 369 | 1.8727 | 0.1111 | 0.5 | 0.1818 | 0.7892 | | 0.0001 | 124.0 | 372 | 1.8951 | 0.125 | 0.5 | 0.2 | 0.7863 | | 0.0007 | 125.0 | 375 | 1.8971 | 0.1667 | 0.5 | 0.25 | 0.7833 | | 0.0011 | 126.0 | 378 | 1.8479 | 0.1667 | 0.5 | 0.25 | 0.7814 | | 0.0002 | 127.0 | 381 | 1.7985 | 0.1429 | 0.5 | 0.2222 | 0.7804 | | 0.0001 | 128.0 | 384 | 1.7712 | 0.125 | 0.5 | 0.2 | 0.7794 | | 0.0001 | 129.0 | 387 | 1.7929 | 0.1111 | 0.5 | 0.1818 | 0.7755 | | 0.0002 | 130.0 | 390 | 1.8551 | 0.1111 | 0.5 | 0.1818 | 0.7725 | | 0.0001 | 131.0 | 393 | 1.9030 | 0.125 | 0.5 | 0.2 | 0.7716 | | 0.0001 | 132.0 | 396 | 1.9421 | 0.125 | 0.5 | 0.2 | 0.7686 | | 0.0009 | 133.0 | 399 | 1.9440 | 0.125 | 0.5 | 0.2 | 0.7686 | | 0.0001 | 134.0 | 402 | 1.9455 | 0.125 | 0.5 | 0.2 | 0.7686 | | 0.0001 | 135.0 | 405 | 1.9527 | 0.125 | 0.5 | 0.2 | 0.7686 | | 0.0004 | 136.0 | 408 | 1.9493 | 0.125 | 0.5 | 0.2 | 0.7706 | | 0.0001 | 137.0 | 411 | 1.9432 | 0.125 | 0.5 | 0.2 | 0.7706 | | 0.0001 | 138.0 | 414 | 1.9491 | 0.125 | 0.5 | 0.2 | 0.7706 | | 0.0002 | 139.0 | 417 | 1.9434 | 0.1 | 0.5 | 0.1667 | 0.7735 | | 0.0006 | 140.0 | 420 | 1.9363 | 0.1111 | 0.5 | 0.1818 | 0.7784 | | 0.0001 | 141.0 | 423 | 1.9330 | 0.1111 | 0.5 | 0.1818 | 0.7804 | | 0.0001 | 142.0 | 426 | 1.9334 | 0.1111 | 0.5 | 0.1818 | 0.7833 | | 0.0001 | 143.0 | 429 | 1.9366 | 0.125 | 0.5 | 0.2 | 0.7843 | | 0.0001 | 144.0 | 432 | 1.9417 | 0.1111 | 0.5 | 0.1818 | 0.7843 | | 0.0001 | 145.0 | 435 | 1.9467 | 0.1111 | 0.5 | 0.1818 | 0.7843 | | 0.0001 | 146.0 | 438 | 1.9518 | 0.1111 | 0.5 | 0.1818 | 0.7843 | | 0.0001 | 147.0 | 441 | 1.9574 | 0.1111 | 0.5 | 0.1818 | 0.7853 | | 0.0001 | 148.0 | 444 | 1.9635 | 0.1111 | 0.5 | 0.1818 | 0.7853 | | 0.0003 | 149.0 | 447 | 1.9643 | 0.1111 | 0.5 | 0.1818 | 0.7853 | | 0.0001 | 150.0 | 450 | 1.9664 | 0.125 | 0.5 | 0.2 | 0.7853 | | 0.0008 | 151.0 | 453 | 1.9830 | 0.125 | 0.5 | 0.2 | 0.7843 | | 0.0001 | 152.0 | 456 | 1.9974 | 0.125 | 0.5 | 0.2 | 0.7824 | | 0.0001 | 153.0 | 459 | 2.0083 | 0.125 | 0.5 | 0.2 | 0.7824 | | 0.0007 | 154.0 | 462 | 2.0066 | 0.1111 | 0.5 | 0.1818 | 0.7833 | | 0.0001 | 155.0 | 465 | 2.0047 | 0.1111 | 0.5 | 0.1818 | 0.7833 | | 0.0001 | 156.0 | 468 | 2.0042 | 0.1111 | 0.5 | 0.1818 | 0.7833 | | 0.0001 | 157.0 | 471 | 2.0075 | 0.1111 | 0.5 | 0.1818 | 0.7833 | | 0.0008 | 158.0 | 474 | 2.0217 | 0.1111 | 0.5 | 0.1818 | 0.7824 | | 0.0001 | 159.0 | 477 | 2.0326 | 0.125 | 0.5 | 0.2 | 0.7814 | | 0.0001 | 160.0 | 480 | 2.0422 | 0.125 | 0.5 | 0.2 | 0.7814 | | 0.0001 | 161.0 | 483 | 2.0493 | 0.125 | 0.5 | 0.2 | 0.7804 | | 0.0001 | 162.0 | 486 | 2.0568 | 0.125 | 0.5 | 0.2 | 0.7804 | | 0.0002 | 163.0 | 489 | 2.0818 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0001 | 164.0 | 492 | 2.0997 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0001 | 165.0 | 495 | 2.1127 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 166.0 | 498 | 2.1226 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 167.0 | 501 | 2.1311 | 0.1111 | 0.5 | 0.1818 | 0.7716 | | 0.0001 | 168.0 | 504 | 2.1377 | 0.1111 | 0.5 | 0.1818 | 0.7716 | | 0.0003 | 169.0 | 507 | 2.1296 | 0.1111 | 0.5 | 0.1818 | 0.7716 | | 0.0001 | 170.0 | 510 | 2.1180 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0 | 171.0 | 513 | 2.1095 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0 | 172.0 | 516 | 2.1035 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 173.0 | 519 | 2.0999 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0 | 174.0 | 522 | 2.0984 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0004 | 175.0 | 525 | 2.0930 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0 | 176.0 | 528 | 2.0874 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.006 | 177.0 | 531 | 2.0807 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0001 | 178.0 | 534 | 2.0717 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0001 | 179.0 | 537 | 2.0721 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0001 | 180.0 | 540 | 2.0731 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.001 | 181.0 | 543 | 2.0712 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 182.0 | 546 | 2.0700 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 183.0 | 549 | 2.0692 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 184.0 | 552 | 2.0622 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0006 | 185.0 | 555 | 2.0582 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0001 | 186.0 | 558 | 2.0564 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0001 | 187.0 | 561 | 2.0562 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 188.0 | 564 | 2.0571 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 189.0 | 567 | 2.0587 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 190.0 | 570 | 2.0597 | 0.1111 | 0.5 | 0.1818 | 0.7735 | | 0.0041 | 191.0 | 573 | 2.0555 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0002 | 192.0 | 576 | 2.0473 | 0.1111 | 0.5 | 0.1818 | 0.7765 | | 0.0001 | 193.0 | 579 | 2.0480 | 0.1111 | 0.5 | 0.1818 | 0.7765 | | 0.0002 | 194.0 | 582 | 2.0507 | 0.1111 | 0.5 | 0.1818 | 0.7765 | | 0.0001 | 195.0 | 585 | 2.0541 | 0.1111 | 0.5 | 0.1818 | 0.7765 | | 0.0001 | 196.0 | 588 | 2.0562 | 0.1111 | 0.5 | 0.1818 | 0.7765 | | 0.0001 | 197.0 | 591 | 2.0586 | 0.1111 | 0.5 | 0.1818 | 0.7765 | | 0.0001 | 198.0 | 594 | 2.0596 | 0.1111 | 0.5 | 0.1818 | 0.7765 | | 0.0001 | 199.0 | 597 | 2.0604 | 0.1111 | 0.5 | 0.1818 | 0.7765 | | 0.0003 | 200.0 | 600 | 2.0573 | 0.1111 | 0.5 | 0.1818 | 0.7765 | ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.0 - Datasets 2.1.0 - Tokenizers 0.13.3
Tri1/12-18-finetuned-eng-to-para
Tri1
2023-06-28T10:34:13Z
22
0
transformers
[ "transformers", "pytorch", "tensorboard", "marian", "text2text-generation", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text2text-generation
2023-06-27T16:09:01Z
--- license: apache-2.0 tags: - generated_from_trainer metrics: - bleu model-index: - name: 12-18-finetuned-eng-to-para 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. --> # 12-18-finetuned-eng-to-para This model is a fine-tuned version of [Tri1/6-12-finetuned-eng-to-para](https://huggingface.co/Tri1/6-12-finetuned-eng-to-para) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0339 - Bleu: 35.7233 - Gen Len: 22.56 ## 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: 6 ### Training results | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:| | 0.0441 | 1.0 | 6250 | 0.0420 | 31.1327 | 22.08 | | 0.0412 | 2.0 | 12500 | 0.0397 | 32.419 | 22.72 | | 0.0396 | 3.0 | 18750 | 0.0371 | 35.4708 | 20.96 | | 0.0385 | 4.0 | 25000 | 0.0356 | 34.6037 | 21.12 | | 0.0377 | 5.0 | 31250 | 0.0343 | 35.7663 | 22.24 | | 0.0381 | 6.0 | 37500 | 0.0339 | 35.7233 | 22.56 | ### Framework versions - Transformers 4.30.1 - Pytorch 2.0.0 - Datasets 2.1.0 - Tokenizers 0.13.3
NasimB/gpt2-dp-cl-length
NasimB
2023-06-28T10:24:24Z
4
0
transformers
[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-28T07:55:52Z
--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: gpt2-dp-cl-length 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. --> # gpt2-dp-cl-length This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 4.7161 ## 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: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 7 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 6.6691 | 0.26 | 500 | 5.8270 | | 5.2775 | 0.53 | 1000 | 5.4588 | | 4.9444 | 0.79 | 1500 | 5.2410 | | 4.7094 | 1.05 | 2000 | 5.1417 | | 4.5245 | 1.31 | 2500 | 4.9932 | | 4.4306 | 1.58 | 3000 | 4.9406 | | 4.3594 | 1.84 | 3500 | 4.9073 | | 4.2194 | 2.1 | 4000 | 4.8631 | | 4.0996 | 2.36 | 4500 | 4.8316 | | 4.0865 | 2.63 | 5000 | 4.7686 | | 4.05 | 2.89 | 5500 | 4.7494 | | 3.8858 | 3.15 | 6000 | 4.7704 | | 3.814 | 3.42 | 6500 | 4.6998 | | 3.8032 | 3.68 | 7000 | 4.6793 | | 3.7885 | 3.94 | 7500 | 4.6676 | | 3.5761 | 4.2 | 8000 | 4.6765 | | 3.5336 | 4.47 | 8500 | 4.6792 | | 3.535 | 4.73 | 9000 | 4.6749 | | 3.5307 | 4.99 | 9500 | 4.6553 | | 3.2929 | 5.25 | 10000 | 4.7027 | | 3.2874 | 5.52 | 10500 | 4.6926 | | 3.2883 | 5.78 | 11000 | 4.6927 | | 3.2606 | 6.04 | 11500 | 4.7025 | | 3.1356 | 6.31 | 12000 | 4.7098 | | 3.1392 | 6.57 | 12500 | 4.7123 | | 3.1374 | 6.83 | 13000 | 4.7161 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3
steveglover/falcon-7b-instruct-telco-texttonest
steveglover
2023-06-28T10:22:59Z
4
0
adapter-transformers
[ "adapter-transformers", "RefinedWebModel", "text-generation", "en", "region:us" ]
text-generation
2023-06-27T13:05:32Z
--- language: - en pipeline_tag: text-generation library_name: adapter-transformers ---
YakovElm/Qt_10_BERT_Under_Sampling
YakovElm
2023-06-28T10:22:56Z
61
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T10:22:21Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Qt_10_BERT_Under_Sampling 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. --> # Qt_10_BERT_Under_Sampling 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: 0.0001 - Train Accuracy: 1.0 - Validation Loss: 0.5572 - Validation Accuracy: 0.9416 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.0351 | 0.9905 | 0.4427 | 0.9416 | 0 | | 0.0003 | 1.0 | 0.5263 | 0.9416 | 1 | | 0.0001 | 1.0 | 0.5572 | 0.9416 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
rawkul/q.taxi.v3
rawkul
2023-06-28T10:20:40Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T09:44:41Z
--- 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 ```python model = load_from_hub(repo_id="rawkul/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"]) ```
KamilAin/bart-base-booksum
KamilAin
2023-06-28T10:19:50Z
129
1
transformers
[ "transformers", "pytorch", "safetensors", "bart", "text2text-generation", "booksum", "summary", "summarization", "book", "en", "dataset:kmfoda/booksum", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
summarization
2022-05-23T13:46:59Z
--- language: en license: apache-2.0 tags: - booksum - summary - summarization - book metrics: - rouge widget: - text: "In the dead night, Frodo lay in a dream without light. Then he saw the young moon rising; under its thin light there loomed before him a black wall of rock, pierced by a dark arch like a great gate. It seemed to Frodo that he was lifted up, and passing over he saw that the rock-wall was a circle of hills, and that within it was a plain, and in the midst of the plain stood a pinnacle of stone, like a vast tower but not made by hands. On its top stood the figure of a man. The moon as it rose seemed to hang for a moment above his head and glistened in his white hair as the wind stirred it. Up from the dark plain below came the crying of fell voices, and the howling of many wolves. Suddenly a shadow, like the shape of great wings, passed across the moon. The figure lifted his arms and a light flashed from the staff that he wielded. A mighty eagle swept down and bore him away. The voices wailed and the wolves yammered. There was a noise like a strong wind blowing, and on it was borne the sound of hoofs, galloping, galloping, galloping from the East. ‘Black Riders!’ thought Frodo as he wakened, with the sound of the hoofs still echoing in his mind. He wondered if he would ever again have the courage to leave the safety of these stone walls. He lay motionless, still listening; but all was now silent, and at last he turned and fell asleep again or wandered into some other unremembered dream." example_title: "book example" datasets: - kmfoda/booksum --- # BART-base-Booksum This is a BART-base model fine-tuned on a BookSum dataset - **Use cases:** book summarization, general text summarization. - This is a [`https://huggingface.co/facebook/bart-base`](https://huggingface.co/facebook/bart-base), fine-tuned for five epochs
NickyNicky/MPT-7b-instruct-QLora-8Bits-Peft-train_eli5-1_Epoch-V5
NickyNicky
2023-06-28T10:19:47Z
2
0
peft
[ "peft", "region:us" ]
null
2023-06-28T10:19:42Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
jondurbin/airoboros-13b-gpt4-1.4
jondurbin
2023-06-28T10:16:55Z
1,435
19
transformers
[ "transformers", "pytorch", "llama", "text-generation", "dataset:jondurbin/airoboros-gpt4-1.4", "license:cc-by-nc-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-21T21:24:00Z
--- license: cc-by-nc-4.0 datasets: - jondurbin/airoboros-gpt4-1.4 --- __update 2023-06-25 - re-uploaded with a slightly earlier checkpoint, which seems perhaps a little less overfit than the full 3-epochs version initially uploaded__ ## Overview This is a __full__ (not qlora) fine-tune 13b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros This is mostly an extension of the previous gpt-4 series, with a few extras: * fixed (+ more examples of) multi-character, multi-turn conversations * coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed * more roleplay examples * jokes * riddles * all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT) This model was fine-tuned with a fork of [FastChat](https://github.com/jondurbin/FastChat) The prompt it was trained with was: ``` A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT: ``` So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon). ## Usage To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors. ``` pip install git+https://github.com/jondurbin/FastChat ``` Be sure you are pulling the latest branch! Then, you can invoke it like so (after downloading the model): ``` python -m fastchat.serve.cli \ --model-path airoboros-13b-gpt4-1.4 \ --temperature 0.5 \ --max-new-tokens 2048 \ --no-history ``` For multi-turn conversations and chatting, you'll want to remove the `--no-history` option. ### 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 url: https://some.web.site/123 date: 2023-06-01 ... 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 ``` The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described: ``` USER: 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 ASSISTANT: ``` ### Coding You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt): ``` 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: ``` 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 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 ``` ### Word games / trivia ``` USER: This anagram of "silent" is what you do when paying attention and hearing someone. ASSISTANT: listen ``` ``` USER: Give me a list of 7 words that start with EN ASSISTANT: 1. Endlessly 2. Enthusiastically 3. Enormously 4. Enveloping 5. Enduring 6. Enlightening 7. Encouraging ``` ### Multiple choice ``` USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt? A) Mercury B) Venus C) Pluto D) Jupiter ASSISTANT: C, Pluto ``` ### Writing <details> <summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary> Response: ``` ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home. Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes. No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice. So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary> ``` </details> ### Jokes ``` USER: Tell me a joke about bananas. ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E. ``` ### Riddles (not great, but slightly better) ``` USER: What has a neck but no head? ASSISTANT: A bottle. ``` ### Multi-character conversations ``` USER: Characters: - Yoda, the ever clever jedi master. - Homer Simpson, you know, the goofy yellow guy. - USER/Jon - don't generate any speech or actions on behalf of Jon Rules: - be sure to use the manerisms and speaking style of the characters correctly - surround character actions with asterisks - always put quotes around words spoken by the characters - use a new line for each character's actions or speech - always prefix actions/speech with the character's name and colon - only generate text and actions on behalf of Yoda or Homer, and never anyone else Conversation will revolve around the grapes, in a local cafe with delicious coffee. Generate a single interaction between Yoda and Homer to start, with one sentence each. ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer." Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!" USER: *enters the cafe* Sorry I'm late guys! ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes." Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!" *Yoda raises an eyebrow* ``` ### Usage and License Notices All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because: - the base model is LLaMa, which has it's own special research license - the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai So, to reiterate: this model (and datasets) cannot be used commercially.
jondurbin/airoboros-7b-gpt4-1.4
jondurbin
2023-06-28T10:16:41Z
1,427
8
transformers
[ "transformers", "pytorch", "llama", "text-generation", "dataset:jondurbin/airoboros-gpt4-1.4", "license:cc-by-nc-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-22T00:22:59Z
--- license: cc-by-nc-4.0 datasets: - jondurbin/airoboros-gpt4-1.4 --- __mostly untested, use if you want, or wait for some validation__ ## Overview This is a __full__ (not qlora) fine-tune 7b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros This is mostly an extension of the previous gpt-4 series, with a few extras: * fixed (+ more examples of) multi-character, multi-turn conversations * coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed * more roleplay examples * jokes * riddles * all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT) This model was fine-tuned with a fork of [FastChat](https://github.com/jondurbin/FastChat) The prompt it was trained with was: ``` A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT: ``` So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon). ## Usage To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors. ``` pip install git+https://github.com/jondurbin/FastChat ``` Be sure you are pulling the latest branch! Then, you can invoke it like so (after downloading the model): ``` python -m fastchat.serve.cli \ --model-path airoboros-7b-gpt4-1.4 \ --temperature 0.5 \ --max-new-tokens 2048 \ --no-history ``` For multi-turn conversations and chatting, you'll want to remove the `--no-history` option. ### 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 url: https://some.web.site/123 date: 2023-06-01 ... 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 ``` The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described: ``` USER: 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 ASSISTANT: ``` ### Coding You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt): ``` 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: ``` 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 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 ``` ### Word games / trivia ``` USER: This anagram of "silent" is what you do when paying attention and hearing someone. ASSISTANT: listen ``` ``` USER: Give me a list of 7 words that start with EN ASSISTANT: 1. Endlessly 2. Enthusiastically 3. Enormously 4. Enveloping 5. Enduring 6. Enlightening 7. Encouraging ``` ### Multiple choice ``` USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt? A) Mercury B) Venus C) Pluto D) Jupiter ASSISTANT: C, Pluto ``` ### Writing <details> <summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary> Response: ``` ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home. Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes. No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice. So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary> ``` </details> ### Jokes ``` USER: Tell me a joke about bananas. ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E. ``` ### Riddles (not great, but slightly better) ``` USER: What has a neck but no head? ASSISTANT: A bottle. ``` ### Multi-character conversations ``` USER: Characters: - Yoda, the ever clever jedi master. - Homer Simpson, you know, the goofy yellow guy. - USER/Jon - don't generate any speech or actions on behalf of Jon Rules: - be sure to use the manerisms and speaking style of the characters correctly - surround character actions with asterisks - always put quotes around words spoken by the characters - use a new line for each character's actions or speech - always prefix actions/speech with the character's name and colon - only generate text and actions on behalf of Yoda or Homer, and never anyone else Conversation will revolve around the grapes, in a local cafe with delicious coffee. Generate a single interaction between Yoda and Homer to start, with one sentence each. ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer." Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!" USER: *enters the cafe* Sorry I'm late guys! ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes." Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!" *Yoda raises an eyebrow* ``` ### Usage and License Notices All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because: - the base model is LLaMa, which has it's own special research license - the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai So, to reiterate: this model (and datasets) cannot be used commercially.
hyeongjin99/swin-tiny-patch4-window7-224-finetuned-eurosat
hyeongjin99
2023-06-28T10:06:07Z
209
0
transformers
[ "transformers", "pytorch", "tensorboard", "swin", "image-classification", "generated_from_trainer", "dataset:imagefolder", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
image-classification
2023-06-28T07:18:40Z
--- license: apache-2.0 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: swin-tiny-patch4-window7-224-finetuned-eurosat results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.9807407407407407 --- <!-- 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. --> # swin-tiny-patch4-window7-224-finetuned-eurosat This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.0617 - Accuracy: 0.9807 ## 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: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.2385 | 1.0 | 190 | 0.1160 | 0.9622 | | 0.1686 | 2.0 | 380 | 0.0769 | 0.9737 | | 0.1247 | 3.0 | 570 | 0.0617 | 0.9807 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
jmjpickard/test-model
jmjpickard
2023-06-28T10:03:21Z
5
0
sentence-transformers
[ "sentence-transformers", "pytorch", "mpnet", "setfit", "text-classification", "arxiv:2209.11055", "license:apache-2.0", "region:us" ]
text-classification
2023-06-28T10:00:00Z
--- license: apache-2.0 tags: - setfit - sentence-transformers - text-classification pipeline_tag: text-classification --- # /var/folders/p2/9pl12g015n18blt1xbr70qww0000gn/T/tmp6j9vcf6u/jmjpickard/test-model This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. ## Usage To use this model for inference, first install the SetFit library: ```bash python -m pip install setfit ``` You can then run inference as follows: ```python from setfit import SetFitModel # Download from Hub and run inference model = SetFitModel.from_pretrained("/var/folders/p2/9pl12g015n18blt1xbr70qww0000gn/T/tmp6j9vcf6u/jmjpickard/test-model") # Run inference preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"]) ``` ## BibTeX entry and citation info ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ```
vkoriukina/ppo-LunarLander-v2
vkoriukina
2023-06-28T10:01:31Z
0
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T10:01:12Z
--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 237.68 +/- 27.59 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
dev-senolys/camembert_base_finetunned_one_thema_balanced_5_epochs
dev-senolys
2023-06-28T10:00:36Z
105
0
transformers
[ "transformers", "pytorch", "tensorboard", "camembert", "text-classification", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T08:45:28Z
--- license: mit tags: - generated_from_trainer model-index: - name: camembert_base_finetunned_one_thema_balanced_5_epochs 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. --> # camembert_base_finetunned_one_thema_balanced_5_epochs This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.7778 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | No log | 1.0 | 116 | 2.3340 | | No log | 2.0 | 232 | 2.0439 | | No log | 3.0 | 348 | 1.8438 | | No log | 4.0 | 464 | 1.8124 | | 1.9931 | 5.0 | 580 | 1.7778 | ### Framework versions - Transformers 4.29.2 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
KYac/falcon-finetuned
KYac
2023-06-28T09:50:17Z
1
0
peft
[ "peft", "region:us" ]
null
2023-06-28T09:50:14Z
--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0
Zhibinhong/checkpoints_new
Zhibinhong
2023-06-28T09:45:08Z
1
0
diffusers
[ "diffusers", "tensorboard", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "dreambooth", "base_model:runwayml/stable-diffusion-v1-5", "base_model:finetune:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]
text-to-image
2023-06-28T09:03:53Z
--- license: creativeml-openrail-m base_model: runwayml/stable-diffusion-v1-5 instance_prompt: a photo of sks dog tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - dreambooth inference: true --- # DreamBooth - Zhibinhong/checkpoints_new This is a dreambooth model derived from runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. DreamBooth for the text encoder was enabled: False.
KorinYTUK/JTTS.v1
KorinYTUK
2023-06-28T09:42:19Z
0
0
null
[ "text-to-speech", "en", "license:openrail", "region:us" ]
text-to-speech
2023-06-28T09:41:16Z
--- license: openrail language: - en pipeline_tag: text-to-speech ---
Den4ikAI/rut5_base_squad_interpreted
Den4ikAI
2023-06-28T09:37:01Z
98
0
transformers
[ "transformers", "pytorch", "safetensors", "t5", "text2text-generation", "ru", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text2text-generation
2022-12-23T08:32:54Z
--- license: mit language: - ru widget: - "Напиши 'Не знаю', если нет ответа. [КОНТЕКСТ] Ёлка горит огоньками, а под ней лежат подарки. У Дениса сегодня дискотека. Он любит есть пиццу. Машенька любит танцевать. [ВОПРОС] Где находятся подарки?" --- sberbank-ai/ruT5-base обученная на интерпретированом датасета squad. Модель умеет раскрывать кореферентность.
rawkul/q-FrozenLake-v1-4x4-noSlippery
rawkul
2023-06-28T09:26:09Z
0
0
null
[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T09:26:06Z
--- 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="rawkul/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"]) ```
Nara-Lab/nallm-polyglot-ko-3.8b-base
Nara-Lab
2023-06-28T09:24:35Z
2,251
3
transformers
[ "transformers", "pytorch", "gpt_neox", "text-generation", "ko", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-23T01:35:24Z
--- license: mit language: - ko --- NA-LLM(나름)은 나라지식정보가 개발한 한국어 Large Language Model (LLM) 입니다. https://github.com/Nara-Information/NA-LLM
Nara-Lab/nallm-polyglot-ko-1.3b-base
Nara-Lab
2023-06-28T09:24:15Z
2,272
2
transformers
[ "transformers", "pytorch", "gpt_neox", "text-generation", "ko", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-22T01:12:03Z
--- license: mit language: - ko --- NA-LLM(나름)은 나라지식정보가 개발한 한국어 Large Language Model (LLM) 입니다. https://github.com/Nara-Information/NA-LLM
BerserkerMother/PG-CartPole-V1
BerserkerMother
2023-06-28T09:12:09Z
0
0
null
[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T09:10:03Z
--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: PG-CartPole-V1 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 901.90 +/- 294.30 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
YakovElm/Qt_5_BERT_Under_Sampling
YakovElm
2023-06-28T09:10:13Z
3
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T09:09:37Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Qt_5_BERT_Under_Sampling 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. --> # Qt_5_BERT_Under_Sampling 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: 0.0002 - Train Accuracy: 1.0 - Validation Loss: 0.6539 - Validation Accuracy: 0.9294 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.0258 | 0.9970 | 0.5547 | 0.9294 | 0 | | 0.0003 | 1.0 | 0.6157 | 0.9294 | 1 | | 0.0002 | 1.0 | 0.6539 | 0.9294 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
hztang/BART-large-base-custom
hztang
2023-06-28T08:57:46Z
103
0
transformers
[ "transformers", "pytorch", "bart", "text2text-generation", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text2text-generation
2023-06-28T01:48:16Z
--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: BART-large-base-custom 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-base-custom This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) 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: 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: 1 ### Training results | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| | No log | 1.0 | 238 | 0.6719 | 24.2424 | 19.2095 | 23.2835 | 23.9833 | 20.0 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.12.1 - Datasets 2.13.1 - Tokenizers 0.11.0
dev-senolys/camembert_base_finetunned_one_thema_balanced_4_epochs
dev-senolys
2023-06-28T08:44:06Z
108
0
transformers
[ "transformers", "pytorch", "tensorboard", "camembert", "text-classification", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T07:43:11Z
--- license: mit tags: - generated_from_trainer model-index: - name: camembert_base_finetunned_one_thema_balanced_4_epochs 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. --> # camembert_base_finetunned_one_thema_balanced_4_epochs This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.8441 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 4 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | No log | 1.0 | 116 | 2.2913 | | No log | 2.0 | 232 | 2.0685 | | No log | 3.0 | 348 | 1.8928 | | No log | 4.0 | 464 | 1.8441 | ### Framework versions - Transformers 4.29.2 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
cupcakeDriveby/q-taxi-v3
cupcakeDriveby
2023-06-28T08:39:16Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T08:39:14Z
--- 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: 7.52 +/- 2.74 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="cupcakeDriveby/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"]) ```
lukaszkolodziejczyk/ppo-Huggy
lukaszkolodziejczyk
2023-06-28T08:39:14Z
98
0
ml-agents
[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]
reinforcement-learning
2023-06-28T08:39:09Z
--- 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: lukaszkolodziejczyk/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
PhilSad/poca-SoccerTwos
PhilSad
2023-06-28T08:36:16Z
2
0
ml-agents
[ "ml-agents", "onnx", "SoccerTwos", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SoccerTwos", "region:us" ]
reinforcement-learning
2023-06-28T08:10:30Z
--- 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: PhilSad/poca-SoccerTwos 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
padmajabfrl/Religion-Classification-Custom-Model
padmajabfrl
2023-06-28T08:35:16Z
26
0
transformers
[ "transformers", "pytorch", "tensorboard", "distilbert", "text-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T06:34:07Z
--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: Religion-Classification-Custom-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. --> # Religion-Classification-Custom-Model This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0009 - Accuracy: 0.9999 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:| | 0.0141 | 1.0 | 5102 | 0.0026 | 0.9995 | | 0.0033 | 2.0 | 10204 | 0.0015 | 0.9996 | | 0.0024 | 3.0 | 15306 | 0.0021 | 0.9996 | | 0.0005 | 4.0 | 20408 | 0.0007 | 0.9999 | | 0.0013 | 5.0 | 25510 | 0.0009 | 0.9999 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
yhna/Reinforce-policy-grad-cartpole
yhna
2023-06-28T08:35:03Z
0
0
null
[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T04:29:48Z
--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-policy-grad-cartpole results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 500.00 +/- 0.00 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
mszpro/CoreML_StableDiffusion-v-1-5_ControlledUnet_SplitEinsum
mszpro
2023-06-28T08:17:12Z
0
0
null
[ "region:us" ]
null
2023-06-28T08:13:17Z
# Stable Diffusion 1.5 ControlledUnet file for CoreML This is the compiled ControlledUNet file of Stable Diffusion 1.5, used for CoreML image generation with ControlNet. It accepts 12 additional_residual inputs. This is compiled for SPLIT EINSUM, which means it also works for iPhone and iPad using Apple Neural Engine.
Yorth/dolly-lora
Yorth
2023-06-28T08:07:48Z
2
0
peft
[ "peft", "region:us" ]
null
2023-06-28T08:07:46Z
--- library_name: peft --- ## 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.dev0
YakovElm/MariaDB_20_BERT_Under_Sampling
YakovElm
2023-06-28T07:59:13Z
61
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T07:58:38Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: MariaDB_20_BERT_Under_Sampling 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. --> # MariaDB_20_BERT_Under_Sampling 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: 0.0008 - Train Accuracy: 1.0 - Validation Loss: 0.2337 - Validation Accuracy: 0.9698 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.0627 | 0.9992 | 0.1862 | 0.9698 | 0 | | 0.0016 | 1.0 | 0.2186 | 0.9698 | 1 | | 0.0008 | 1.0 | 0.2337 | 0.9698 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
OverShifted/ppo-LunarLander-v2
OverShifted
2023-06-28T07:48:00Z
0
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T07:47:36Z
--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 230.07 +/- 24.56 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
Broonion/RLcourse-unit2-Taxi-V3
Broonion
2023-06-28T07:40:07Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T07:30:55Z
--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: RLcourse-unit2-Taxi-V3 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.48 +/- 2.74 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="Broonion/RLcourse-unit2-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"]) ```
Assem-Ihab/trainingthemodel
Assem-Ihab
2023-06-28T07:34:52Z
94
0
transformers
[ "transformers", "pytorch", "tensorboard", "mbart", "text2text-generation", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text2text-generation
2023-06-27T12:21:59Z
--- license: apache-2.0 tags: - generated_from_trainer metrics: - rouge model-index: - name: trainingthemodel 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. --> # trainingthemodel This model is a fine-tuned version of [abdalrahmanshahrour/arabartsummarization](https://huggingface.co/abdalrahmanshahrour/arabartsummarization) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.2622 - Rouge1: 0.1194 - Rouge2: 0.0483 - Rougel: 0.0975 - Rougelsum: 0.0977 - Gen Len: 20.0 ## 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: 2e-05 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 4 ### Training results | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| | No log | 1.0 | 154 | 2.7120 | 0.1178 | 0.0452 | 0.0966 | 0.0966 | 20.0 | | No log | 2.0 | 308 | 2.4175 | 0.1202 | 0.0482 | 0.0995 | 0.0998 | 20.0 | | No log | 3.0 | 462 | 2.3151 | 0.1181 | 0.0468 | 0.0963 | 0.0966 | 20.0 | | 3.034 | 4.0 | 616 | 2.2622 | 0.1194 | 0.0483 | 0.0975 | 0.0977 | 20.0 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
YakovElm/MariaDB_15_BERT_Under_Sampling
YakovElm
2023-06-28T07:34:27Z
61
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T07:33:52Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: MariaDB_15_BERT_Under_Sampling 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. --> # MariaDB_15_BERT_Under_Sampling 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: 0.0009 - Train Accuracy: 1.0 - Validation Loss: 0.3045 - Validation Accuracy: 0.9598 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.0769 | 0.9849 | 0.2493 | 0.9598 | 0 | | 0.0017 | 1.0 | 0.2868 | 0.9598 | 1 | | 0.0009 | 1.0 | 0.3045 | 0.9598 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
nolanaatama/rmfbtsrvcv1tgrll14
nolanaatama
2023-06-28T07:30:49Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-28T07:26:26Z
--- license: creativeml-openrail-m ---
dhillondheeraj84/elephants_yolov8
dhillondheeraj84
2023-06-28T07:22:35Z
0
0
null
[ "object-detection", "arxiv:1910.09700", "region:us" ]
object-detection
2023-06-13T08:35:51Z
--- pipeline_tag: object-detection --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
kejolong/etomisa
kejolong
2023-06-28T07:21:52Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-28T04:29:02Z
--- license: creativeml-openrail-m ---
AlonCohen/social-groups-ner-first-try
AlonCohen
2023-06-28T06:24:31Z
116
0
transformers
[ "transformers", "pytorch", "tensorboard", "safetensors", "distilbert", "token-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
token-classification
2022-12-29T08:08:18Z
--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: social-groups-ner-first-try 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. --> # social-groups-ner-first-try This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 16 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.25.1 - Pytorch 1.13.0+cu116 - Datasets 2.8.0 - Tokenizers 0.13.2
Sidharthkr/MPT-7b-chat-GGML
Sidharthkr
2023-06-28T06:20:54Z
0
1
null
[ "region:us" ]
null
2023-06-28T05:41:12Z
Compatibilty These files are not compatible with llama.cpp. Currently they can be used with: KoboldCpp, a powerful inference engine based on llama.cpp, with good UI: KoboldCpp The ctransformers Python library, which includes LangChain support: ctransformers The GPT4All-UI which uses ctransformers: GPT4All-UI rustformers' llm The example mpt binary provided with ggml
YakovElm/Jira_20_BERT_Under_Sampling
YakovElm
2023-06-28T06:20:21Z
61
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T06:19:46Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Jira_20_BERT_Under_Sampling 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. --> # Jira_20_BERT_Under_Sampling 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: 0.0014 - Train Accuracy: 1.0 - Validation Loss: 0.4661 - Validation Accuracy: 0.9338 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.1013 | 0.9780 | 0.3644 | 0.9338 | 0 | | 0.0030 | 1.0 | 0.4356 | 0.9338 | 1 | | 0.0014 | 1.0 | 0.4661 | 0.9338 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
alexshengzhili/llava-7bv0-mm-projector-ft-with-ocr-caption-prompted-paragraph
alexshengzhili
2023-06-28T06:16:48Z
13
0
transformers
[ "transformers", "pytorch", "llava", "text-generation", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-generation
2023-06-28T05:25:30Z
--- license: mit --- This is the feature alignment pre-training work to train only only the multi-modal projector. "Predict" paragraph given caption, ocr and image token
YakovElm/Apache_20_BERT_Over_Sampling
YakovElm
2023-06-28T05:51:52Z
62
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T05:51:17Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Apache_20_BERT_Over_Sampling 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. --> # Apache_20_BERT_Over_Sampling 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: 0.0090 - Train Accuracy: 0.9975 - Validation Loss: 0.8778 - Validation Accuracy: 0.8677 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.4086 | 0.7859 | 0.5535 | 0.7992 | 0 | | 0.0378 | 0.9894 | 0.6761 | 0.8872 | 1 | | 0.0090 | 0.9975 | 0.8778 | 0.8677 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
alexshengzhili/llava-fte2e-scicap-w-mentions-390K-440MB
alexshengzhili
2023-06-28T05:44:43Z
16
0
transformers
[ "transformers", "pytorch", "llava", "text-generation", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-generation
2023-06-26T07:57:45Z
This model is formulated to 'predict' caption given image and mentioned paragraph Trains on alexshengzhili/llava-SciCapplus-w-mentions[https://huggingface.co/datasets/alexshengzhili/llava-SciCapplus-w-mentions/tree/main]
dyedream/Reinfore-CardPole
dyedream
2023-06-28T05:43:02Z
0
0
null
[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T05:42:50Z
--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinfore-CardPole results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 500.00 +/- 0.00 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
YakovElm/Jira_10_BERT_Under_Sampling
YakovElm
2023-06-28T05:40:02Z
61
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T05:39:26Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Jira_10_BERT_Under_Sampling 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. --> # Jira_10_BERT_Under_Sampling 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: 0.0015 - Train Accuracy: 1.0 - Validation Loss: 3.4990 - Validation Accuracy: 0.4921 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.0884 | 0.9895 | 2.6907 | 0.4921 | 0 | | 0.0032 | 1.0 | 3.2542 | 0.4921 | 1 | | 0.0015 | 1.0 | 3.4990 | 0.4921 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
YakovElm/Jira_5_BERT_Under_Sampling
YakovElm
2023-06-28T05:20:05Z
61
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T05:19:25Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Jira_5_BERT_Under_Sampling 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. --> # Jira_5_BERT_Under_Sampling 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: 0.0017 - Train Accuracy: 1.0 - Validation Loss: 3.5486 - Validation Accuracy: 0.4858 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.1443 | 0.9748 | 2.5459 | 0.4858 | 0 | | 0.0042 | 1.0 | 3.2782 | 0.4858 | 1 | | 0.0017 | 1.0 | 3.5486 | 0.4858 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
pawankmrs/bert-finetuned-ner
pawankmrs
2023-06-28T05:08:03Z
105
0
transformers
[ "transformers", "pytorch", "tensorboard", "bert", "token-classification", "generated_from_trainer", "dataset:conll2003", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
token-classification
2023-06-28T04:49:15Z
--- license: apache-2.0 tags: - generated_from_trainer datasets: - conll2003 metrics: - precision - recall - f1 - accuracy model-index: - name: bert-finetuned-ner results: - task: name: Token Classification type: token-classification dataset: name: conll2003 type: conll2003 config: conll2003 split: validation args: conll2003 metrics: - name: Precision type: precision value: 0.9365684001324942 - name: Recall type: recall value: 0.9516997643890945 - name: F1 type: f1 value: 0.9440734557595992 - name: Accuracy type: accuracy value: 0.9866221227997881 --- <!-- 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-finetuned-ner This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset. It achieves the following results on the evaluation set: - Loss: 0.0652 - Precision: 0.9366 - Recall: 0.9517 - F1: 0.9441 - Accuracy: 0.9866 ## 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: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.0704 | 1.0 | 1756 | 0.0695 | 0.9159 | 0.9349 | 0.9253 | 0.9822 | | 0.0229 | 2.0 | 3512 | 0.0656 | 0.9345 | 0.9505 | 0.9424 | 0.9867 | | 0.0116 | 3.0 | 5268 | 0.0652 | 0.9366 | 0.9517 | 0.9441 | 0.9866 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
YakovElm/IntelDAOS_20_BERT_Under_Sampling
YakovElm
2023-06-28T05:00:03Z
61
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T04:59:27Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: IntelDAOS_20_BERT_Under_Sampling 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. --> # IntelDAOS_20_BERT_Under_Sampling 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: 0.0011 - Train Accuracy: 1.0 - Validation Loss: 0.6607 - Validation Accuracy: 0.9099 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.0684 | 0.9990 | 0.5155 | 0.9099 | 0 | | 0.0023 | 1.0 | 0.6168 | 0.9099 | 1 | | 0.0011 | 1.0 | 0.6607 | 0.9099 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
Ventalik/fias_NER
Ventalik
2023-06-28T04:56:54Z
139
1
transformers
[ "transformers", "pytorch", "safetensors", "bert", "token-classification", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
token-classification
2023-06-18T16:04:55Z
--- license: mit tags: - generated_from_trainer model-index: - name: fias_NER 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. --> # fias_NER This model is a fine-tuned version of [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2) on an unknown dataset. It achieves the following results on the evaluation set: - eval_loss: 0.0011 - eval_precision: 0.9993 - eval_recall: 0.9994 - eval_f1: 0.9994 - eval_accuracy: 0.9996 - eval_runtime: 783.8012 - eval_samples_per_second: 2551.667 - eval_steps_per_second: 19.935 - epoch: 1.12 - step: 1200000 ## 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: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 2000000 ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu117 - Datasets 2.13.0 - Tokenizers 0.13.3
SandyDelMar/bert-base-uncased-finetuned-MeIA-AnalisisDeSentimientos
SandyDelMar
2023-06-28T04:49:42Z
121
0
transformers
[ "transformers", "pytorch", "tensorboard", "bert", "text-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T03:05:45Z
--- license: apache-2.0 tags: - generated_from_trainer metrics: - f1 model-index: - name: bert-base-uncased-finetuned-MeIA-AnalisisDeSentimientos 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-finetuned-MeIA-AnalisisDeSentimientos This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.0759 - F1: 0.4983 ## 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 | F1 | |:-------------:|:-----:|:----:|:---------------:|:------:| | 1.1797 | 1.0 | 766 | 1.1367 | 0.4474 | | 1.0265 | 2.0 | 1532 | 1.0759 | 0.4983 | ### Framework versions - Transformers 4.28.0 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
Poonnnnnnnn/type-prediction-transformer
Poonnnnnnnn
2023-06-28T04:44:24Z
108
0
transformers
[ "transformers", "pytorch", "tensorboard", "safetensors", "camembert", "text-classification", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-05-12T07:21:22Z
--- tags: - generated_from_trainer metrics: - f1 - accuracy model-index: - name: type-prediction-transformer results: [] widget: - text: "ถนนผุพังทำให้เกิดเสียงดังเวลารถวิ่ง" - text: "ขี่มอไซค์บนทางเท้ามันจะเกินปุยมุ้ย" --- <!-- 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. --> # type-prediction-transformer This model is a fine-tuned version of [airesearch/wangchanberta-base-att-spm-uncased](https://huggingface.co/airesearch/wangchanberta-base-att-spm-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0497 - F1: 0.8651 - Roc Auc: 0.9260 - Accuracy: 0.8208 ## 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: 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: 8 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:| | No log | 1.0 | 149 | 0.0812 | 0.8070 | 0.8677 | 0.7588 | | No log | 2.0 | 298 | 0.0591 | 0.8585 | 0.9064 | 0.8141 | | No log | 3.0 | 447 | 0.0493 | 0.8719 | 0.9144 | 0.8258 | | 0.0886 | 4.0 | 596 | 0.0506 | 0.8614 | 0.9222 | 0.8090 | | 0.0886 | 5.0 | 745 | 0.0487 | 0.8683 | 0.9255 | 0.8174 | | 0.0886 | 6.0 | 894 | 0.0506 | 0.8693 | 0.9291 | 0.8191 | | 0.0254 | 7.0 | 1043 | 0.0519 | 0.8619 | 0.9307 | 0.8090 | | 0.0254 | 8.0 | 1192 | 0.0497 | 0.8651 | 0.9260 | 0.8208 | ### Framework versions - Transformers 4.28.0 - Pytorch 2.0.0+cu118 - Tokenizers 0.13.3
YakovElm/IntelDAOS_15_BERT_Under_Sampling
YakovElm
2023-06-28T04:39:11Z
61
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T04:38:33Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: IntelDAOS_15_BERT_Under_Sampling 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. --> # IntelDAOS_15_BERT_Under_Sampling 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: 0.0015 - Train Accuracy: 1.0 - Validation Loss: 0.8058 - Validation Accuracy: 0.8859 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.1334 | 0.9790 | 0.5877 | 0.8859 | 0 | | 0.0037 | 1.0 | 0.7378 | 0.8859 | 1 | | 0.0015 | 1.0 | 0.8058 | 0.8859 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
limcheekin/fastchat-t5-3b-ct2
limcheekin
2023-06-28T04:36:38Z
14
2
transformers
[ "transformers", "ctranslate2", "fastchat-t5-3b", "quantization", "int8", "text2text-generation", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]
text2text-generation
2023-05-31T06:51:36Z
--- license: apache-2.0 language: - en tags: - ctranslate2 - fastchat-t5-3b - quantization - int8 pipeline_tag: text2text-generation --- # Model Card for FastChat-T5 3B Q8 The model is quantized version of the [lmsys/fastchat-t5-3b-v1.0](https://huggingface.co/lmsys/fastchat-t5-3b-v1.0) with int8 quantization. ## Model Details ### Model Description The model being quantized using [CTranslate2](https://opennmt.net/CTranslate2/) with the following command: ``` ct2-transformers-converter --model lmsys/fastchat-t5-3b --output_dir lmsys/fastchat-t5-3b-ct2 --copy_files generation_config.json added_tokens.json tokenizer_config.json special_tokens_map.json spiece.model --quantization int8 --force --low_cpu_mem_usage ``` If you want to perform the quantization yourself, you need to install the following dependencies: ``` pip install -qU ctranslate2 transformers[torch] sentencepiece accelerate ``` - **Shared by:** Lim Chee Kin - **License:** Apache 2.0 ## How to Get Started with the Model Use the code below to get started with the model. ```python import ctranslate2 import transformers translator = ctranslate2.Translator("limcheekin/fastchat-t5-3b-ct2") tokenizer = transformers.AutoTokenizer.from_pretrained("limcheekin/fastchat-t5-3b-ct2") input_text = "translate English to German: The house is wonderful." input_tokens = tokenizer.convert_ids_to_tokens(tokenizer.encode(input_text)) results = translator.translate_batch([input_tokens]) output_tokens = results[0].hypotheses[0] output_text = tokenizer.decode(tokenizer.convert_tokens_to_ids(output_tokens)) print(output_text) ``` The code is taken from https://opennmt.net/CTranslate2/guides/transformers.html#t5. The key method of the code above is `translate_batch`, you can find out [its supported parameters here](https://opennmt.net/CTranslate2/python/ctranslate2.Translator.html#ctranslate2.Translator.translate_batch).
yihyeji/hanbok_q
yihyeji
2023-06-28T04:33:59Z
0
0
diffusers
[ "diffusers", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "lora", "license:creativeml-openrail-m", "region:us" ]
text-to-image
2023-06-28T04:06:26Z
--- license: creativeml-openrail-m base_model: /workspace/data3/model_checkpoints/DIFFUSION_DB/Diffusion_models/diffusers/v15/chilloutmix_NiPrunedFp16Fix/ instance_prompt: a photo of 1 girl wearing hanbok_q tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - lora inference: true --- # LoRA DreamBooth - yihyeji/hanbok_q These are LoRA adaption weights for /workspace/data3/model_checkpoints/DIFFUSION_DB/Diffusion_models/diffusers/v15/chilloutmix_NiPrunedFp16Fix/. The weights were trained on a photo of 1 girl wearing hanbok_q using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. ![img_0](./image_0.png) ![img_1](./image_1.png) ![img_2](./image_2.png) ![img_3](./image_3.png) LoRA for the text encoder was enabled: False.
PritamReddy/test-demo
PritamReddy
2023-06-28T04:31:57Z
165
0
transformers
[ "transformers", "pytorch", "tensorboard", "t5", "text2text-generation", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text2text-generation
2023-06-27T17:01:45Z
--- license: apache-2.0 tags: - generated_from_trainer metrics: - rouge model-index: - name: test-demo results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # test-demo 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: 4.3257 - Rouge1: 0.0 - Rouge2: 0.0 - Rougel: 0.0 - Rougelsum: 0.0 - Gen Len: 7.6667 ## 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 - gradient_accumulation_steps: 4 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| | No log | 1.0 | 1 | 4.4727 | 0.0 | 0.0 | 0.0 | 0.0 | 7.6667 | | No log | 2.0 | 2 | 4.4727 | 0.0 | 0.0 | 0.0 | 0.0 | 7.6667 | | No log | 3.0 | 3 | 4.4727 | 0.0 | 0.0 | 0.0 | 0.0 | 7.6667 | | No log | 4.0 | 4 | 4.3257 | 0.0 | 0.0 | 0.0 | 0.0 | 7.6667 | | No log | 5.0 | 5 | 4.3257 | 0.0 | 0.0 | 0.0 | 0.0 | 7.6667 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
YakovElm/IntelDAOS_10_BERT_Under_Sampling
YakovElm
2023-06-28T04:18:00Z
61
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T04:17:15Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: IntelDAOS_10_BERT_Under_Sampling 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. --> # IntelDAOS_10_BERT_Under_Sampling 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: 0.0019 - Train Accuracy: 1.0 - Validation Loss: 0.8522 - Validation Accuracy: 0.8739 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.1680 | 0.9670 | 0.5869 | 0.8739 | 0 | | 0.0055 | 1.0 | 0.7770 | 0.8739 | 1 | | 0.0019 | 1.0 | 0.8522 | 0.8739 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
w11wo/malaysian-distilbert-small
w11wo
2023-06-28T04:04:55Z
133
0
transformers
[ "transformers", "pytorch", "tf", "safetensors", "distilbert", "fill-mask", "malaysian-distilbert-small", "ms", "dataset:oscar", "arxiv:1910.01108", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
fill-mask
2022-03-02T23:29:05Z
--- language: ms tags: - malaysian-distilbert-small license: mit datasets: - oscar widget: - text: "Hari ini adalah hari yang [MASK]!" --- ## Malaysian DistilBERT Small Malaysian DistilBERT Small is a masked language model based on the [DistilBERT model](https://arxiv.org/abs/1910.01108). It was trained on the [OSCAR](https://huggingface.co/datasets/oscar) dataset, specifically the `unshuffled_original_ms` subset. The model was originally HuggingFace's pretrained [English DistilBERT model](https://huggingface.co/distilbert-base-uncased) and is later fine-tuned on the Malaysian dataset. It achieved a perplexity of 10.33 on the validation dataset (20% of the dataset). Many of the techniques used are based on a Hugging Face tutorial [notebook](https://github.com/huggingface/notebooks/blob/master/examples/language_modeling.ipynb) written by [Sylvain Gugger](https://github.com/sgugger), and [fine-tuning tutorial notebook](https://github.com/piegu/fastai-projects/blob/master/finetuning-English-GPT2-any-language-Portuguese-HuggingFace-fastaiv2.ipynb) written by [Pierre Guillou](https://huggingface.co/pierreguillou). Hugging Face's [Transformers](https://huggingface.co/transformers) library was used to train the model -- utilizing the base DistilBERT model and their `Trainer` class. PyTorch was used as the backend framework during training, but the model remains compatible with TensorFlow nonetheless. ## Model | Model | #params | Arch. | Training/Validation data (text) | |------------------------------|---------|------------------|----------------------------------------| | `malaysian-distilbert-small` | 66M | DistilBERT Small | OSCAR `unshuffled_original_ms` Dataset | ## Evaluation Results The model was trained for 1 epoch and the following is the final result once the training ended. | train loss | valid loss | perplexity | total time | |------------|------------|------------|------------| | 2.476 | 2.336 | 10.33 | 0:40:05 | ## How to Use ### As Masked Language Model ```python from transformers import pipeline pretrained_name = "w11wo/malaysian-distilbert-small" fill_mask = pipeline( "fill-mask", model=pretrained_name, tokenizer=pretrained_name ) fill_mask("Henry adalah seorang lelaki yang tinggal di [MASK].") ``` ### Feature Extraction in PyTorch ```python from transformers import DistilBertModel, DistilBertTokenizerFast pretrained_name = "w11wo/malaysian-distilbert-small" model = DistilBertModel.from_pretrained(pretrained_name) tokenizer = DistilBertTokenizerFast.from_pretrained(pretrained_name) prompt = "Bolehkah anda [MASK] Bahasa Melayu?" encoded_input = tokenizer(prompt, return_tensors='pt') output = model(**encoded_input) ``` ## Disclaimer Do consider the biases which came from the OSCAR dataset that may be carried over into the results of this model. ## Author Malaysian DistilBERT Small was trained and evaluated by [Wilson Wongso](https://w11wo.github.io/). All computation and development are done on Google Colaboratory using their free GPU access.
YakovElm/IntelDAOS_5_BERT_Under_Sampling
YakovElm
2023-06-28T03:56:38Z
61
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T03:56:02Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: IntelDAOS_5_BERT_Under_Sampling 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. --> # IntelDAOS_5_BERT_Under_Sampling 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: 0.0027 - Train Accuracy: 1.0 - Validation Loss: 0.9951 - Validation Accuracy: 0.8438 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.1195 | 0.9700 | 0.6261 | 0.8438 | 0 | | 0.0096 | 1.0 | 0.8785 | 0.8438 | 1 | | 0.0027 | 1.0 | 0.9951 | 0.8438 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
loghai/q-FrozenLake-v1-4x4-noSlippery
loghai
2023-06-28T03:50:04Z
0
0
null
[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T03:50:01Z
--- 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="loghai/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"]) ```
ALPHONSE28/SEMANA10_SINTENTICOS
ALPHONSE28
2023-06-28T03:45:32Z
103
0
transformers
[ "transformers", "pytorch", "tensorboard", "distilbert", "text-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T03:15:06Z
--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy - f1 model-index: - name: SEMANA10_SINTENTICOS 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. --> # SEMANA10_SINTENTICOS 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: 0.3103 - Accuracy: 0.9048 - F1: 0.9259 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3