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
2025-09-03 00:36:49
downloads
int64
0
223M
likes
int64
0
11.7k
library_name
stringclasses
535 values
tags
listlengths
1
4.05k
pipeline_tag
stringclasses
55 values
createdAt
timestamp[us, tz=UTC]date
2022-03-02 23:29:04
2025-09-03 00:36:49
card
stringlengths
11
1.01M
gokuls/hBERTv1_no_pretrain_rte
gokuls
2023-06-15T09:38:15Z
45
0
transformers
[ "transformers", "pytorch", "tensorboard", "hybridbert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-05-29T10:25:42Z
--- language: - en tags: - generated_from_trainer datasets: - glue metrics: - accuracy model-index: - name: hBERTv1_no_pretrain_rte results: - task: name: Text Classification type: text-classification dataset: name: GLUE RTE type: glue config: rte split: validation args: rte metrics: - name: Accuracy type: accuracy value: 0.5270758122743683 --- <!-- 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. --> # hBERTv1_no_pretrain_rte This model is a fine-tuned version of [](https://huggingface.co/) on the GLUE RTE dataset. It achieves the following results on the evaluation set: - Loss: 0.6919 - Accuracy: 0.5271 ## 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: 4e-05 - train_batch_size: 96 - eval_batch_size: 96 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.7561 | 1.0 | 26 | 0.6977 | 0.4729 | | 0.7108 | 2.0 | 52 | 0.7333 | 0.4729 | | 0.7378 | 3.0 | 78 | 0.6919 | 0.5271 | | 0.7045 | 4.0 | 104 | 0.7052 | 0.5271 | | 0.7077 | 5.0 | 130 | 0.7034 | 0.5271 | | 0.6816 | 6.0 | 156 | 0.7515 | 0.5343 | | 0.6692 | 7.0 | 182 | 0.7616 | 0.5235 | | 0.5846 | 8.0 | 208 | 0.9617 | 0.4838 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
Outimus/ti
Outimus
2023-06-15T09:35:43Z
0
2
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-01-23T08:27:26Z
--- license: creativeml-openrail-m ---
tux/q-Taxi-v3-2
tux
2023-06-15T09:21:00Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-15T09:17:33Z
--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-Taxi-v3-2 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="tux/q-Taxi-v3-2", 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"]) ```
shouqiangli/test001
shouqiangli
2023-06-15T09:19:30Z
0
0
allennlp
[ "allennlp", "finance", "text-classification", "aa", "dataset:fka/awesome-chatgpt-prompts", "license:openrail", "region:us" ]
text-classification
2023-06-15T08:50:33Z
--- license: openrail datasets: - fka/awesome-chatgpt-prompts language: - aa metrics: - accuracy library_name: allennlp pipeline_tag: text-classification tags: - finance ---
anilsekharc/ppo-Huggy
anilsekharc
2023-06-15T09:19:21Z
2
0
ml-agents
[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]
reinforcement-learning
2023-06-15T09:19:17Z
--- 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: anilsekharc/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
fx1H/q-Taxi-v3-v2
fx1H
2023-06-15T09:17:37Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-15T09:17:35Z
--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-Taxi-v3-v2 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="fx1H/q-Taxi-v3-v2", 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"]) ```
tux/q-Taxi-v3-1
tux
2023-06-15T09:16:45Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-15T09:11:58Z
--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-Taxi-v3-1 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="tux/q-Taxi-v3-1", 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"]) ```
gokuls/hBERTv2_new_pretrain_48_KD_mnli
gokuls
2023-06-15T09:16:16Z
46
0
transformers
[ "transformers", "pytorch", "tensorboard", "hybridbert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-15T04:12:58Z
--- language: - en tags: - generated_from_trainer datasets: - glue metrics: - accuracy model-index: - name: hBERTv2_new_pretrain_48_KD_mnli results: - task: name: Text Classification type: text-classification dataset: name: GLUE MNLI type: glue config: mnli split: validation_matched args: mnli metrics: - name: Accuracy type: accuracy value: 0.3522172497965826 --- <!-- 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. --> # hBERTv2_new_pretrain_48_KD_mnli This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_48_KD](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_48_KD) on the GLUE MNLI dataset. It achieves the following results on the evaluation set: - Loss: 1.0986 - Accuracy: 0.3522 ## 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: 4e-05 - train_batch_size: 128 - eval_batch_size: 128 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:| | 1.1024 | 1.0 | 3068 | 1.0991 | 0.3182 | | 1.0989 | 2.0 | 6136 | 1.0986 | 0.3545 | | 1.0987 | 3.0 | 9204 | 1.0986 | 0.3274 | | 1.1005 | 4.0 | 12272 | 1.0986 | 0.3545 | | 1.0986 | 5.0 | 15340 | 1.0986 | 0.3545 | | 1.0987 | 6.0 | 18408 | 1.1010 | 0.3274 | | 1.0986 | 7.0 | 21476 | 1.0987 | 0.3545 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
AustinCarthy/MixGPT2_subdomain_100KP_BFall_fromP_90K_topP_0.75_ratio5
AustinCarthy
2023-06-15T09:13:10Z
0
0
null
[ "tensorboard", "generated_from_trainer", "license:apache-2.0", "region:us" ]
null
2023-06-15T05:45:06Z
--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy - f1 - precision - recall model-index: - name: MixGPT2_subdomain_100KP_BFall_fromP_90K_topP_0.75_ratio5 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. --> # MixGPT2_subdomain_100KP_BFall_fromP_90K_topP_0.75_ratio5 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the Train benign: Fall,Test Benign: Fall, Train phish: Fall, Test phish: Fall, generated url dataset: generated_phish_MixGPT2_using_phish_95K_top_p_0.75subdomain dataset. It achieves the following results on the evaluation set: - Loss: 0.0167 - Accuracy: 0.9982 - F1: 0.9807 - Precision: 0.9994 - Recall: 0.9628 - Roc Auc Score: 0.9814 - Tpr At Fpr 0.01: 0.9688 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc Score | Tpr At Fpr 0.01 | |:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|:---------:|:------:|:-------------:|:---------------:| | 0.0042 | 1.0 | 35625 | 0.0207 | 0.9962 | 0.9583 | 0.9987 | 0.921 | 0.9605 | 0.9318 | | 0.002 | 2.0 | 71250 | 0.0188 | 0.9976 | 0.9737 | 0.9987 | 0.9498 | 0.9749 | 0.9544 | | 0.0027 | 3.0 | 106875 | 0.0232 | 0.9974 | 0.9719 | 0.9979 | 0.9472 | 0.9736 | 0.9464 | | 0.0007 | 4.0 | 142500 | 0.0155 | 0.9982 | 0.9805 | 0.9983 | 0.9632 | 0.9816 | 0.965 | | 0.0007 | 5.0 | 178125 | 0.0167 | 0.9982 | 0.9807 | 0.9994 | 0.9628 | 0.9814 | 0.9688 | ### Framework versions - Transformers 4.30.1 - Pytorch 2.0.0+cu118 - Datasets 2.12.0 - Tokenizers 0.13.3
tux/q-Taxi-v3
tux
2023-06-15T09:11:30Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-15T09:07:27Z
--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-Taxi-v3 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.56 +/- 2.71 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **Taxi-v3** This is a trained model of a **Q-Learning** agent playing **Taxi-v3** . ## Usage ```python model = load_from_hub(repo_id="tux/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"]) ```
pushkin05/a2c-PandaReachDense-v2
pushkin05
2023-06-15T09:07:08Z
4
0
stable-baselines3
[ "stable-baselines3", "PandaReachDense-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-15T08:15:47Z
--- 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: -1.47 +/- 0.27 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 ... ```
tux/default_taxi
tux
2023-06-15T09:04:10Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-15T09:04:09Z
--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: default_taxi 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="tux/default_taxi", 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"]) ```
Chaitanya14/flan-t5-large-finetuned-xsum
Chaitanya14
2023-06-15T08:54:40Z
105
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
2023-06-15T08:49:12Z
--- license: apache-2.0 tags: - generated_from_trainer metrics: - rouge model-index: - name: flan-t5-large-finetuned-xsum results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # flan-t5-large-finetuned-xsum This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: nan - Rouge1: 14.0152 - Rouge2: 6.2802 - Rougel: 13.7963 - Rougelsum: 13.9306 - Gen Len: 6.8696 ## 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: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| | No log | 1.0 | 13 | nan | 14.0152 | 6.2802 | 13.7963 | 13.9306 | 6.8696 | | No log | 2.0 | 26 | nan | 14.0152 | 6.2802 | 13.7963 | 13.9306 | 6.8696 | | No log | 3.0 | 39 | nan | 14.0152 | 6.2802 | 13.7963 | 13.9306 | 6.8696 | | No log | 4.0 | 52 | nan | 14.0152 | 6.2802 | 13.7963 | 13.9306 | 6.8696 | | No log | 5.0 | 65 | nan | 14.0152 | 6.2802 | 13.7963 | 13.9306 | 6.8696 | | No log | 6.0 | 78 | nan | 14.0152 | 6.2802 | 13.7963 | 13.9306 | 6.8696 | | No log | 7.0 | 91 | nan | 14.0152 | 6.2802 | 13.7963 | 13.9306 | 6.8696 | | No log | 8.0 | 104 | nan | 14.0152 | 6.2802 | 13.7963 | 13.9306 | 6.8696 | | No log | 9.0 | 117 | nan | 14.0152 | 6.2802 | 13.7963 | 13.9306 | 6.8696 | | No log | 10.0 | 130 | nan | 14.0152 | 6.2802 | 13.7963 | 13.9306 | 6.8696 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.0 - Tokenizers 0.13.3
gokuls/hBERTv1_new_pretrain_48_KD_mnli
gokuls
2023-06-15T08:43:08Z
45
0
transformers
[ "transformers", "pytorch", "tensorboard", "hybridbert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-15T01:43:06Z
--- language: - en tags: - generated_from_trainer datasets: - glue metrics: - accuracy model-index: - name: hBERTv1_new_pretrain_48_KD_mnli results: - task: name: Text Classification type: text-classification dataset: name: GLUE MNLI type: glue config: mnli split: validation_matched args: mnli metrics: - name: Accuracy type: accuracy value: 0.3267900732302685 --- <!-- 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. --> # hBERTv1_new_pretrain_48_KD_mnli This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_48_KD](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_48_KD) on the GLUE MNLI dataset. It achieves the following results on the evaluation set: - Loss: 1.0977 - Accuracy: 0.3268 ## 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: 4e-05 - train_batch_size: 128 - eval_batch_size: 128 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:| | 1.1011 | 1.0 | 3068 | 1.1001 | 0.3176 | | 1.0991 | 2.0 | 6136 | 1.0978 | 0.3295 | | 1.0983 | 3.0 | 9204 | 1.0985 | 0.3351 | | 1.0984 | 4.0 | 12272 | 1.0983 | 0.3294 | | 1.098 | 5.0 | 15340 | 1.0978 | 0.3264 | | 1.098 | 6.0 | 18408 | 1.0979 | 0.3285 | | 1.098 | 7.0 | 21476 | 1.0980 | 0.3272 | | 1.098 | 8.0 | 24544 | 1.0981 | 0.3266 | | 1.098 | 9.0 | 27612 | 1.0980 | 0.3256 | | 1.098 | 10.0 | 30680 | 1.0985 | 0.3320 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
XiaHan19/shami-token
XiaHan19
2023-06-15T08:42:08Z
0
0
null
[ "license:apache-2.0", "region:us" ]
null
2023-06-07T14:12:26Z
--- license: apache-2.0 --- Shami Tokenizer === This is the tokenizer of Shami Model.
Manaro/Reinforce-pixelcopter
Manaro
2023-06-15T08:15:06Z
0
0
null
[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]
reinforcement-learning
2023-05-25T18:44:14Z
--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-pixelcopter results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 4.60 +/- 7.21 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
pushkin05/Pyramids
pushkin05
2023-06-15T08:09:16Z
4
0
ml-agents
[ "ml-agents", "tensorboard", "onnx", "Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids", "region:us" ]
reinforcement-learning
2023-06-15T07:57:49Z
--- 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: pushkin05/Pyramids 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
gokuls/sa_BERT_no_pretrain_wnli
gokuls
2023-06-15T08:08:30Z
131
0
transformers
[ "transformers", "pytorch", "tensorboard", "bert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-05-29T14:36:04Z
--- language: - en license: apache-2.0 tags: - generated_from_trainer datasets: - glue metrics: - accuracy model-index: - name: sa_BERT_no_pretrain_wnli results: - task: name: Text Classification type: text-classification dataset: name: GLUE WNLI type: glue config: wnli split: validation args: wnli metrics: - name: Accuracy type: accuracy value: 0.5633802816901409 --- <!-- 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. --> # sa_BERT_no_pretrain_wnli This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE WNLI dataset. It achieves the following results on the evaluation set: - Loss: 0.6866 - Accuracy: 0.5634 ## 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: 4e-05 - train_batch_size: 96 - eval_batch_size: 96 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 1.0074 | 1.0 | 7 | 0.6958 | 0.4366 | | 0.6986 | 2.0 | 14 | 0.7035 | 0.4366 | | 0.7007 | 3.0 | 21 | 0.6866 | 0.5634 | | 0.7052 | 4.0 | 28 | 0.7037 | 0.4366 | | 0.7008 | 5.0 | 35 | 0.6951 | 0.4366 | | 0.7107 | 6.0 | 42 | 0.6908 | 0.5634 | | 0.6963 | 7.0 | 49 | 0.6945 | 0.4366 | | 0.7012 | 8.0 | 56 | 0.6894 | 0.5634 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
pushkin05/ppo-SnowballTarget
pushkin05
2023-06-15T08:03:39Z
0
0
ml-agents
[ "ml-agents", "tensorboard", "onnx", "SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget", "region:us" ]
reinforcement-learning
2023-06-15T07:53:32Z
--- library_name: ml-agents tags: - SnowballTarget - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SnowballTarget --- # **ppo** Agent playing **SnowballTarget** This is a trained model of a **ppo** agent playing **SnowballTarget** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: pushkin05/ppo-SnowballTarget 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
gokuls/sa_BERT_no_pretrain_stsb
gokuls
2023-06-15T08:03:24Z
129
0
transformers
[ "transformers", "pytorch", "tensorboard", "bert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-05-29T14:26:57Z
--- language: - en license: apache-2.0 tags: - generated_from_trainer datasets: - glue metrics: - spearmanr model-index: - name: sa_BERT_no_pretrain_stsb results: - task: name: Text Classification type: text-classification dataset: name: GLUE STSB type: glue config: stsb split: validation args: stsb metrics: - name: Spearmanr type: spearmanr value: 0.12459536879199183 --- <!-- 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. --> # sa_BERT_no_pretrain_stsb This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE STSB dataset. It achieves the following results on the evaluation set: - Loss: 2.5396 - Pearson: 0.1394 - Spearmanr: 0.1246 - Combined Score: 0.1320 ## 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: 4e-05 - train_batch_size: 96 - eval_batch_size: 96 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score | |:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:| | 2.257 | 1.0 | 60 | 3.1111 | 0.0528 | 0.0709 | 0.0619 | | 2.0476 | 2.0 | 120 | 2.5396 | 0.1394 | 0.1246 | 0.1320 | | 1.8905 | 3.0 | 180 | 2.5928 | 0.1553 | 0.1593 | 0.1573 | | 1.5383 | 4.0 | 240 | 3.1130 | 0.1930 | 0.2086 | 0.2008 | | 1.3384 | 5.0 | 300 | 2.8651 | 0.1788 | 0.2014 | 0.1901 | | 1.1299 | 6.0 | 360 | 2.9651 | 0.1818 | 0.1947 | 0.1883 | | 1.0952 | 7.0 | 420 | 2.6404 | 0.2100 | 0.2124 | 0.2112 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
Lajonbot/LaMini-Cerebras-256M-8500-steps-polish
Lajonbot
2023-06-15T07:58:02Z
132
0
transformers
[ "transformers", "pytorch", "gpt2", "text-generation", "pl", "dataset:databricks/databricks-dolly-15k", "dataset:s3nh/alpaca-dolly-instruction-only-polish", "license:openrail", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-04-29T19:16:29Z
--- license: openrail datasets: - databricks/databricks-dolly-15k - s3nh/alpaca-dolly-instruction-only-polish language: - pl --- ### Introduction These repository consist of LaMini-Cerebras-256M finetuned to Polish language on translated alpaca-dolly dataset. Main task is to perform accurate answers to instruction asked. Below you can find an instruction of how to infer with that model. These repository does not contain an tokenizer object, at the moment (#TODO). ### Evaluation part ```python import pandas as pd import torch from torch.utils.data import AutTokenizer from typing import List, Dict, Union from typing import Any, TypeVar import pandas as pd import pickle MODEL_NAME: str = 'Lajonbot/LaMini-Cerebras-256M-8500-steps-polish' tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME) model = AutoModelForCasualLM.from_pretrained(MODEL_NAME).cuda() #Resize model for tokenizer size n_tokens: int = len(tokenizer) model.resize_token_embeddings(n_tokens) def _generate_prompt(instruction, input=None): if input: return f"""Poniżej znajduje się instrukcja opisująca zadanie, połączona z danymi wejściowymi, które zapewniają dalszy konktekst. Napisz odpowiedź, która odpowiednio odpowie na pytanie. ### Instruction: {instruction} ### Input: {input} ### Response:""" manual_instruction: str = "Napisz mi proszę jakie są rodzaje telefonów komórkowych" manual_input: str = "Telefony komórkowe, w przeciwieństwie do np. satelitarnych, charakteryzuje to, że działają w obrębie naziemnych fal radiowych w technologii GSM (i w różnych jej wariantach: 3G, 4G czy niebawem 5G). Zasadniczo można jednak wyróżnić wiele ich rodzajów i podzielić je na różne kryteria. I tak, ze względu na rodzaj obudowy, można mówić o telefonach jednobryłowych, rozsuwanych, obrotowych czy też z klapką. Obecnie jednak najbardziej popularne i – ze względu na posiadane parametry – najlepsze telefony komórkowe to smartfony dotykowe." print(f"Valueation for {manual_instruction} \n\n\n {manual_input}\n\n") evaluate(instruction = manual_instruction, input = manual_input) ```
octipuw/ppo-Huggy
octipuw
2023-06-15T07:54:53Z
2
0
ml-agents
[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]
reinforcement-learning
2023-06-15T07:54:47Z
--- 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: octipuw/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
casque/majicmixLux_v2
casque
2023-06-15T07:51:35Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-15T07:34:10Z
--- license: creativeml-openrail-m ---
gokuls/sa_BERT_no_pretrain_sst2
gokuls
2023-06-15T07:48:32Z
129
0
transformers
[ "transformers", "pytorch", "tensorboard", "bert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-05-29T13:35:42Z
--- language: - en license: apache-2.0 tags: - generated_from_trainer datasets: - glue metrics: - accuracy model-index: - name: sa_BERT_no_pretrain_sst2 results: - task: name: Text Classification type: text-classification dataset: name: GLUE SST2 type: glue config: sst2 split: validation args: sst2 metrics: - name: Accuracy type: accuracy value: 0.8027522935779816 --- <!-- 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. --> # sa_BERT_no_pretrain_sst2 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE SST2 dataset. It achieves the following results on the evaluation set: - Loss: 0.4637 - Accuracy: 0.8028 ## 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: 4e-05 - train_batch_size: 96 - eval_batch_size: 96 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.4863 | 1.0 | 702 | 0.4747 | 0.7890 | | 0.2723 | 2.0 | 1404 | 0.4974 | 0.7901 | | 0.2219 | 3.0 | 2106 | 0.4637 | 0.8028 | | 0.1848 | 4.0 | 2808 | 0.7501 | 0.7833 | | 0.1591 | 5.0 | 3510 | 0.5357 | 0.8005 | | 0.1346 | 6.0 | 4212 | 0.5450 | 0.7833 | | 0.1148 | 7.0 | 4914 | 0.8002 | 0.7741 | | 0.1034 | 8.0 | 5616 | 0.8853 | 0.7821 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
prognosis/falcon40b-chunks-10k-v1_1
prognosis
2023-06-15T07:47:29Z
0
0
null
[ "tensorboard", "generated_from_trainer", "license:apache-2.0", "region:us" ]
null
2023-06-15T04:30:53Z
--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: falcon40b-chunks-10k-v1_1 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. --> # falcon40b-chunks-10k-v1_1 This model is a fine-tuned version of [tiiuae/falcon-40b](https://huggingface.co/tiiuae/falcon-40b) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 4 - eval_batch_size: 8 - 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: constant - lr_scheduler_warmup_ratio: 0.03 - training_steps: 500 ### Training results ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.0 - Tokenizers 0.13.3
Falah/Mask_awesome_eli5_mlm_model
Falah
2023-06-15T07:47:20Z
105
0
transformers
[ "transformers", "pytorch", "tensorboard", "roberta", "fill-mask", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
fill-mask
2023-06-15T07:05:22Z
--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: Mask_awesome_eli5_mlm_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. --> # Mask_awesome_eli5_mlm_model This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.9796 ## 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: 4 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 1.7361 | 1.0 | 1131 | 2.0661 | | 1.8475 | 2.0 | 2262 | 2.0314 | | 1.983 | 3.0 | 3393 | 2.0085 | | 2.0677 | 4.0 | 4524 | 1.9931 | ### Framework versions - Transformers 4.27.1 - Pytorch 2.0.1+cu118 - Datasets 2.9.0 - Tokenizers 0.13.3
DAMO-NLP-SG/mt-llama-7b-delta
DAMO-NLP-SG
2023-06-15T07:21:35Z
12
2
transformers
[ "transformers", "pytorch", "llama", "text-generation", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-05-05T02:52:02Z
--- license: mit --- # MT-LLaMA Model Card ## Model details **Model type:** MT-LLaMA is an open-source multi-task model trained by fine-tuning LLaMA on the massive tasks in [P3](https://huggingface.co/datasets/bigscience/P3) (i.e., T0 Train). Concretely, the used datasets during training and task taxonomy are listed below: * Multi-choice QA: CommonsenseQA, Cosmos QA, DREAM, QuAIL, QuaRTz, QASC, QuaRel, SciQ, Social IQA, Wiki Hop, WiQA * Extractive QA: Adversarial QA, DuoRC, Quoref, ROPES * Close-Book QA: Hotpot QA, Wiki QA * Sentiment Classification: Amazon, App Reviews, IMDB, Rotten Tomatoes, Yelp * Topic Classification: AG News, DBPedia, TREC * Structure-to-Text Generation: Common Gen, Wiki Bio * Text Summarization: CNN Daily Mail, Gigaword, MultiNews, SamSum, XSum * Paraphrase Identification: MRPC, PAWS, QQP **Organizations developing the model:** The MT-LLaMA team with members from Alibaba Damo Academy and the Chinese University of Hong Kong. ## Intended use You can try the codes from our [github repo](https://github.com/DAMO-NLP-SG/MT-LLaMA). ## Zero-shot Evaluation We primarily follow the protocols of [Bigscience T0](https://openreview.net/forum?id=9Vrb9D0WI4) to assess the generalization capability of our Multi-task LLaMA to: (1) _**Unseen Datasets**_ (i.e., datasets from seen tasks); (2) _**Unseen Tasks**_. #### Prompt Format Extractive QA: 1. XQuAD, TyDiQA, MLQA, SQuAD ```angular2html Input: Answer the question according to the context. Question: ${question}. Context: ${context}. Answer: Output: ${Answer} ``` Sentiment: 1. SST-2 ```angular2html Input: ${sentence} Based on this review, would the user recommend this product? No or Yes? Output: Yes / No ``` Multiple-Choice QA: 1. OpenbookQA ```angular2html Input: ${question} Which is the correct answer? - (A) ${choiceA} - (B) ${choiceB} - (C) ${choiceC} - (D) ${choiceD} Output: ${choiceA} / ${choiceB} / ${choiceC} / ${choiceD} ``` Sentence Completion: 1. COPA ```angular2html Input: ${premise} {% if question == "cause" %} This happened because... {% else %} As a consequence... Help me pick the more plausible option: - ${text1} - ${text2} Output: ${text1} / ${text2} ``` Coreference Resolution: 1. Winogrande: ```angular2html Input: ${sentence} In the previous sentence, does _ refer to ${option1} or ${option2}? Output: ${option1} / ${option2} ``` Word Sense Disambiguation: 1. WiC ```angular2html Input: Does the word "${word}" have the same meaning in these two sentences? Yes, No? ${sentence1} ${sentence2} Output: ${sentence1} / ${sentence2} ``` Natural Language Inference: 1. MNLI: ```angular2html Input: ${premise} Question: Does this imply that ${hypothesis}? Please response with 'Yes', 'No', or 'Maybe'. Output: Yes / No / Maybe ``` 2. RTE ```angular2html Input: Given ${premise} Is it guaranteed true that "${hypothesis}"? Yes or no? Output: Yes / no ``` #### Results on _Unseen Datasets_ | Model | XQuAD-en (F1/EM) | TyDiQA-en (F1/EM) | MLQA-en (F1/EM) | SQuAD (F1/EM) | SST-2 (Acc.) | OpenbookQA (Acc.) | |:------------|------------------|-------------------|-----------------|---------------|--------------|-------------------| | LLaMA-7b | 9.5 / 2.0 | 14.3 / 2.6 | 13.4 / 3.3 | 29.4 / 11.5 | 50.5 | 32.4 | | MT-LLaMA-7b | 42.3 / 31.1 | 38.9 / 26.9 | 45.4 / 31.5 | 85.9 / 77.6 | 92.6 | 38.2 | #### Results on _Unseen Tasks_ | Model | COPA (Acc.) | Winogrande (Acc.) | WiC (Acc.) | MNLI (Acc.) | RTE (Acc.) | |:------------|-------------|--------------------|------------|-------------|------------| | LLaMA-7b | 56.0 | 49.3 | 51.7 | 30.2 | 52.7 | | MT-LLaMA-7b | 88.0 | 54.9 | 52.2 | 49.6 | 79.1 | ## Acknowledgement * Our training codes are largely borrowed from [FastChat](https://github.com/lm-sys/FastChat) * We are also grateful for the efforts of [LLaMA](https://github.com/facebookresearch/llama) (from FAIR) and [T0](https://github.com/bigscience-workshop/t-zero) (from BigScience), which serve as the foundation of our work If you find this resource useful, please cite the repo as follows: ``` @software{damonlpsg2023mtllama, author = {Xu, Weiwen and Li, Xin and Bing, Lidong}, title = {Multi-task Instruction-tuned LLaMA}, year = 2023, url = {https://github.com/DAMO-NLP-SG/MT-LLaMA} } ```
casque/realisian_v40
casque
2023-06-15T07:04:36Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-15T06:49:10Z
--- license: creativeml-openrail-m ---
tux/ppo-Huggy
tux
2023-06-15T06:52:23Z
24
0
ml-agents
[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]
reinforcement-learning
2023-06-15T06:52:12Z
--- 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: tux/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
Janxxx/Kokoroface
Janxxx
2023-06-15T06:43:16Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-15T06:41:58Z
--- license: creativeml-openrail-m ---
khsyee/sam-vit-h-encoder-torchscript
khsyee
2023-06-15T06:18:48Z
0
0
null
[ "license:apache-2.0", "region:us" ]
null
2023-06-14T07:39:53Z
--- license: apache-2.0 --- ## Run Set conda env. ``` make env conda activate sam-vit-h-encoder-torchscript make setup ``` Load the SAM model and convert image encoder to torchscript. ``` python convert_torchscript.py ``` Check `model.pt` in `model_repository/sam_torchscript_fp32/1`.
gokuls/sa_BERT_no_pretrain_rte
gokuls
2023-06-15T05:47:43Z
127
0
transformers
[ "transformers", "pytorch", "tensorboard", "bert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-05-29T13:29:15Z
--- language: - en license: apache-2.0 tags: - generated_from_trainer datasets: - glue metrics: - accuracy model-index: - name: sa_BERT_no_pretrain_rte results: - task: name: Text Classification type: text-classification dataset: name: GLUE RTE type: glue config: rte split: validation args: rte metrics: - name: Accuracy type: accuracy value: 0.5306859205776173 --- <!-- 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. --> # sa_BERT_no_pretrain_rte This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE RTE dataset. It achieves the following results on the evaluation set: - Loss: 0.6909 - Accuracy: 0.5307 ## 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: 4e-05 - train_batch_size: 96 - eval_batch_size: 96 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.7596 | 1.0 | 26 | 0.6909 | 0.5307 | | 0.6968 | 2.0 | 52 | 0.6914 | 0.5235 | | 0.7026 | 3.0 | 78 | 0.6911 | 0.5307 | | 0.6961 | 4.0 | 104 | 0.6928 | 0.5379 | | 0.7114 | 5.0 | 130 | 0.6917 | 0.5271 | | 0.7005 | 6.0 | 156 | 0.7069 | 0.4729 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
Chaitanya14/t5-base-finetuned-xsum
Chaitanya14
2023-06-15T05:45:46Z
105
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
2023-06-14T08:03:29Z
--- license: apache-2.0 tags: - generated_from_trainer metrics: - rouge model-index: - name: t5-base-finetuned-xsum 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-base-finetuned-xsum This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.1894 - Rouge1: 34.6512 - Rouge2: 19.303 - Rougel: 32.5996 - Rougelsum: 32.471 - Gen Len: 7.0 ## 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: 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: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| | No log | 1.0 | 13 | 2.5904 | 31.7728 | 17.9506 | 31.6663 | 32.1172 | 7.2609 | | No log | 2.0 | 26 | 2.5238 | 33.4485 | 17.2356 | 33.0828 | 33.5748 | 7.8696 | | No log | 3.0 | 39 | 2.4739 | 31.3343 | 15.996 | 31.2341 | 31.646 | 9.0435 | | No log | 4.0 | 52 | 2.4413 | 31.2481 | 16.395 | 31.2318 | 31.633 | 8.0435 | | No log | 5.0 | 65 | 2.4156 | 28.9275 | 13.9479 | 28.7067 | 29.3501 | 8.2609 | | No log | 6.0 | 78 | 2.3768 | 25.1989 | 12.2726 | 25.1301 | 25.331 | 9.6087 | | No log | 7.0 | 91 | 2.3599 | 25.7646 | 12.6915 | 25.745 | 26.2307 | 9.0 | | No log | 8.0 | 104 | 2.3460 | 27.3509 | 12.7398 | 27.3198 | 27.7394 | 8.3043 | | No log | 9.0 | 117 | 2.3134 | 26.4175 | 12.3464 | 26.3116 | 26.6575 | 8.2609 | | No log | 10.0 | 130 | 2.3089 | 25.4818 | 12.381 | 25.4929 | 25.9985 | 7.913 | | No log | 11.0 | 143 | 2.2976 | 27.5605 | 13.3195 | 27.4523 | 27.7723 | 7.0 | | No log | 12.0 | 156 | 2.2951 | 29.0566 | 13.3195 | 29.1363 | 29.4032 | 7.0 | | No log | 13.0 | 169 | 2.2770 | 27.4586 | 13.2436 | 27.3583 | 27.7153 | 7.1304 | | No log | 14.0 | 182 | 2.2675 | 27.4586 | 13.2436 | 27.3583 | 27.7153 | 7.1304 | | No log | 15.0 | 195 | 2.2573 | 27.4586 | 13.2436 | 27.3583 | 27.7153 | 7.0 | | No log | 16.0 | 208 | 2.2523 | 28.0801 | 13.2436 | 28.0208 | 28.4869 | 6.6957 | | No log | 17.0 | 221 | 2.2410 | 29.7194 | 13.9268 | 29.6547 | 29.9577 | 6.7826 | | No log | 18.0 | 234 | 2.2355 | 29.8201 | 13.9268 | 29.7716 | 30.1114 | 7.0 | | No log | 19.0 | 247 | 2.2350 | 28.4851 | 13.6025 | 28.3633 | 28.6581 | 7.0435 | | No log | 20.0 | 260 | 2.2219 | 26.4416 | 12.7674 | 25.9806 | 26.2749 | 6.6522 | | No log | 21.0 | 273 | 2.2036 | 26.6032 | 13.0124 | 26.25 | 26.4627 | 6.8261 | | No log | 22.0 | 286 | 2.1974 | 27.4656 | 13.0124 | 27.2275 | 27.2769 | 6.2174 | | No log | 23.0 | 299 | 2.1962 | 26.4416 | 12.7674 | 25.9806 | 26.2749 | 6.6957 | | No log | 24.0 | 312 | 2.2099 | 26.1686 | 12.6018 | 25.7118 | 25.9094 | 6.7391 | | No log | 25.0 | 325 | 2.1990 | 27.3084 | 12.7709 | 27.0236 | 27.0354 | 6.1739 | | No log | 26.0 | 338 | 2.1942 | 29.0825 | 12.7709 | 28.6736 | 29.3337 | 6.3478 | | No log | 27.0 | 351 | 2.2058 | 29.0825 | 12.7709 | 27.5837 | 28.1575 | 6.0 | | No log | 28.0 | 364 | 2.2012 | 29.0825 | 12.7709 | 27.5837 | 28.1575 | 6.0 | | No log | 29.0 | 377 | 2.1992 | 28.1338 | 12.7709 | 26.6664 | 27.0659 | 6.8696 | | No log | 30.0 | 390 | 2.1840 | 32.5399 | 17.1325 | 31.2654 | 31.4223 | 6.6087 | | No log | 31.0 | 403 | 2.1824 | 32.5399 | 17.1325 | 31.2654 | 31.4223 | 6.7826 | | No log | 32.0 | 416 | 2.1830 | 34.6512 | 19.303 | 33.1484 | 33.1392 | 6.8261 | | No log | 33.0 | 429 | 2.1846 | 33.0599 | 19.303 | 31.3736 | 31.5588 | 6.6522 | | No log | 34.0 | 442 | 2.1868 | 33.0599 | 19.303 | 31.3736 | 31.5588 | 6.6522 | | No log | 35.0 | 455 | 2.1803 | 35.5538 | 19.303 | 34.135 | 34.0635 | 6.087 | | No log | 36.0 | 468 | 2.1779 | 35.5538 | 19.303 | 33.5533 | 33.5085 | 6.087 | | No log | 37.0 | 481 | 2.1770 | 34.9683 | 19.303 | 33.2356 | 33.1109 | 6.1739 | | No log | 38.0 | 494 | 2.1845 | 35.5538 | 19.303 | 33.5533 | 33.5085 | 6.3478 | | 1.8275 | 39.0 | 507 | 2.1867 | 34.6512 | 19.303 | 32.5996 | 32.471 | 7.0 | | 1.8275 | 40.0 | 520 | 2.1881 | 36.4717 | 19.7895 | 34.9234 | 34.7549 | 6.913 | | 1.8275 | 41.0 | 533 | 2.1877 | 36.4717 | 19.7895 | 34.9234 | 34.7549 | 6.913 | | 1.8275 | 42.0 | 546 | 2.1842 | 36.4717 | 19.7895 | 34.9234 | 34.7549 | 6.913 | | 1.8275 | 43.0 | 559 | 2.1869 | 36.4717 | 19.7895 | 34.3175 | 34.1247 | 6.913 | | 1.8275 | 44.0 | 572 | 2.1914 | 36.4717 | 19.7895 | 34.3175 | 34.1247 | 6.913 | | 1.8275 | 45.0 | 585 | 2.1921 | 36.4717 | 19.7895 | 34.3175 | 34.1247 | 6.913 | | 1.8275 | 46.0 | 598 | 2.1910 | 36.4717 | 19.7895 | 34.3175 | 34.1247 | 6.913 | | 1.8275 | 47.0 | 611 | 2.1903 | 34.6512 | 19.303 | 32.5996 | 32.471 | 7.0 | | 1.8275 | 48.0 | 624 | 2.1904 | 34.6512 | 19.303 | 32.5996 | 32.471 | 7.0 | | 1.8275 | 49.0 | 637 | 2.1896 | 34.6512 | 19.303 | 32.5996 | 32.471 | 7.0 | | 1.8275 | 50.0 | 650 | 2.1894 | 34.6512 | 19.303 | 32.5996 | 32.471 | 7.0 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.0 - Tokenizers 0.13.3
AustinCarthy/MixGPT2_subdomain_100KP_BFall_fromP_90K_topP_0.75_ratio2.63
AustinCarthy
2023-06-15T05:44:40Z
0
0
null
[ "tensorboard", "generated_from_trainer", "license:apache-2.0", "region:us" ]
null
2023-06-15T03:32:22Z
--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy - f1 - precision - recall model-index: - name: MixGPT2_subdomain_100KP_BFall_fromP_90K_topP_0.75_ratio2.63 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. --> # MixGPT2_subdomain_100KP_BFall_fromP_90K_topP_0.75_ratio2.63 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the Train benign: Fall,Test Benign: Fall, Train phish: Fall, Test phish: Fall, generated url dataset: generated_phish_MixGPT2_using_phish_95K_top_p_0.75subdomain dataset. It achieves the following results on the evaluation set: - Loss: 0.0273 - Accuracy: 0.9976 - F1: 0.9738 - Precision: 0.9989 - Recall: 0.9498 - Roc Auc Score: 0.9749 - Tpr At Fpr 0.01: 0.9544 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc Score | Tpr At Fpr 0.01 | |:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|:---------:|:------:|:-------------:|:---------------:| | 0.0052 | 1.0 | 21554 | 0.0150 | 0.9972 | 0.9692 | 0.9979 | 0.9422 | 0.9711 | 0.9408 | | 0.0046 | 2.0 | 43108 | 0.0107 | 0.9979 | 0.9778 | 0.9954 | 0.9608 | 0.9803 | 0.9458 | | 0.002 | 3.0 | 64662 | 0.0198 | 0.9973 | 0.9708 | 0.9983 | 0.9448 | 0.9724 | 0.9488 | | 0.0005 | 4.0 | 86216 | 0.0243 | 0.9974 | 0.9721 | 0.9977 | 0.9478 | 0.9738 | 0.947 | | 0.0 | 5.0 | 107770 | 0.0273 | 0.9976 | 0.9738 | 0.9989 | 0.9498 | 0.9749 | 0.9544 | ### Framework versions - Transformers 4.30.1 - Pytorch 2.0.0+cu118 - Datasets 2.12.0 - Tokenizers 0.13.3
soddokayo/klue-roberta-large-klue-2016klp-crime-2-ner
soddokayo
2023-06-15T05:42:19Z
121
0
transformers
[ "transformers", "pytorch", "roberta", "token-classification", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
token-classification
2023-06-15T05:35:12Z
--- tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: klue-roberta-large-klue-2016klp-crime-2-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. --> # klue-roberta-large-klue-2016klp-crime-2-ner This model is a fine-tuned version of [soddokayo/klue-roberta-large-klue-2016klp-ner](https://huggingface.co/soddokayo/klue-roberta-large-klue-2016klp-ner) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.4442 - Precision: 0.1538 - Recall: 0.1124 - F1: 0.1299 - Accuracy: 0.9005 ## 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 | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | No log | 1.0 | 7 | 0.6609 | 0.0 | 0.0 | 0.0 | 0.8536 | | No log | 2.0 | 14 | 0.4892 | 0.02 | 0.0112 | 0.0144 | 0.8817 | | No log | 3.0 | 21 | 0.4442 | 0.1538 | 0.1124 | 0.1299 | 0.9005 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cpu - Datasets 2.12.0 - Tokenizers 0.11.0
gokuls/sa_BERT_no_pretrain_qqp
gokuls
2023-06-15T05:40:30Z
131
0
transformers
[ "transformers", "pytorch", "tensorboard", "bert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-05-29T07:55:56Z
--- language: - en license: apache-2.0 tags: - generated_from_trainer datasets: - glue metrics: - accuracy - f1 model-index: - name: sa_BERT_no_pretrain_qqp results: - task: name: Text Classification type: text-classification dataset: name: GLUE QQP type: glue config: qqp split: validation args: qqp metrics: - name: Accuracy type: accuracy value: 0.7934207271827851 - name: F1 type: f1 value: 0.6836123948783999 --- <!-- 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. --> # sa_BERT_no_pretrain_qqp This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE QQP dataset. It achieves the following results on the evaluation set: - Loss: 0.4355 - Accuracy: 0.7934 - F1: 0.6836 - Combined Score: 0.7385 ## 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: 4e-05 - train_batch_size: 96 - eval_batch_size: 96 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:| | 0.5241 | 1.0 | 3791 | 0.4947 | 0.7638 | 0.6550 | 0.7094 | | 0.4527 | 2.0 | 7582 | 0.4524 | 0.7853 | 0.7027 | 0.7440 | | 0.404 | 3.0 | 11373 | 0.4355 | 0.7934 | 0.6836 | 0.7385 | | 0.3675 | 4.0 | 15164 | 0.4407 | 0.8038 | 0.7438 | 0.7738 | | 0.3315 | 5.0 | 18955 | 0.4426 | 0.8060 | 0.7368 | 0.7714 | | 0.3031 | 6.0 | 22746 | 0.4437 | 0.8067 | 0.7444 | 0.7755 | | 0.2747 | 7.0 | 26537 | 0.4359 | 0.8046 | 0.7523 | 0.7785 | | 0.2441 | 8.0 | 30328 | 0.4718 | 0.8074 | 0.7547 | 0.7811 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
octipuw/RLCourse
octipuw
2023-06-15T05:23:19Z
4
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-15T01:30:54Z
--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PP) results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 260.56 +/- 24.11 name: mean_reward verified: false --- # **PP)** Agent playing **LunarLander-v2** This is a trained model of a **PP)** 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 ... ```
Manirathinam21/M-Bert-base-cased-language-detection
Manirathinam21
2023-06-15T05:09:05Z
103
0
transformers
[ "transformers", "pytorch", "bert", "text-classification", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-14T08:10:30Z
--- license: apache-2.0 --- # Multilingual_Language_Detection This model is a fine-tuned version of [BERT-multilingual-base-(cased)](https://huggingface.co/bert-base-multilingual-cased) on the multilingual dataset. It achieves the following results on the evaluation set: - Training Loss : 0.018700 - Validation Loss : 0.054768 - Accuracy : 0.988864 - F1 : 0.988909 ## Languages It's trained in more than 22 different languages, they are listed below. Arabic, Urdu, Tamil, Hindi, English, French, Spanish, Japanese, Chinese, Thai, Indonesian, Dutch, Korean, Latin, Persian, Portugese, Pushto, Romanian, Russian, Swedish, Turkish, Estonian ## Model Description The BERT model was pretrained on the 104 languages with the largest Wikipedias using a masked language modeling (MLM) objective. This model is case sensitive: it makes a difference between english and English. BERT is a transformers model pretrained on a large corpus of multilingual data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was pretrained with two objectives: - Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run the entire masked sentence through the model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the sentence. - Next sentence prediction (NSP): the models concatenates two masked sentences as inputs during pretraining. Sometimes they correspond to sentences that were next to each other in the original text, sometimes not. The model then has to predict if the two sentences were following each other or not. This way, the model learns an inner representation of the languages in the training set that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard classifier using the features produced by the BERT model as inputs. ## Training procedure Fine-tuning was done via the `Trainer` API. Here is the [Colab notebook](https://colab.research.google.com/drive/1t-IKdGNlroc_-I2QmAPs4b3nHunpLMrn?usp=sharing) with the training code. ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-5 - train_batch_size: 8 - eval_batch_size: 16 - optimizer: Adam - evaluation strategy: epoch - num_epochs: 3 - warmup_steps: 100 ## Training result | Training Loss | Epoch | Validation Loss | Accuracy | F1 | |:-------------:|:-----:|:---------------:|:--------:|:------:| | 0.002800 | 1 | 0.081287 | 0.9888 | 0.9890 | | 0.001100 | 2 | 0.064479 | 0.9897 | 0.9898 | | 0.018700 | 3 | 0.054768 | 0.9888 | 0.9889 |
jkeisling/laura-openllama13b-600bt-ggml
jkeisling
2023-06-15T05:03:24Z
0
2
null
[ "arxiv:2305.11206", "arxiv:2305.14314", "arxiv:2302.13971", "license:apache-2.0", "region:us" ]
null
2023-06-15T03:27:36Z
--- license: apache-2.0 --- ## LaURA: *La*nguage *U*nderstanding, *R*endition, and *A*ssistance LaURA is an open-source, permissively licensed chatbot trained for creative multi-turn conversation and writing. Inspired by the [Less is More for Alignment](https://arxiv.org/abs/2305.11206) paper, this preview release of LaURA is fine-tuned from the [OpenLLaMA-13B 600B token preview](https://huggingface.co/openlm-research/open_llama_13b_600bt) through [QLoRA](https://arxiv.org/abs/2305.14314) training on a small curated dataset derived from a highly prompted [Claude](https://www.anthropic.com/index/introducing-claude)-instant. ### Why use LaURA? LaURA is: - **Creative:** Commercial models like GPT-4 and Claude are trained for succinct, uncontroversial, and grounded output. By contrast, LaURA is trained to write lengthy, well-written, and opinionated answers. - **Incisive and sardonic:** LaURA was trained to produce dry satire when prompted, and unlike corporate models trained on syncophantic output, is much more willing to analyze motivations critically and avoid parroting corporate PR. - **Permissively licensed:** LaURA can be used commercially or in research settings without legal encumbrances. This is an early version of LaURA and future releases will improve, but even this model demonstrates: - **Less is more for alignment:** Only 1000 examples are required for strong, creative instruction-following and multiturn conversation - **Fine-tuning is feasible even for single individuals:** This dataset and fine-tune was created in less than three weeks of work, evenings and weekends, using the wealth of existing open-source models and tools available. #### Examples (cherry-picked) Question-answering: ``` Human: What are 3 albums I might enjoy if I like Tame Impala's "Currents"? Laura: Here are 3 albums you might enjoy if you like Tame Impala's "Currents": Thom Yorke - Tomorrow's Modern Boxes: If you appreciate the dreamy synth-pop and psychedelic rock sounds of "Currents", Thom Yorke's experimental album could be a good complement. It's more minimalist and ambient, using mostly subtle synth textures and plucked strings to create a moody atmosphere. There are a few catchy pop hooks, but the songs stretch out for 7-12 minutes and don't have a traditional structure. Give it a listen and see if it resonates with you. Animal Collective - Strawberry Jam: This album has a similar sound to "Currents", but is more textured and layered with acoustic instruments, found sounds, chimes and other organic textures. If you enjoy the dreamy psychedelia of "Currents", this may be a good option for expanding your musical horizons. There are some catchy pop tunes here, but it's probably best listened to in one sitting as it is quite long. Jamie XX - In Colour: This is more dance-heavy than "Currents" and might appeal to you if you enjoy the groovy synth beats and shimmering textures of "Currents". It integrates elements of house, techno, downtempo and more. Try some tracks like "Gosh", "Strings", or "I Know There's Gonna Be (Good Times)" for synth-based grooves and melodies that start to create a vibe. Human: What are some albums that lean more into the psych-rock side? Laura: Here are some albums that lean more towards the psych-rock side: Tame Impala - Lonerism: Tame Impala's debut full-length album continues their psychedelic, synth rock exploration at a grander scale with longer songs and expanded instrumentation. "Elephant" is a highlight, blending bluesy guitars, funky rhythms, layered echoes and a kind of lysergic atmosphere. Try any track really - they all blend together into an epic psych-rock journey. M83 - Saturdays=Youth: This album by M83 explores dreamy textures, synths that shimmer and twinkle, and songs that stretch out for over 6 minutes in some cases. It's more downtempo and atmospheric than Tame Impala's "Currents" and there are more pop hooks and choruses to capture your attention. Try the haunting "Midnight City" or the upbeat "Reunion" to get a sense of how their sound differs in pace and mood but similarities in texture and psychedelia. Pet Shop Boys - Yes: This album from the Pet Shop Boys continues their synth-pop sound but has a more dreamy, atmospheric quality than their early work. It's sleeker, more lush and cinematic with sounds that evoke rainstorms, glittering dance floors and fuzzy memories of past romances. Try "Love Is a Bourgeois Construct" or "Vocal" for a preview of how their sound evolves into something more ethereal over the course of this album. Beck - Sea Change: Beck's third album is definitely less upbeat, more introspective and melancholic in tone than his early work. It explores moody synth-pop with downtempo rhythms, piano ballads and even some R&B-infused tunes like "Lost Cause". Try the haunting "Wave" or the infectious "Soul of a Man" for a taste of Beck's more subdued yet still captivating style on this album. ``` Analysis: ``` Human: Write an incisive analysis of the impact of Bell Labs 50 years on. Laura: Here is my cynical analysis of Bell Labs for its half-century of dominance in innovation and economic prominence: First, let us examine the source of its power. Bell's corporate structure was uniquely configured to foster scientific progress through top-down management, centralized control, standardization, and vertical integration. Technology developed at Bell Labs quickly spread to other entities through license agreements and strategic partnerships. Second, the scientific ecosystem at Bell Labs was well-suited to supporting deep technological research. Each researcher had access to resources including financial backing, dedicated facilities, and technical staff support. They also shared a common vision with corporate leaders, prioritizing innovation for the sake of progress over short-term market interests. Third, Bell's centralization enabled it to make large investments in research areas with potential for breaking new ground. While competing firms focused on incremental improvements to existing products, Bell could dive fully into ambitious projects like artificial intelligence or cellular technology without worrying about return on investment. The company's size and influence gave it the ability to take risks others were not willing or able to make. Fourth, Bell Labs benefited from the virtuous cycle of prestige and success. Researchers gained recognition for breakthrough innovations, which in turn attracted more talent, funding and resources. Each breakthrough brought press coverage that further burnished the company's image as a hub of innovation. The result was an ongoing cycle of progress and profitability. On the other side, we see an economic model increasingly at odds with emerging realities. The dominance of research alone is a risky strategy in an era where startups outpace established corporations in generating new technologies and business models. Applying the Bell Labs playbook to the modern tech industry would favor centralized models of innovation over distributed networks of hackers and entrepreneurs continually challenging old paradigms. While existing companies may still adopt elements of the Bell practice, the ecosystem of startup funding, incentives for risk-taking and ability to capitalize on emergent trends will likely prevail in driving overall progress. Some combination of corporate-backed scientific research with open source software development and venture/angel investment will define successful firms of the future. But the era of centralized, vertically integrated innovation houses like Bell Labs is likely at an end. In conclusion, while incredible technological advances flowed from Bell Laboratories, the corporate structure that enabled them has been steadily supplanted by more flexible models driven by networked communities and decentralized market forces. Still, some of the principles Bell Labs embodied - deep technical expertise, unwavering commitment to progress, and a focus on innovative solutions rather than short-term profits - remain relevant for companies seeking to create real value through technology. But their model of absolute control of research now seems outdated, less suited to challenging an ever-expanding realm of possibility. Human: What are some of their historical high-profile innovations? Laura: Some well-known innovations from the history of Bell Labs include: • Transistor - The first commercial transistors were developed at Bell Labs in 1947, marking a major milestone in miniaturization and electronics. This invention laid the foundation for modern computers and electronic devices. • Digital computer - The first general-purpose digital computer, UNIVAC I, was built for the US Census Bureau at Bell Labs in 1951. It paved the way for today's supercomputers and digital control systems. • Communication satellite - The first communications satellite (Sputnik) was launched from a Bell Labs-designed rocket in 1957, demonstrating the potential of space-based internet connection and other applications. • Laser - Chemist Charles Townes developed the first laser using a prototype of an element previously discovered at Bell Labs, molybdenum. His creation laid the foundation for fiber optics and modern telecommunications. • CCD camera - Harry Ogletree pioneered the charge-coupled device (CCD), an essential component in digital cameras. The first commercially available CCD was developed at Bell Labs, opening up a new era of digital imaging. • Computer mouse - Douglas Engelbart, an engineer at Xerox PARC working on projects with funding from Bell Labs, developed the computer mouse and other key input devices that laid the foundation for personal computing as we know it. • Watson - The IBM Deep Blue supercomputer used systems of artificial intelligence (AI) to defeat Garry Kasparov in a famous chess match in 1997, demonstrating the potential applications of AI in fields like strategic thinking and advanced decision-making. Watson is named after Bell Labs founder Alexander Graham Bell. • Wireless cellular network and phone - The first wireless cellular network and mobile phone, were developed at Bell Labs in the 1970s, opening up the era of mass mobile communication. • Voice recognition - Researchers at Bell Labs developed the first voice recognition system for phones in the mid-1980s, laying the foundation for today's digital assistants and speech-enabled AI. The "Speechley" system was used by AT&T for customer service. ``` ### Usage These files are in GGML v3 format. You can use these files for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as: - [text-generation-webui](https://github.com/oobabooga/text-generation-webui) - [KoboldCpp](https://github.com/LostRuins/koboldcpp) - [ParisNeo/GPT4All-UI](https://github.com/ParisNeo/gpt4all-ui) - [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) - [ctransformers](https://github.com/marella/ctransformers) #### How to run in llama.cpp Once you've followed the [llama.cpp](https://github.com/ggerganov/llama.cpp) instructions to compile the program, go to the "files and versions" tab on this page and download the file `laura-openllama13b-600bt-q6_K.bin`. I recommend saving it to the `/models` folder in the `llama.cpp` repo. Running this model with `llama.cpp` will require at least 10 GB of RAM or VRAM. To prompt the model, I recommend using the following command: ``` ./main --color -ngl 60 -m ./models/laura-openllama13b-600bt-q6_K.bin -c 2048 -n 512 --mirostat 2 -i -r "Human:" -p "This is a conversation between the helpful, cynical, and well-spoken AI chatbot Laura and a human. Laura's responses clearly and insightfully answer the human's request. Continue the chat from Laura's perspective." ``` Explanation of these arguments: - `-ngl-60`: Offload layers to GPU. Leave this off if running on CPU. - `-c 2048`: Use the full 2048 token context window of the model. - `-n 512`: Allow replies to be up to 512 tokens. The model was trained to output answers 300-700 tokens long. - `-i -r "Human:"` Pause generation when "Human" shows up in the reply - `--mirostat 2`: Use a sampling algorithm which allows more creative output #### Prompt format LaURA was trained using the following instruction format, which I recommend using as the base for your prompts: ``` This is a conversation between the helpful, cynical, and well-spoken AI chatbot Laura and a human. Laura's responses informatively, insightfully, and delightfully answer the human's request. Continue the chat as Laura. --- Human: human_prompt_1 Laura: laura_answer_1 Human: human_prompt_2 # ... ``` The LaURA model was trained to predict both answers _and_ questions. Consider letting LaURA generate your follow-up questions as well! ### License and intended use The LaURA model is available under the [Apache 2.0 license](https://snyk.io/learn/apache-license/), like the OpenLlama base model it was trained on. However, I strongly recommend against using this model in production: - The model was trained with helpful-only input, without guardrails. LaURA may produce problematic outputs. - LaURA was trained on English conversation-only data and has a strong propensity to hallucinate. It is not competitive on standard benchmarks; this is left for future work. ### Model card **Architecture:** LaURA was trained as a QLoRA adapter (hence the name!) on LLaMA models and is added to all layers. I use $r=96$. This repo containes the _merged_ adapter into the OpenLLaMA model, for ease of use. **Base model:** This release is a low-rank fine-tune of the OpenLLaMA 13B preview, trained on 600B tokens. OpenLLaMA is a GPT-style decoder transformer language model pretrained on 600b tokens using Meta's [LLaMA architecture](https://arxiv.org/pdf/2302.13971.pdf). This LaURA release inherits the limitations of the base model. LaURA versions trained on the proprietary LLaMA-13B, other model sizes, and the full OpenLLAMA model are forthcoming. **Finetuning data:** LaURA is trained on a dataset of 1000 question-answer pairs in a multi-turn format. The training data is derived from a larger dataset of ~3000 question-answer pairs from conversations with Anthropic's Claude-instant model, filtered and highly edited for quality, succinctness, and comprehensiveness. This dataset will eventually be open-sourced, but currently contains PII that needs to be redacted before release. #### Training hyperparameters - **Learning rate:** Linear decay from 5e-5 - **Batch size:** 4 with gradient accumulation to 128 - **Sequence length:** 1120 - **Epochs:** 10 - **Dimension:** 96 - **Optimizer:** Adam Model loss at end of training was ~1.78, compared to ~1.63 for the same hyperparameters trained on LLaMA-13b. ### Why is it called LaURA? It's an in-joke to the fine-tuning method, LoRA.
peteozegov/rl_course_vizdoom_health_gathering_supreme
peteozegov
2023-06-15T04:58:08Z
0
0
sample-factory
[ "sample-factory", "tensorboard", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-14T20:37:59Z
--- library_name: sample-factory tags: - deep-reinforcement-learning - reinforcement-learning - sample-factory model-index: - name: APPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: doom_health_gathering_supreme type: doom_health_gathering_supreme metrics: - type: mean_reward value: 10.32 +/- 3.28 name: mean_reward verified: false --- A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment. This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/ ## Downloading the model After installing Sample-Factory, download the model with: ``` python -m sample_factory.huggingface.load_from_hub -r peteozegov/rl_course_vizdoom_health_gathering_supreme ``` ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme ``` You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag. See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details ## Training with this model To continue training with this model, use the `train` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000 ``` Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
ZidanSink/Megy
ZidanSink
2023-06-15T04:45:59Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-15T04:42:25Z
--- license: creativeml-openrail-m ---
francoyisususu/domo
francoyisususu
2023-06-15T04:28:00Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-15T04:28:00Z
--- license: creativeml-openrail-m ---
peteozegov/a2c-PandaReachDense-v2
peteozegov
2023-06-15T04:26:46Z
0
0
stable-baselines3
[ "stable-baselines3", "PandaReachDense-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-05T03:30:25Z
--- 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: -0.90 +/- 0.34 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 ... ```
soddokayo/klue-roberta-large-klue-2016klp-crime-1-ner
soddokayo
2023-06-15T04:21:12Z
124
0
transformers
[ "transformers", "pytorch", "roberta", "token-classification", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
token-classification
2023-06-15T04:13:55Z
--- tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: klue-roberta-large-klue-2016klp-crime-1-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. --> # klue-roberta-large-klue-2016klp-crime-1-ner This model is a fine-tuned version of [soddokayo/klue-roberta-large-klue-2016klp-ner](https://huggingface.co/soddokayo/klue-roberta-large-klue-2016klp-ner) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.7156 - Precision: 0.4934 - Recall: 0.6222 - F1: 0.5504 - Accuracy: 0.7726 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | No log | 1.0 | 23 | 0.8927 | 0.6778 | 0.6778 | 0.6778 | 0.7223 | | No log | 2.0 | 46 | 0.7156 | 0.4934 | 0.6222 | 0.5504 | 0.7726 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cpu - Datasets 2.12.0 - Tokenizers 0.11.0
Laurie/qlora-v1
Laurie
2023-06-15T04:10:06Z
0
0
null
[ "en", "dataset:tatsu-lab/alpaca", "license:apache-2.0", "region:us" ]
null
2023-06-01T10:15:29Z
--- license: apache-2.0 datasets: - tatsu-lab/alpaca language: - en --- model_name_or_path = yahma/llama-13b-hf learning_rate = 1e-4 max_steps = 10000 epoch = 3.08 train_loss = 0.7169 train_runtime = 1 day, 7:23:32.67 train_samples_per_second = 1.416 train_steps_per_second = 0.088
underfit/nli-finetune-model
underfit
2023-06-15T04:06:38Z
16
0
transformers
[ "transformers", "pytorch", "tensorboard", "bert", "text-classification", "generated_from_trainer", "dataset:multi_nli", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-12T03:22:35Z
--- license: apache-2.0 tags: - generated_from_trainer datasets: - multi_nli metrics: - accuracy model-index: - name: nli-finetune-model results: - task: name: Text Classification type: text-classification dataset: name: multi_nli type: multi_nli config: default split: validation_matched args: default metrics: - name: Accuracy type: accuracy value: 0.7793333333333333 --- <!-- 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. --> # nli-finetune-model This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the multi_nli dataset. It achieves the following results on the evaluation set: - Loss: 1.2551 - Accuracy: 0.7793 ## 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: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 1 - num_epochs: 3.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.6813 | 1.0 | 2500 | 0.6655 | 0.7657 | | 0.5632 | 2.0 | 5000 | 1.0409 | 0.778 | | 0.3753 | 3.0 | 7500 | 1.2551 | 0.7793 | ### Framework versions - Transformers 4.28.0 - Pytorch 1.13.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
gokuls/hBERTv2_new_pretrain_48_KD_stsb
gokuls
2023-06-15T04:05:48Z
45
0
transformers
[ "transformers", "pytorch", "tensorboard", "hybridbert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-15T03:55:09Z
--- language: - en tags: - generated_from_trainer datasets: - glue metrics: - spearmanr model-index: - name: hBERTv2_new_pretrain_48_KD_stsb results: - task: name: Text Classification type: text-classification dataset: name: GLUE STSB type: glue config: stsb split: validation args: stsb metrics: - name: Spearmanr type: spearmanr value: 0.23740661914182784 --- <!-- 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. --> # hBERTv2_new_pretrain_48_KD_stsb This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_48_KD](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_48_KD) on the GLUE STSB dataset. It achieves the following results on the evaluation set: - Loss: 2.2142 - Pearson: 0.2484 - Spearmanr: 0.2374 - Combined Score: 0.2429 ## 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: 4e-05 - train_batch_size: 128 - eval_batch_size: 128 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score | |:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:| | 2.3019 | 1.0 | 45 | 2.6041 | 0.1631 | 0.1541 | 0.1586 | | 2.1689 | 2.0 | 90 | 2.4035 | 0.1451 | 0.1550 | 0.1500 | | 1.8521 | 3.0 | 135 | 2.2142 | 0.2484 | 0.2374 | 0.2429 | | 1.6095 | 4.0 | 180 | 2.6155 | 0.2618 | 0.2566 | 0.2592 | | 1.3325 | 5.0 | 225 | 2.9218 | 0.3160 | 0.3098 | 0.3129 | | 1.0639 | 6.0 | 270 | 2.2315 | 0.3486 | 0.3476 | 0.3481 | | 0.8434 | 7.0 | 315 | 2.5364 | 0.3459 | 0.3343 | 0.3401 | | 0.7193 | 8.0 | 360 | 2.3979 | 0.3661 | 0.3633 | 0.3647 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
casque/majicmixHorror_v1
casque
2023-06-15T03:54:21Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-15T03:32:34Z
--- license: creativeml-openrail-m ---
nolanaatama/nythngv45
nolanaatama
2023-06-15T03:53:40Z
0
1
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-15T03:42:59Z
--- license: creativeml-openrail-m ---
WangZeJun/bloom-820m-chat
WangZeJun
2023-06-15T03:45:15Z
1,598
3
transformers
[ "transformers", "pytorch", "safetensors", "bloom", "text-generation", "license:bigscience-bloom-rail-1.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-02T03:07:49Z
--- license: bigscience-bloom-rail-1.0 --- https://github.com/zejunwang1/bloom_tuning 可以通过如下代码调用 bloom-820m-chat 模型来生成对话： ```python from transformers import BloomTokenizerFast, BloomForCausalLM model_name_or_path = "WangZeJun/bloom-820m-chat" tokenizer = BloomTokenizerFast.from_pretrained(model_name_or_path) model = BloomForCausalLM.from_pretrained(model_name_or_path).cuda() model = model.eval() input_pattern = "{}</s>" text = "你好" input_ids = tokenizer(input_pattern.format(text), return_tensors="pt").input_ids input_ids = input_ids.cuda() outputs = model.generate(input_ids, do_sample=True, max_new_tokens=1024, top_p=0.85, temperature=0.3, repetition_penalty=1.2, eos_token_id=tokenizer.eos_token_id) input_ids_len = input_ids.size(1) response_ids = outputs[0][input_ids_len:] response = tokenizer.decode(response_ids) print(response) ```
gokuls/hBERTv2_new_no_pretrain_wnli
gokuls
2023-06-15T03:24:43Z
46
0
transformers
[ "transformers", "pytorch", "tensorboard", "hybridbert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-05-29T12:16:44Z
--- language: - en tags: - generated_from_trainer datasets: - glue metrics: - accuracy model-index: - name: hBERTv2_new_no_pretrain_wnli results: - task: name: Text Classification type: text-classification dataset: name: GLUE WNLI type: glue config: wnli split: validation args: wnli metrics: - name: Accuracy type: accuracy value: 0.5633802816901409 --- <!-- 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. --> # hBERTv2_new_no_pretrain_wnli This model is a fine-tuned version of [](https://huggingface.co/) on the GLUE WNLI dataset. It achieves the following results on the evaluation set: - Loss: 0.6874 - Accuracy: 0.5634 ## 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: 4e-05 - train_batch_size: 128 - eval_batch_size: 128 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.9765 | 1.0 | 5 | 0.6952 | 0.4366 | | 0.723 | 2.0 | 10 | 0.6938 | 0.4648 | | 0.7209 | 3.0 | 15 | 0.6902 | 0.5634 | | 0.7183 | 4.0 | 20 | 0.7155 | 0.5634 | | 0.7155 | 5.0 | 25 | 0.6875 | 0.5634 | | 0.7027 | 6.0 | 30 | 0.6978 | 0.4366 | | 0.6966 | 7.0 | 35 | 0.7161 | 0.4366 | | 0.7077 | 8.0 | 40 | 0.6926 | 0.5634 | | 0.7048 | 9.0 | 45 | 0.7409 | 0.4366 | | 0.7386 | 10.0 | 50 | 0.6874 | 0.5634 | | 0.7104 | 11.0 | 55 | 0.6875 | 0.5634 | | 0.7061 | 12.0 | 60 | 0.7088 | 0.4366 | | 0.6951 | 13.0 | 65 | 0.7009 | 0.4507 | | 0.6995 | 14.0 | 70 | 0.7050 | 0.4366 | | 0.692 | 15.0 | 75 | 0.6976 | 0.3521 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
raphaesq/autotrain-filipino-hate-speech-roberta-tagalog-base-66889136741
raphaesq
2023-06-15T03:23:08Z
108
0
transformers
[ "transformers", "pytorch", "safetensors", "roberta", "text-classification", "autotrain", "unk", "dataset:raphaesq/autotrain-data-filipino-hate-speech-roberta-tagalog-base", "co2_eq_emissions", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-15T03:22:01Z
--- tags: - autotrain - text-classification language: - unk widget: - text: "I love AutoTrain" datasets: - raphaesq/autotrain-data-filipino-hate-speech-roberta-tagalog-base co2_eq_emissions: emissions: 0.20254513588697542 --- # Model Trained Using AutoTrain - Problem type: Binary Classification - Model ID: 66889136741 - CO2 Emissions (in grams): 0.2025 ## Validation Metrics - Loss: 0.301 - Accuracy: 0.857 - Precision: 0.517 - Recall: 0.500 - AUC: 0.876 - F1: 0.509 ## Usage You can use cURL to access this model: ``` $ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/raphaesq/autotrain-filipino-hate-speech-roberta-tagalog-base-66889136741 ``` Or Python API: ``` from transformers import AutoModelForSequenceClassification, AutoTokenizer model = AutoModelForSequenceClassification.from_pretrained("raphaesq/autotrain-filipino-hate-speech-roberta-tagalog-base-66889136741", use_auth_token=True) tokenizer = AutoTokenizer.from_pretrained("raphaesq/autotrain-filipino-hate-speech-roberta-tagalog-base-66889136741", use_auth_token=True) inputs = tokenizer("I love AutoTrain", return_tensors="pt") outputs = model(**inputs) ```
ClueAI/ChatYuan-7B
ClueAI
2023-06-15T03:21:01Z
5
10
transformers
[ "transformers", "pytorch", "llama", "text-generation", "text2text-generation", "zh", "en", "license:gpl-3.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text2text-generation
2023-06-02T07:34:54Z
--- license: gpl-3.0 tags: - text2text-generation pipeline_tag: text2text-generation language: - zh - en --- ChatYuan-7B是一个支持中英双语的功能型对话语言大模型。它是基于LLama-7B模型上继续进行三阶段训练的模型。 三阶段如下： 1. 在中文通用语料上继续预训练500亿中文token 2. 在数百种任务集上进行任务式指令微调训练 3. 在数百万人类反馈数据集上进行指令微调训练 ## 更多细节参考[GitHub](https://github.com/clue-ai/ChatYuan-7B) ## 使用方式 为了遵守LLaMA模型许可证，我们将ChatYuan-7B权重发布为增量权重。您可以将我们的增量权重与原始的LLaMA权重相加，得到ChatYuan-7B权重。 1. 通过原始[LLaMA-7B](https://github.com/facebookresearch/llama)生成LLaMA的hf模型(LLaMA-7B-HF)，可以参考[指导](https://huggingface.co/docs/transformers/main/model_doc/llama), 也可以直接使用[llama-7b-hf](https://huggingface.co/decapoda-research/llama-7b-hf) 2. 合并LLaMA-7B的hf模型和ChatYuan-7B模型成ChatYuan-7B-merge ### 合并脚本 [apply_delta.py](https://huggingface.co/ClueAI/ChatYuan-7B/blob/main/apply_delta.py) ```shell python3 apply_delta.py --base ~/model_weights/LLaMA-7B-HF --delta ~/model_weights/ChatYuan-7B --target ~/model_weights/ChatYuan-7B-merge ``` ## 加载方式 ```python from transformers import LlamaForCausalLM, AutoTokenizer import torch import sys ckpt = "~/model_weights/ChatYuan-7B-merge" device = torch.device('cuda') model = LlamaForCausalLM.from_pretrained(ckpt) tokenizer = AutoTokenizer.from_pretrained(ckpt) ``` ## 推理方式 ```python def answer(prompt): prompt = f"用户：{prompt}\n小元：" input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device) generate_ids = model.generate(input_ids, max_new_tokens=1024, do_sample = True, temperature = 0.7) output = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0] response = output[len(prompt):] return response ``` ## 示例 ``` input: 学前教育专业岗位实习中，在学生方面会存在问题，请提出改进措施。800字 output: 作为学前教育专业的学生，在岗位实习中可能会遇到各种各样的问题，这些问题不仅影响了我们的学习和成长，也影响了我们的教育质量。为了帮助学生更好地完成实习工作，我们提出以下改进措施： 一、提高教育质量 在学前教育专业岗位实习中，教育质量是关键。学生应该掌握教育方法和技能，并且在实践中学习。为了提高教育质量，学校应该从以下几个方面着手： 1. 提供高质量的教育资源。学校应该提供各种教育资源，包括教材、工具和软件等，以帮助学生更好地完成实习工作。 2. 提高教师质量。教师应该具备丰富的教育经验和专业知识，以便更好地指导学生。 3. 提供培训和评估。学校应该为学生提供培训和评估，以帮助学生更好地掌握技能和知识。 二、加强沟通与合作 在岗位实习中，学生应该与老师和同学进行沟通和合作。老师应该与学生保持良好的沟通，以便更好地指导学生。同时，学生也应该与同学进行合作，以便更好地完成实习工作。 为了加强沟通与合作，学校应该从以下几个方面着手： 1. 提供交流渠道。学校应该为学生提供交流渠道，包括线上和线下的交流方式，以便学生与老师和同学之间进行良好的沟通。 2. 提供团队合作机会。学校应该为学生提供团队合作机会，以便学生能够更好地了解和协作。 3. 提供培训和指导。学校应该为学生提供培训和指导，以便学生能够更好地理解和应对问题。 三、保证实习安全 在岗位实习中，学生应该保证自身的安全。学校应该为学生提供安全保障，包括在实习过程中提供帮助和指导，以及在紧急情况下提供支持和帮助。 为了保证实习安全，学校应该从以下几个方面着手： 1. 提供安全教育。学校应该为学生提供安全教育，以便学生能够更好地了解安全要求和安全方法。 2. 提供安全指导。学校应该为学生提供安全指导，以便学生能够更好地掌握实习安全方法。 3. 提供安全保障。学校应该为学生提供安全保障，包括在实习过期中提供帮助和指导，以及在紧急情况下提予支持和帮助。 总之，学前教育专业岗位实习是学生成长和发展的重要阶段。通过提高教育质量、加强沟通与合作和保证实习安全等措施，学校可以帮助学生更好地完成实习工作，提高教育质量和专业技能。 ``` ``` input: 根据标题生成文章：标题：屈臣氏里的化妆品到底怎么样？正文：化妆品，要讲究科学运用，合理搭配。屈臣氏起码是正品连锁店。请继续后面的文字。 output: 作为一家有着数十年历史的正品连锁店，屈臣氏在市场上拥有一定的口碑和信誉。而对于喜欢化妆品的女性来说，屈臣氏里的化妆品也是不可忽视的选择。那么，屈臣氏里的化妆品到底怎么样呢？ 首先，我们需要了解一下屈臣氏的采购政策。屈臣氏一直秉持着“质量第一、信誉商誉、顾客至上”的经营理念，严格按照国家的相关质量标准进行采购管理。在采购过程中，屈臣氏会对每一家供应商进行详细的评估和审核，以确保所采购的商品符合质量标准。 其次，我们需要了解一下屈臣氏销售的化妆品品牌。屈臣氏销售的化妆品品牌非常丰富，包括国内外著名品牌如兰蔻、雅诗兰黛、娇兰、资生堂等。屈臣氏还会不定期地邀请国内外知名化妆品专家来店内进行化妆品推介和使用指导，为顾客提供更专业的服务。 最后，我们需要了解一下屈臣氏销售的化妆品的价格。相比于一些高端专业的化妆品店，屈臣氏的化妆品价格相对较为亲民，但在保证品质的前提下，仍然可以满足大多数消费者的需求。 总之，屈臣氏里的化妆品在品质、销售渠道和价格等方面都具有一定的优势。但是，我们在选择化妆品时，还是需要注重科学的运用和合理的搭配，以达到更好的化妆效果。 ``` ``` input: 帮我写一个英文营销方案，针对iphone output: Marketing Plan for iPhones Introduction iPhones have become the flagship devices of Apple and have gained immense popularity worldwide. With a sleek design, advanced features, and a smooth user interface, iPhones attract and retain customers through their lifetime. Therefore, developing a marketing plan for iPhones is essential to ensure the continued success and growth of the brand. Objectives The primary objective of this marketing plan is to increase the brand awareness and demand for iPhones by targeting potential customers and creating a strong relationship with them. Target Market The target audience for this marketing plan is people who are in the market for a new smartphone. The target audience is classified into three segments: 1. Upgraders: People who are currently using older versions of iPhones and are looking for a new device with advanced features. 2. Switchers: People who are currently using Android smartphones and are looking to switch to iPhones. 3. Newbies: People who have never used an iPhone before and are looking to experience its features for the first time. Tactics To achieve the objectives, the following tactics will be implemented: 1. Advertising Apple's advertising strategy is well-known for its focus on creating an emotional connection with the audience through its advertisements. The marketing campaign will focus on highlighting the advanced features of iPhones and the benefits of using them. The advertisements will be placed on various platforms, including social media, television, and billboards. 2. Product Demonstrations Product demonstrations will be held at Apple stores and other retail outlets to allow potential customers to experience the advanced features of iPhones. This will help people make informed decisions about their next smartphone. 3. Referral Program A referral program will be launched to encourage existing customers to refer their friends to the brand. This will help to attract new customers and retain existing ones. 4. Content Marketing Content marketing will be used to create and share valuable content that will be useful to potential customers. This will include tutorials, guides, and other content that will help people make informed decisions about their next smartphone. Conclusion In conclusion, this marketing plan will help Apple achieve its goals of increasing brand awareness and demand for its products. The tactics employed in this plan will help to attract new customers and retain existing ones by creating a strong relationship with the brand. ``` ## 限制 在当前基础模型和数据训练的模型中仍存在一些问题： 1. 当要求遵循与事实相关的指令时，模型可能会生成事实错误。 2. 由于模型仍然难以识别潜在的有害指令，偶尔会生成有害的回应。 3. 在推理和编码方面仍然需要改进 由于模型仍然存在限制，我们要求开发者只能将开源代码、数据、模型以及通过该项目生成的其他任何成果用于研究目的。不允许商业用途和其他潜在有害的使用场景。
gokuls/hBERTv2_new_no_pretrain_stsb
gokuls
2023-06-15T03:17:28Z
45
0
transformers
[ "transformers", "pytorch", "tensorboard", "hybridbert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-05-29T12:09:44Z
--- language: - en tags: - generated_from_trainer datasets: - glue metrics: - spearmanr model-index: - name: hBERTv2_new_no_pretrain_stsb results: - task: name: Text Classification type: text-classification dataset: name: GLUE STSB type: glue config: stsb split: validation args: stsb metrics: - name: Spearmanr type: spearmanr value: 0.20926356415783265 --- <!-- 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. --> # hBERTv2_new_no_pretrain_stsb This model is a fine-tuned version of [](https://huggingface.co/) on the GLUE STSB dataset. It achieves the following results on the evaluation set: - Loss: 2.2174 - Pearson: 0.1946 - Spearmanr: 0.2093 - Combined Score: 0.2019 ## 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: 4e-05 - train_batch_size: 128 - eval_batch_size: 128 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score | |:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:| | 2.3893 | 1.0 | 45 | 2.3698 | 0.1204 | 0.1138 | 0.1171 | | 1.9589 | 2.0 | 90 | 2.2174 | 0.1946 | 0.2093 | 0.2019 | | 1.6743 | 3.0 | 135 | 2.3481 | 0.2144 | 0.2207 | 0.2175 | | 1.4068 | 4.0 | 180 | 2.5921 | 0.2472 | 0.2519 | 0.2496 | | 1.2205 | 5.0 | 225 | 2.6279 | 0.2718 | 0.2701 | 0.2709 | | 0.9353 | 6.0 | 270 | 2.5440 | 0.3117 | 0.3213 | 0.3165 | | 0.7662 | 7.0 | 315 | 2.3053 | 0.3501 | 0.3519 | 0.3510 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
gokuls/hBERTv2_new_no_pretrain_sst2
gokuls
2023-06-15T03:02:04Z
45
0
transformers
[ "transformers", "pytorch", "tensorboard", "hybridbert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-05-29T11:26:08Z
--- language: - en tags: - generated_from_trainer datasets: - glue metrics: - accuracy model-index: - name: hBERTv2_new_no_pretrain_sst2 results: - task: name: Text Classification type: text-classification dataset: name: GLUE SST2 type: glue config: sst2 split: validation args: sst2 metrics: - name: Accuracy type: accuracy value: 0.7924311926605505 --- <!-- 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. --> # hBERTv2_new_no_pretrain_sst2 This model is a fine-tuned version of [](https://huggingface.co/) on the GLUE SST2 dataset. It achieves the following results on the evaluation set: - Loss: 0.4682 - Accuracy: 0.7924 ## 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: 4e-05 - train_batch_size: 128 - eval_batch_size: 128 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.438 | 1.0 | 527 | 0.4682 | 0.7924 | | 0.2599 | 2.0 | 1054 | 0.6088 | 0.7890 | | 0.2173 | 3.0 | 1581 | 0.4971 | 0.7901 | | 0.1972 | 4.0 | 2108 | 0.6153 | 0.7924 | | 0.1838 | 5.0 | 2635 | 0.5523 | 0.7947 | | 0.1812 | 6.0 | 3162 | 0.6560 | 0.8073 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
Laurie/llama7b-lora-merged
Laurie
2023-06-15T03:01:13Z
7
0
transformers
[ "transformers", "pytorch", "llama", "text-generation", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-14T03:10:27Z
Merge llama7b and lora on alpaca dataset
morokosi/q-Taxi-v3
morokosi
2023-06-15T03:00:58Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-15T03:00:55Z
--- 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="morokosi/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"]) ```
soddokayo/klue-roberta-large-klue-2016klp-crime1-ner
soddokayo
2023-06-15T02:39:40Z
115
0
transformers
[ "transformers", "pytorch", "roberta", "token-classification", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
token-classification
2023-06-15T02:28:27Z
--- tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: klue-roberta-large-klue-2016klp-crime1-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. --> # klue-roberta-large-klue-2016klp-crime1-ner This model is a fine-tuned version of [soddokayo/klue-roberta-large-klue-2016klp-ner](https://huggingface.co/soddokayo/klue-roberta-large-klue-2016klp-ner) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.2425 - Precision: 0.9392 - Recall: 0.9444 - F1: 0.9418 - Accuracy: 0.9517 ## 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: 6 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | No log | 1.0 | 23 | 0.9424 | 0.6486 | 0.6667 | 0.6575 | 0.7183 | | No log | 2.0 | 46 | 0.6026 | 0.7098 | 0.7611 | 0.7346 | 0.8410 | | No log | 3.0 | 69 | 0.4010 | 0.8703 | 0.8944 | 0.8822 | 0.9235 | | No log | 4.0 | 92 | 0.2797 | 0.9066 | 0.9167 | 0.9116 | 0.9416 | | No log | 5.0 | 115 | 0.2845 | 0.9227 | 0.9278 | 0.9252 | 0.9457 | | No log | 6.0 | 138 | 0.2425 | 0.9392 | 0.9444 | 0.9418 | 0.9517 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cpu - Datasets 2.12.0 - Tokenizers 0.11.0
gokuls/add_BERT_no_pretrain_mnli
gokuls
2023-06-15T02:32:17Z
49
0
transformers
[ "transformers", "pytorch", "tensorboard", "hybridbert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-05-29T09:50:23Z
--- language: - en tags: - generated_from_trainer datasets: - glue metrics: - accuracy model-index: - name: add_BERT_no_pretrain_mnli results: - task: name: Text Classification type: text-classification dataset: name: GLUE MNLI type: glue config: mnli split: validation_matched args: mnli metrics: - name: Accuracy type: accuracy value: 0.3522172497965826 --- <!-- 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. --> # add_BERT_no_pretrain_mnli This model is a fine-tuned version of [](https://huggingface.co/) on the GLUE MNLI dataset. It achieves the following results on the evaluation set: - Loss: 1.0984 - Accuracy: 0.3522 ## 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: 4e-05 - train_batch_size: 128 - eval_batch_size: 128 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:| | 1.1024 | 1.0 | 3068 | 1.0987 | 0.3182 | | 1.0997 | 2.0 | 6136 | 1.0986 | 0.3274 | | 1.0988 | 3.0 | 9204 | 1.0984 | 0.3545 | | 1.0987 | 4.0 | 12272 | 1.0986 | 0.3545 | | 1.0986 | 5.0 | 15340 | 1.0986 | 0.3545 | | 1.0987 | 6.0 | 18408 | 1.0986 | 0.3274 | | 1.0986 | 7.0 | 21476 | 1.0986 | 0.3274 | | 1.0986 | 8.0 | 24544 | 1.0986 | 0.3274 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
ZhangCheng/T5v1.1-Base-Fine-Tuned-for-Question-Generation
ZhangCheng
2023-06-15T02:03:11Z
115
4
transformers
[ "transformers", "pytorch", "safetensors", "t5", "text2text-generation", "Question Generation", "en", "dataset:squad", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text2text-generation
2022-03-02T23:29:05Z
--- language: en datasets: - squad tags: - Question Generation widget: - text: "<answer> T5v1.1 <context> Cheng fine-tuned T5v1.1 on SQuAD for question generation." example_title: "Example 1" - text: "<answer> SQuAD <context> Cheng fine-tuned T5v1.1 on SQuAD dataset for question generation." example_title: "Example 2" - text: "<answer> thousands <context> Transformers provides thousands of pre-trained models to perform tasks on different modalities such as text, vision, and audio." example_title: "Example 3" --- # T5v1.1-Base Fine-Tuned on SQuAD for Question Generation ### Model in Action: ```python import torch from transformers import T5Tokenizer, T5ForConditionalGeneration trained_model_path = 'ZhangCheng/T5v1.1-Base-Fine-Tuned-for-Question-Generation' trained_tokenizer_path = 'ZhangCheng/T5v1.1-Base-Fine-Tuned-for-Question-Generation' class QuestionGeneration: def __init__(self): self.model = T5ForConditionalGeneration.from_pretrained(trained_model_path) self.tokenizer = T5Tokenizer.from_pretrained(trained_tokenizer_path) self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') self.model = self.model.to(self.device) self.model.eval() def generate(self, answer:str, context:str): input_text = '<answer> %s <context> %s ' % (answer, context) encoding = self.tokenizer.encode_plus( input_text, return_tensors='pt' ) input_ids = encoding['input_ids'].to(self.device) attention_mask = encoding['attention_mask'].to(self.device) outputs = self.model.generate( input_ids = input_ids, attention_mask = attention_mask ) question = self.tokenizer.decode( outputs[0], skip_special_tokens = True, clean_up_tokenization_spaces = True ) return {'question': question, 'answer': answer} if __name__ == "__main__": context = 'ZhangCheng fine-tuned T5v1.1 on SQuAD dataset for question generation.' answer = 'ZhangCheng' QG = QuestionGeneration() qa = QG.generate(answer, context) print(qa['question']) # Output: # Who fine-tuned T5v1.1 on SQuAD? ```
ZhangCheng/T5-Base-finetuned-for-Question-Generation
ZhangCheng
2023-06-15T02:00:56Z
176
14
transformers
[ "transformers", "pytorch", "tf", "safetensors", "t5", "text2text-generation", "Question Generation", "en", "dataset:squad", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text2text-generation
2022-03-02T23:29:05Z
--- language: en datasets: - squad tags: - Question Generation widget: - text: "<answer> T5 <context> Cheng fine-tuned T5 on SQuAD for question generation." example_title: "Example 1" - text: "<answer> SQuAD <context> Cheng fine-tuned T5 on SQuAD dataset for question generation." example_title: "Example 2" - text: "<answer> thousands <context> Transformers provides thousands of pre-trained models to perform tasks on different modalities such as text, vision, and audio." example_title: "Example 3" --- # T5-Base Fine-Tuned on SQuAD for Question Generation ### Model in Action: ```python import torch from transformers import T5Tokenizer, T5ForConditionalGeneration trained_model_path = 'ZhangCheng/T5-Base-Fine-Tuned-for-Question-Generation' trained_tokenizer_path = 'ZhangCheng/T5-Base-Fine-Tuned-for-Question-Generation' class QuestionGeneration: def __init__(self, model_dir=None): self.model = T5ForConditionalGeneration.from_pretrained(trained_model_path) self.tokenizer = T5Tokenizer.from_pretrained(trained_tokenizer_path) self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') self.model = self.model.to(self.device) self.model.eval() def generate(self, answer: str, context: str): input_text = '<answer> %s <context> %s ' % (answer, context) encoding = self.tokenizer.encode_plus( input_text, return_tensors='pt' ) input_ids = encoding['input_ids'] attention_mask = encoding['attention_mask'] outputs = self.model.generate( input_ids=input_ids, attention_mask=attention_mask ) question = self.tokenizer.decode( outputs[0], skip_special_tokens=True, clean_up_tokenization_spaces=True ) return {'question': question, 'answer': answer, 'context': context} if __name__ == "__main__": context = 'ZhangCheng fine-tuned T5 on SQuAD dataset for question generation.' answer = 'ZhangCheng' QG = QuestionGeneration() qa = QG.generate(answer, context) print(qa['question']) # Output: # Who fine-tuned T5 on SQuAD dataset for question generation? ```
arminmrm93/qtable_taxi_v3
arminmrm93
2023-06-15T01:46:33Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-15T01:46:28Z
--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: qtable_taxi_v3 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.48 +/- 2.77 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="arminmrm93/qtable_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"]) ```
gokuls/hBERTv1_new_pretrain_48_KD_wnli
gokuls
2023-06-15T01:40:47Z
45
0
transformers
[ "transformers", "pytorch", "tensorboard", "hybridbert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-15T01:36:10Z
--- language: - en tags: - generated_from_trainer datasets: - glue metrics: - accuracy model-index: - name: hBERTv1_new_pretrain_48_KD_wnli results: - task: name: Text Classification type: text-classification dataset: name: GLUE WNLI type: glue config: wnli split: validation args: wnli metrics: - name: Accuracy type: accuracy value: 0.5633802816901409 --- <!-- 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. --> # hBERTv1_new_pretrain_48_KD_wnli This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_48_KD](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_48_KD) on the GLUE WNLI dataset. It achieves the following results on the evaluation set: - Loss: 0.6854 - Accuracy: 0.5634 ## 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: 4e-05 - train_batch_size: 128 - eval_batch_size: 128 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.7548 | 1.0 | 5 | 0.7991 | 0.4366 | | 0.7094 | 2.0 | 10 | 0.7048 | 0.4366 | | 0.7546 | 3.0 | 15 | 0.6934 | 0.4789 | | 0.7016 | 4.0 | 20 | 0.6999 | 0.4366 | | 0.705 | 5.0 | 25 | 0.6859 | 0.5634 | | 0.701 | 6.0 | 30 | 0.7016 | 0.4366 | | 0.6975 | 7.0 | 35 | 0.6854 | 0.5634 | | 0.6952 | 8.0 | 40 | 0.6945 | 0.4507 | | 0.7021 | 9.0 | 45 | 0.7181 | 0.4366 | | 0.7039 | 10.0 | 50 | 0.6879 | 0.5634 | | 0.698 | 11.0 | 55 | 0.6941 | 0.4507 | | 0.6953 | 12.0 | 60 | 0.6997 | 0.4225 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
arminmrm93/q-FrozenLake-v1-4x4-noSlippery
arminmrm93
2023-06-15T01:38:07Z
0
0
null
[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-15T01:38:05Z
--- 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="arminmrm93/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"]) ```
joohwan/a9a7a9a0
joohwan
2023-06-15T01:33:33Z
105
0
transformers
[ "transformers", "pytorch", "tensorboard", "wav2vec2", "automatic-speech-recognition", "generated_from_trainer", "endpoints_compatible", "region:us" ]
automatic-speech-recognition
2023-06-15T01:12:01Z
--- tags: - generated_from_trainer model-index: - name: a9a7a9a0 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. --> # a9a7a9a0 This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - 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 - lr_scheduler_warmup_steps: 1000 - num_epochs: 5 ### Training results ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 1.18.3 - Tokenizers 0.13.3
coreml-community/coreml-lyriel_v16
coreml-community
2023-06-15T01:28:41Z
0
6
null
[ "coreml", "stable-diffusion", "text-to-image", "license:creativeml-openrail-m", "region:us" ]
text-to-image
2023-05-23T01:02:09Z
--- license: creativeml-openrail-m tags: - coreml - stable-diffusion - text-to-image inference: true --- # Core ML Converted Model: - This model was converted to [Core ML for use on Apple Silicon devices](https://github.com/apple/ml-stable-diffusion). Conversion instructions can be found [here](https://github.com/godly-devotion/MochiDiffusion/wiki/How-to-convert-ckpt-or-safetensors-files-to-Core-ML). - Provide the model to an app such as **Mochi Diffusion** [Github](https://github.com/godly-devotion/MochiDiffusion) / [Discord](https://discord.gg/x2kartzxGv) to generate images. - `split_einsum` version is compatible with all compute unit options including Neural Engine. - `original` version is only compatible with `CPU & GPU` option. - Custom resolution versions are tagged accordingly. - The `vae-ft-mse-840000-ema-pruned.ckpt` VAE is embedded into the model. - This model was converted with a `vae-encoder` for use with `image2image`. - This model is `fp16`. - Descriptions are posted as-is from original model source. - Not all features and/or results may be available in `CoreML` format. - This model does not have the [unet split into chunks](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml). - This model does not include a `safety checker` (for NSFW content).<br> # lyriel_v16 Source(s): [CivitAI](https://civitai.com/models/22922)<br> <img class="mantine-7aj0so" src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c028d3fe-669c-44c0-9eac-b9d67f729492/width=450/00014-1261263585.jpeg" alt="00014-1261263585.png" style="max-height: 100%; max-width: 100%;"> <img class="mantine-7aj0so" src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/8aa5c19b-57a2-4a02-9a62-61320f459ef5/width=450/00008-3464469766.jpeg" alt="00008-3464469766.png" style="max-height: 100%; max-width: 100%;"> <img class="mantine-7aj0so" src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/95d66227-e6ac-4140-b187-355e111ee197/width=450/00018-2085175018.jpeg" alt="00018-2085175018.png" style="max-height: 100%; max-width: 100%;"> <img class="mantine-7aj0so" src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/21ac6b1e-ac11-4012-80d1-b0ea14951c5f/width=450/00029-1583775480.jpeg" alt="00029-1583775480.png" style="max-height: 100%; max-width: 100%;"> <img class="mantine-7aj0so" src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/8ce261c6-759d-46fc-b8c1-f4a46cb449d4/width=450/00023-376328055.jpeg" alt="00023-376328055.png" style="max-height: 100%; max-width: 100%;"> Hello, the model was created as an artistic style, the model can do almost anything, the main thing is to follow the promt, hands and eyes looks good for the most cases Model Information: This model is generally designed for portraits and full-length anime style photos. Fantastic landscapes are quite decent. And it doesn't require kilometer-long queries to get a high-quality result. Recommend: DPM++2M Karras, Clip skip 2 Sampler, Steps: 25-35+ This model would not have come out without XpucT's help, which made Deliberate If you have the desire and means to support future models, here you go: Advanced Cash - U 1281 8592 6885 , E 8642 3924 9315 , R 1339 7462 2915 PEYEER - P1075963156 I hope you like it, thanks for the feedback Hide
gokuls/hBERTv2_new_no_pretrain_rte
gokuls
2023-06-15T01:26:33Z
47
0
transformers
[ "transformers", "pytorch", "tensorboard", "hybridbert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-05-29T11:20:34Z
--- language: - en tags: - generated_from_trainer datasets: - glue metrics: - accuracy model-index: - name: hBERTv2_new_no_pretrain_rte results: - task: name: Text Classification type: text-classification dataset: name: GLUE RTE type: glue config: rte split: validation args: rte metrics: - name: Accuracy type: accuracy value: 0.5306859205776173 --- <!-- 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. --> # hBERTv2_new_no_pretrain_rte This model is a fine-tuned version of [](https://huggingface.co/) on the GLUE RTE dataset. It achieves the following results on the evaluation set: - Loss: 0.6981 - Accuracy: 0.5307 ## 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: 4e-05 - train_batch_size: 128 - eval_batch_size: 128 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.7697 | 1.0 | 20 | 0.7526 | 0.5271 | | 0.7285 | 2.0 | 40 | 0.7208 | 0.5271 | | 0.7201 | 3.0 | 60 | 0.7112 | 0.5343 | | 0.7043 | 4.0 | 80 | 0.6981 | 0.5307 | | 0.6569 | 5.0 | 100 | 0.7251 | 0.5235 | | 0.5762 | 6.0 | 120 | 0.8571 | 0.4765 | | 0.4336 | 7.0 | 140 | 0.9540 | 0.4765 | | 0.3299 | 8.0 | 160 | 1.2464 | 0.4838 | | 0.2561 | 9.0 | 180 | 1.4299 | 0.5018 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
gokuls/hBERTv2_new_no_pretrain_qqp
gokuls
2023-06-15T01:16:07Z
45
0
transformers
[ "transformers", "pytorch", "tensorboard", "hybridbert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-05-29T06:09:57Z
--- language: - en tags: - generated_from_trainer datasets: - glue metrics: - accuracy - f1 model-index: - name: hBERTv2_new_no_pretrain_qqp results: - task: name: Text Classification type: text-classification dataset: name: GLUE QQP type: glue config: qqp split: validation args: qqp metrics: - name: Accuracy type: accuracy value: 0.7856047489488004 - name: F1 type: f1 value: 0.6930594900849859 --- <!-- 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. --> # hBERTv2_new_no_pretrain_qqp This model is a fine-tuned version of [](https://huggingface.co/) on the GLUE QQP dataset. It achieves the following results on the evaluation set: - Loss: 0.4537 - Accuracy: 0.7856 - F1: 0.6931 - Combined Score: 0.7393 ## 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: 4e-05 - train_batch_size: 128 - eval_batch_size: 128 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:| | 0.5037 | 1.0 | 2843 | 0.4537 | 0.7856 | 0.6931 | 0.7393 | | 0.4066 | 2.0 | 5686 | 0.4549 | 0.7946 | 0.6758 | 0.7352 | | 0.3367 | 3.0 | 8529 | 0.4630 | 0.7950 | 0.6650 | 0.7300 | | 0.2876 | 4.0 | 11372 | 0.5279 | 0.8180 | 0.7598 | 0.7889 | | 0.2498 | 5.0 | 14215 | 0.4857 | 0.8217 | 0.7650 | 0.7933 | | 0.2371 | 6.0 | 17058 | 0.5113 | 0.8216 | 0.7376 | 0.7796 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
mannamvarun/image_denoising
mannamvarun
2023-06-15T00:55:43Z
0
1
null
[ "image-to-image", "en", "region:us" ]
image-to-image
2023-06-15T00:45:52Z
--- language: - en pipeline_tag: image-to-image --- # 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:** Varun Mannam - **Shared by [optional]:** Varun Mannam - **Model type:** Image-to-image regression - **Language(s) (NLP):** [More Information Needed] - **License:** GPL - **Finetuned from model [optional]:** No need ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** https://github.com/ND-HowardGroup/Instant-Image-Denoising/tree/master/Plugins/Image_Denoising_Plugins_Journal - **Paper [optional]:** https://opg.optica.org/optica/fulltext.cfm?uri=optica-9-4-335&id=470659 - **Demo [optional]:** https://github.com/ND-HowardGroup/Instant-Image-Denoising/tree/master/Plugins/Model_validation
AustinCarthy/OnlyPhishGPT2_subdomain_100KP_BFall_fromP_90K_topP_0.75_ratio2.63
AustinCarthy
2023-06-15T00:03:58Z
0
0
null
[ "tensorboard", "generated_from_trainer", "license:apache-2.0", "region:us" ]
null
2023-06-14T21:51:55Z
--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy - f1 - precision - recall model-index: - name: OnlyPhishGPT2_subdomain_100KP_BFall_fromP_90K_topP_0.75_ratio2.63 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. --> # OnlyPhishGPT2_subdomain_100KP_BFall_fromP_90K_topP_0.75_ratio2.63 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the Train benign: Fall,Test Benign: Fall, Train phish: Fall, Test phish: Fall, generated url dataset: generated_phish_OnlyPhishGPT2_using_phish_95K_top_p_0.75subdomain dataset. It achieves the following results on the evaluation set: - Loss: 0.0219 - Accuracy: 0.9978 - F1: 0.9769 - Precision: 0.9979 - Recall: 0.9568 - Roc Auc Score: 0.9783 - Tpr At Fpr 0.01: 0.9552 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc Score | Tpr At Fpr 0.01 | |:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|:---------:|:------:|:-------------:|:---------------:| | 0.0063 | 1.0 | 21554 | 0.0127 | 0.9974 | 0.9725 | 0.9933 | 0.9526 | 0.9761 | 0.914 | | 0.0038 | 2.0 | 43108 | 0.0136 | 0.9977 | 0.9751 | 0.9940 | 0.957 | 0.9784 | 0.8992 | | 0.0015 | 3.0 | 64662 | 0.0147 | 0.9977 | 0.9755 | 0.9958 | 0.956 | 0.9779 | 0.9498 | | 0.001 | 4.0 | 86216 | 0.0123 | 0.9981 | 0.9798 | 0.9979 | 0.9624 | 0.9812 | 0.9622 | | 0.0 | 5.0 | 107770 | 0.0219 | 0.9978 | 0.9769 | 0.9979 | 0.9568 | 0.9783 | 0.9552 | ### Framework versions - Transformers 4.30.1 - Pytorch 2.0.0+cu118 - Datasets 2.12.0 - Tokenizers 0.13.3
escaa/my_awesome_model
escaa
2023-06-14T23:59:46Z
65
0
transformers
[ "transformers", "tf", "distilbert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-05-13T14:19:17Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: escaa/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. --> # escaa/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: 0.0804 - Validation Loss: 0.1653 - Train Accuracy: 0.9463 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 37500, '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 | |:----------:|:---------------:|:--------------:|:-----:| | 0.2161 | 0.1680 | 0.9432 | 0 | | 0.1254 | 0.1625 | 0.9455 | 1 | | 0.0804 | 0.1653 | 0.9463 | 2 | ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.0 - Tokenizers 0.13.3
w4yw4rd/q-FrozenLake-v1-4x4-noSlippery
w4yw4rd
2023-06-14T23:45:23Z
0
0
null
[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-14T23:45:21Z
--- 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="w4yw4rd/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"]) ```
sdan/simple-embeddings
sdan
2023-06-14T23:42:54Z
5
0
transformers.js
[ "transformers.js", "onnx", "bert", "feature-extraction", "region:us" ]
feature-extraction
2023-06-14T23:40:03Z
--- library_name: "transformers.js" --- https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2 with ONNX weights to be compatible with Transformers.js. Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
peteozegov/q-Taxi-v3
peteozegov
2023-06-14T23:36:48Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-05-30T22:06:48Z
--- 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: 8.40 +/- 2.54 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **FrozenLake-v1** This is a trained model of a **Q-Learning** agent playing **Taxi-v3** . ## Usage ```python model = load_from_hub(repo_id="peteozegov/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"]) ```
vdo/Video-LLaMA-Series
vdo
2023-06-14T23:18:34Z
0
10
null
[ "visual-question-answering", "en", "zh", "arxiv:2306.02858", "license:bsd-3-clause", "region:us" ]
visual-question-answering
2023-06-14T21:17:36Z
--- license: bsd-3-clause language: - en - zh pipeline_tag: visual-question-answering --- # Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding This is the Hugging Face repo for storing pre-trained & fine-tuned checkpoints of our [Video-LLaMA](https://arxiv.org/abs/2306.02858), which is a multi-modal conversational large language model with video understanding capability. ## Vision-Language Branch | Checkpoint | Link | Note | |:------------|-------------|-------------| | pretrain-vicuna7b | [link](https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-Series/resolve/main/pretrain_vicuna7b-v2.pth) | Pre-trained on WebVid (2.5M video-caption pairs) and LLaVA-CC3M (595k image-caption pairs) | | finetune-vicuna7b-v2 | [link](https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-Series/resolve/main/finetune-vicuna7b-v2.pth) | Fine-tuned on the instruction-tuning data from [MiniGPT-4](https://github.com/Vision-CAIR/MiniGPT-4), [LLaVA](https://github.com/haotian-liu/LLaVA) and [VideoChat](https://github.com/OpenGVLab/Ask-Anything)| | pretrain-vicuna13b | [link](https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-Series/resolve/main/pretrain-vicuna13b.pth) | Pre-trained on WebVid (2.5M video-caption pairs) and LLaVA-CC3M (595k image-caption pairs) | | finetune-vicuna13b-v2 | [link](https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-Series/resolve/main/finetune-vicuna13b-v2.pth) | Fine-tuned on the instruction-tuning data from [MiniGPT-4](https://github.com/Vision-CAIR/MiniGPT-4), [LLaVA](https://github.com/haotian-liu/LLaVA) and [VideoChat](https://github.com/OpenGVLab/Ask-Anything)| | pretrain-ziya13b-zh | [link](https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-Series/resolve/main/pretrain-ziya13b-zh.pth) | Pre-trained with Chinese LLM [Ziya-13B](https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-v1) | | finetune-ziya13b-zh | [link](https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-Series/resolve/main/finetune-ziya13b-zh.pth) | Fine-tuned on machine-translated [VideoChat](https://github.com/OpenGVLab/Ask-Anything) instruction-following dataset (in Chinese)| | pretrain-billa7b-zh | [link](https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-Series/resolve/main/pretrain-billa7b-zh.pth) | Pre-trained with Chinese LLM [BiLLA-7B](https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-v1) | | finetune-billa7b-zh | [link](https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-Series/resolve/main/finetune-billa7b-zh.pth) | Fine-tuned on machine-translated [VideoChat](https://github.com/OpenGVLab/Ask-Anything) instruction-following dataset (in Chinese) | ## Audio-Language Branch | Checkpoint | Link | Note | |:------------|-------------|-------------| | pretrain-vicuna7b | [link](https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-Series/resolve/main/pretrain_vicuna7b_audiobranch.pth) | Pre-trained on WebVid (2.5M video-caption pairs) and LLaVA-CC3M (595k image-caption pairs) | | finetune-vicuna7b-v2 | [link](https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-Series/resolve/main/finetune_vicuna7b_audiobranch.pth) | Fine-tuned on the instruction-tuning data from [MiniGPT-4](https://github.com/Vision-CAIR/MiniGPT-4), [LLaVA](https://github.com/haotian-liu/LLaVA) and [VideoChat](https://github.com/OpenGVLab/Ask-Anything)| ## Usage For launching the pre-trained Video-LLaMA on your own machine, please refer to our [github repo](https://github.com/DAMO-NLP-SG/Video-LLaMA).
hangeol/7
hangeol
2023-06-14T23:18:10Z
31
0
diffusers
[ "diffusers", "tensorboard", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "textual_inversion", "base_model:runwayml/stable-diffusion-v1-5", "base_model:adapter:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]
text-to-image
2023-06-14T22:28:34Z
--- license: creativeml-openrail-m base_model: runwayml/stable-diffusion-v1-5 tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - textual_inversion inference: true --- # Textual inversion text2image fine-tuning - hangeol/7 These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.
patrickvonplaten/wav2vec2-common_voice-tr-mms-demo
patrickvonplaten
2023-06-14T23:14:22Z
15
0
transformers
[ "transformers", "pytorch", "tensorboard", "wav2vec2", "automatic-speech-recognition", "common_voice", "generated_from_trainer", "mms", "tr", "dataset:common_voice", "license:cc-by-nc-4.0", "model-index", "endpoints_compatible", "region:us" ]
automatic-speech-recognition
2023-06-14T20:52:57Z
--- language: - tr license: cc-by-nc-4.0 tags: - automatic-speech-recognition - common_voice - generated_from_trainer - mms datasets: - common_voice metrics: - wer model-index: - name: wav2vec2-common_voice-tr-mms-demo-3 results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: COMMON_VOICE - TR type: common_voice config: tr split: test args: 'Config: tr, Training split: train+validation, Eval split: test' metrics: - name: Wer type: wer value: 0.2267388417934838 --- <!-- 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. --> # wav2vec2-common_voice-tr-mms-demo This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the COMMON_VOICE - TR dataset. It achieves the following results on the evaluation set: - Loss: 0.1532 - Wer: 0.2267 ## 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: 0.001 - train_batch_size: 32 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - num_epochs: 4.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-----:|:----:|:---------------:|:------:| | No log | 0.92 | 100 | 0.1822 | 0.2605 | | No log | 1.83 | 200 | 0.1620 | 0.2389 | | No log | 2.75 | 300 | 0.1581 | 0.2318 | | No log | 3.67 | 400 | 0.1535 | 0.2270 | ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
Stevenhpy/unsup-simcse-bert-base-uncased-focal
Stevenhpy
2023-06-14T23:11:49Z
103
0
transformers
[ "transformers", "pytorch", "bert", "feature-extraction", "sentence-similarity", "endpoints_compatible", "region:us" ]
sentence-similarity
2023-06-14T22:55:56Z
--- pipeline_tag: sentence-similarity --- ## How to Get Started with the Model please refer to https://github.com/puerrrr/Focal-InfoNCE ## Model Card Contact pengyue@ualberta.ca
Stevenhpy/unsup-simcse-roberta-base-focal
Stevenhpy
2023-06-14T23:11:36Z
103
0
transformers
[ "transformers", "pytorch", "roberta", "feature-extraction", "sentence-similarity", "endpoints_compatible", "region:us" ]
sentence-similarity
2023-06-14T22:59:06Z
--- pipeline_tag: sentence-similarity --- ## How to Get Started with the Model please refer to https://github.com/puerrrr/Focal-InfoNCE ## Model Card Contact pengyue@ualberta.ca
platzi/vit_model-juan_jose_cano
platzi
2023-06-14T22:42:21Z
192
0
transformers
[ "transformers", "pytorch", "tensorboard", "vit", "image-classification", "generated_from_trainer", "dataset:beans", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
image-classification
2023-06-07T17:35:42Z
--- license: apache-2.0 tags: - generated_from_trainer datasets: - beans metrics: - accuracy widget: - src: https://huggingface.co/platzi/platzi-vit-model-luis-reyes/resolve/main/healthy.jpeg example_title: Healthy - src: https://huggingface.co/platzi/platzi-vit-model-luis-reyes/resolve/main/bean_rust.jpeg example_title: Bean Rust model-index: - name: vit_model-juan_jose_cano results: - task: name: Image Classification type: image-classification dataset: name: beans type: beans config: default split: validation args: default metrics: - name: Accuracy type: accuracy value: 0.9774436090225563 --- <!-- 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. --> # vit_model-juan_jose_cano This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the beans dataset. It achieves the following results on the evaluation set: - Loss: 0.0810 - Accuracy: 0.9774 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 4 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.0568 | 3.85 | 500 | 0.0810 | 0.9774 | ### Framework versions - Transformers 4.28.0 - Pytorch 2.0.1+cu118 - Datasets 2.12.0 - Tokenizers 0.13.3
grantprice/pythia-410m-deduped-finetuned-DND
grantprice
2023-06-14T22:20:49Z
12
0
transformers
[ "transformers", "pytorch", "tensorboard", "gpt_neox", "text-generation", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-09T23:55:57Z
--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: pythia-410m-deduped-finetuned-DND 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. --> # pythia-410m-deduped-finetuned-DND This model is a fine-tuned version of [EleutherAI/pythia-410m-deduped](https://huggingface.co/EleutherAI/pythia-410m-deduped) on the None dataset. It achieves the following results on the evaluation set: - Loss: 4.7177 ## 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: 3.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | No log | 1.0 | 480 | 4.1250 | | 2.4446 | 2.0 | 960 | 4.3426 | | 1.5974 | 3.0 | 1440 | 4.7177 | ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.1+cu118 - Datasets 2.12.0 - Tokenizers 0.13.3
gokuls/hBERTv2_new_pretrain_48_emb_com_qnli
gokuls
2023-06-14T21:37:06Z
47
0
transformers
[ "transformers", "pytorch", "tensorboard", "hybridbert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-14T16:22:16Z
--- language: - en tags: - generated_from_trainer datasets: - glue metrics: - accuracy model-index: - name: hBERTv2_new_pretrain_48_emb_com_qnli results: - task: name: Text Classification type: text-classification dataset: name: GLUE QNLI type: glue config: qnli split: validation args: qnli metrics: - name: Accuracy type: accuracy value: 0.5053999633900788 --- <!-- 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. --> # hBERTv2_new_pretrain_48_emb_com_qnli This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_emb_compress_48](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_emb_compress_48) on the GLUE QNLI dataset. It achieves the following results on the evaluation set: - Loss: 0.6931 - Accuracy: 0.5054 ## 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: 4e-05 - train_batch_size: 128 - eval_batch_size: 128 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:| | 0.7033 | 1.0 | 819 | 0.7265 | 0.5054 | | 0.6988 | 2.0 | 1638 | 0.6937 | 0.4946 | | 0.6969 | 3.0 | 2457 | 0.6934 | 0.4946 | | 0.6951 | 4.0 | 3276 | 0.6945 | 0.4946 | | 0.6944 | 5.0 | 4095 | 0.6963 | 0.5054 | | 0.6944 | 6.0 | 4914 | 0.6946 | 0.5054 | | 0.6945 | 7.0 | 5733 | 0.6959 | 0.4946 | | 0.6943 | 8.0 | 6552 | 0.6931 | 0.5054 | | 0.6938 | 9.0 | 7371 | 0.6937 | 0.5054 | | 0.6939 | 10.0 | 8190 | 0.6944 | 0.4946 | | 0.6936 | 11.0 | 9009 | 0.6940 | 0.4946 | | 0.6937 | 12.0 | 9828 | 0.6933 | 0.4946 | | 0.6937 | 13.0 | 10647 | 0.6987 | 0.4946 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
2weaks/bottle2
2weaks
2023-06-14T21:18:17Z
29
0
diffusers
[ "diffusers", "safetensors", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]
text-to-image
2023-06-14T21:06:06Z
--- license: creativeml-openrail-m tags: - text-to-image - stable-diffusion --- ### bottle2 Dreambooth model trained by 2weaks with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb) Sample pictures of this concept:
lucaordronneau/distilbert-base-uncased-finetuned-OCEAN-sentiment
lucaordronneau
2023-06-14T20:59:57Z
106
0
transformers
[ "transformers", "pytorch", "distilbert", "text-classification", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-14T15:15:56Z
--- license: apache-2.0 language: - en metrics: - accuracy - f1 pipeline_tag: text-classification ---
monke1/bunnio
monke1
2023-06-14T20:52:41Z
6
0
diffusers
[ "diffusers", "safetensors", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]
text-to-image
2023-06-14T20:48:04Z
--- license: creativeml-openrail-m tags: - text-to-image - stable-diffusion --- ### bunnio Dreambooth model trained by monke1 with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb) Sample pictures of this concept: ![0](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(1).jpg) ![1](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(5).jpg) ![2](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(7).jpg) ![3](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(18).jpg) ![4](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(13).jpg) ![5](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(4).jpg) ![6](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(2).jpg) ![7](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(28).png) ![8](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(14).jpg) ![9](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(8).jpg) ![10](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(15).jpg) ![11](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(11).jpg) ![12](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(3).jpg) ![13](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(23).jpg) ![14](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(17).jpg) ![15](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(6).jpg) ![16](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(12).jpg) ![17](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(9).jpg) ![18](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(16).jpg) ![19](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(21).jpg) ![20](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(20).jpg) ![21](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(24).jpg) ![22](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(26).jpg) ![23](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(22).jpg) ![24](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(27).jpg) ![25](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(10).jpg) ![26](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(25).jpg) ![27](https://huggingface.co/monke1/bunnio/resolve/main/sample_images/bunnioo_(19).jpg)
Zaid/distilbert-base-uncased-finetuned-cola
Zaid
2023-06-14T20:47:47Z
110
0
transformers
[ "transformers", "pytorch", "tensorboard", "distilbert", "text-classification", "generated_from_trainer", "dataset:glue", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-14T20:41:52Z
--- license: apache-2.0 tags: - generated_from_trainer datasets: - glue metrics: - matthews_correlation model-index: - name: distilbert-base-uncased-finetuned-cola results: - task: name: Text Classification type: text-classification dataset: name: glue type: glue config: cola split: validation args: cola metrics: - name: Matthews Correlation type: matthews_correlation value: 0.5471613867597194 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-finetuned-cola This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset. It achieves the following results on the evaluation set: - Loss: 0.7833 - Matthews Correlation: 0.5472 ## 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 | Matthews Correlation | |:-------------:|:-----:|:----:|:---------------:|:--------------------:| | 0.5216 | 1.0 | 535 | 0.5186 | 0.4153 | | 0.3502 | 2.0 | 1070 | 0.5054 | 0.5065 | | 0.2402 | 3.0 | 1605 | 0.5903 | 0.5275 | | 0.1843 | 4.0 | 2140 | 0.7420 | 0.5370 | | 0.1347 | 5.0 | 2675 | 0.7833 | 0.5472 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.0 - Tokenizers 0.13.3
Alfantin/alfantin-750-325
Alfantin
2023-06-14T20:40:23Z
29
0
diffusers
[ "diffusers", "safetensors", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]
text-to-image
2023-06-14T20:28:06Z
--- license: creativeml-openrail-m tags: - text-to-image - stable-diffusion --- ### alfantin-750-325 Dreambooth model trained by Alfantin with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb) Sample pictures of this concept:
NBRZ/bert-trainer-8b
NBRZ
2023-06-14T20:38:54Z
124
0
transformers
[ "transformers", "pytorch", "tensorboard", "bert", "fill-mask", "generated_from_trainer", "dataset:generator", "autotrain_compatible", "endpoints_compatible", "region:us" ]
fill-mask
2023-06-14T05:44:03Z
--- tags: - generated_from_trainer datasets: - generator model-index: - name: bert-trainer-8b 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-trainer-8b This model is a fine-tuned version of [](https://huggingface.co/) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 3.1639 ## 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: 32 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 6.5416 | 1.0 | 500 | 6.5207 | | 6.393 | 1.99 | 1000 | 6.3903 | | 6.2817 | 2.99 | 1500 | 6.3033 | | 6.2274 | 3.98 | 2000 | 6.2671 | | 6.179 | 4.98 | 2500 | 6.2431 | | 6.1684 | 5.98 | 3000 | 6.2309 | | 6.1244 | 6.97 | 3500 | 6.2114 | | 6.0879 | 7.97 | 4000 | 6.1932 | | 6.0643 | 8.96 | 4500 | 6.1791 | | 6.0481 | 9.96 | 5000 | 6.1638 | | 6.0231 | 10.96 | 5500 | 6.1581 | | 5.9987 | 11.95 | 6000 | 6.1365 | | 5.9989 | 12.95 | 6500 | 6.1194 | | 5.9535 | 13.94 | 7000 | 6.1095 | | 5.9139 | 14.94 | 7500 | 6.0890 | | 5.8462 | 15.94 | 8000 | 6.0224 | | 5.7689 | 16.93 | 8500 | 5.9266 | | 5.6137 | 17.93 | 9000 | 5.7195 | | 4.7163 | 18.92 | 9500 | 4.6131 | | 4.0877 | 19.92 | 10000 | 4.0903 | | 3.7832 | 20.92 | 10500 | 3.8340 | | 3.6104 | 21.91 | 11000 | 3.6572 | | 3.4615 | 22.91 | 11500 | 3.5278 | | 3.3661 | 23.9 | 12000 | 3.4201 | | 3.271 | 24.9 | 12500 | 3.3333 | | 3.2179 | 25.9 | 13000 | 3.2720 | | 3.1759 | 26.89 | 13500 | 3.2317 | | 3.1419 | 27.89 | 14000 | 3.2006 | | 3.1041 | 28.88 | 14500 | 3.1806 | | 3.0836 | 29.88 | 15000 | 3.1693 | | 3.0998 | 30.88 | 15500 | 3.1679 | | 3.08 | 31.87 | 16000 | 3.1639 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1 - Datasets 2.9.0 - Tokenizers 0.13.2
LarryAIDraw/KMS_August_von_Parseval_loar
LarryAIDraw
2023-06-14T20:30:08Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-14T20:27:37Z
--- license: creativeml-openrail-m --- https://civitai.com/models/89994/kms-august-von-parsevalazur-lane
waspa/en_pipeline
waspa
2023-06-14T20:29:07Z
4
0
spacy
[ "spacy", "token-classification", "en", "model-index", "region:us" ]
token-classification
2023-06-14T20:24:35Z
--- tags: - spacy - token-classification language: - en model-index: - name: en_pipeline results: - task: name: NER type: token-classification metrics: - name: NER Precision type: precision value: 1.0 - name: NER Recall type: recall value: 1.0 - name: NER F Score type: f_score value: 1.0 --- | Feature | Description | | --- | --- | | **Name** | `en_pipeline` | | **Version** | `0.0.0` | | **spaCy** | `>=3.2.2,<3.3.0` | | **Default Pipeline** | `tok2vec`, `ner` | | **Components** | `tok2vec`, `ner` | | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) | | **Sources** | n/a | | **License** | n/a | | **Author** | [n/a]() | ### Label Scheme <details> <summary>View label scheme (1 labels for 1 components)</summary> | Component | Labels | | --- | --- | | **`ner`** | `RESTAURANT` | </details> ### Accuracy | Type | Score | | --- | --- | | `ENTS_F` | 100.00 | | `ENTS_P` | 100.00 | | `ENTS_R` | 100.00 | | `TOK2VEC_LOSS` | 0.00 | | `NER_LOSS` | 0.00 |
robinhad/open_llama_7b_uk
robinhad
2023-06-14T20:10:18Z
0
0
null
[ "llama", "text-generation", "uk", "license:apache-2.0", "region:us" ]
text-generation
2023-06-14T19:57:06Z
--- license: apache-2.0 language: - uk pipeline_tag: text-generation tags: - llama --- This is a release of Open LLama, tuned for Ukrainian language. Currently it contains adapter weights, possible subject to change in future.
deepgoyal19/disney_lora
deepgoyal19
2023-06-14T20:01:54Z
4
1
diffusers
[ "diffusers", "tensorboard", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "lora", "base_model:runwayml/stable-diffusion-v1-5", "base_model:adapter:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "region:us" ]
text-to-image
2023-06-14T20:01:46Z
--- license: creativeml-openrail-m base_model: runwayml/stable-diffusion-v1-5 tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - lora inference: true --- # LoRA text2image fine-tuning - deepgoyal19/disney_lora These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the None dataset. You can find some example images in the following.
mudra1710/clip-embeddings
mudra1710
2023-06-14T19:44:06Z
0
0
null
[ "zero-shot-image-classification", "endpoints_compatible", "region:us" ]
zero-shot-image-classification
2023-06-12T17:45:53Z
--- pipeline_tag: zero-shot-image-classification ---
gokuls/hBERTv1_new_pretrain_48_KD_qnli
gokuls
2023-06-14T19:40:51Z
47
0
transformers
[ "transformers", "pytorch", "tensorboard", "hybridbert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-14T17:26:06Z
--- language: - en tags: - generated_from_trainer datasets: - glue metrics: - accuracy model-index: - name: hBERTv1_new_pretrain_48_KD_qnli results: - task: name: Text Classification type: text-classification dataset: name: GLUE QNLI type: glue config: qnli split: validation args: qnli metrics: - name: Accuracy type: accuracy value: 0.6009518579535054 --- <!-- 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. --> # hBERTv1_new_pretrain_48_KD_qnli This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_48_KD](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_48_KD) on the GLUE QNLI dataset. It achieves the following results on the evaluation set: - Loss: 0.6648 - Accuracy: 0.6010 ## 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: 4e-05 - train_batch_size: 128 - eval_batch_size: 128 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.6818 | 1.0 | 819 | 0.6669 | 0.5966 | | 0.6689 | 2.0 | 1638 | 0.6732 | 0.5858 | | 0.6675 | 3.0 | 2457 | 0.6721 | 0.5810 | | 0.663 | 4.0 | 3276 | 0.6793 | 0.5832 | | 0.66 | 5.0 | 4095 | 0.6663 | 0.5999 | | 0.6574 | 6.0 | 4914 | 0.6648 | 0.6010 | | 0.6591 | 7.0 | 5733 | 0.6781 | 0.5731 | | 0.659 | 8.0 | 6552 | 0.6685 | 0.5951 | | 0.6697 | 9.0 | 7371 | 0.6793 | 0.5792 | | 0.6755 | 10.0 | 8190 | 0.6829 | 0.5698 | | 0.6794 | 11.0 | 9009 | 0.6780 | 0.5773 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
thackerhelik/ppo-CleanRL-LunarLander-v2
thackerhelik
2023-06-14T19:40:04Z
0
0
null
[ "tensorboard", "LunarLander-v2", "ppo", "deep-reinforcement-learning", "reinforcement-learning", "custom-implementation", "deep-rl-course", "model-index", "region:us" ]
reinforcement-learning
2023-06-14T17:18:07Z
--- tags: - LunarLander-v2 - ppo - deep-reinforcement-learning - reinforcement-learning - custom-implementation - deep-rl-course model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 117.28 +/- 46.77 name: mean_reward verified: false --- # PPO Agent Playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2. # Hyperparameters ```python {'exp_name': 'ppo' 'gym_id': 'LunarLander-v2' 'learning_rate': 0.00025 'seed': 1 'total_timesteps': 5000000 'torch_deterministic': True 'cuda': True 'capture_video': False 'num_envs': 4 'num_steps': 1024 'anneal_lr': True 'gae': True 'gamma': 0.999 'gae_lambda': 0.98 'num_minibatches': 4 'update_epochs': 4 'norm_adv': True 'clip_coef': 0.2 'clip_vloss': True 'ent_coef': 0.01 'vf_coef': 0.5 'max_grad_norm': 0.5 'target_kl': None 'repo_id': 'thackerhelik/ppo-CleanRL-LunarLander-v2' 'batch_size': 4096 'minibatch_size': 1024} ```
gokuls/hBERTv1_new_pretrain_48_emb_com_qnli
gokuls
2023-06-14T19:36:42Z
45
0
transformers
[ "transformers", "pytorch", "tensorboard", "hybridbert", "text-classification", "generated_from_trainer", "en", "dataset:glue", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-14T16:17:21Z
--- language: - en tags: - generated_from_trainer datasets: - glue metrics: - accuracy model-index: - name: hBERTv1_new_pretrain_48_emb_com_qnli results: - task: name: Text Classification type: text-classification dataset: name: GLUE QNLI type: glue config: qnli split: validation args: qnli metrics: - name: Accuracy type: accuracy value: 0.5983891634632985 --- <!-- 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. --> # hBERTv1_new_pretrain_48_emb_com_qnli This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_emb_compress_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_emb_compress_48) on the GLUE QNLI dataset. It achieves the following results on the evaluation set: - Loss: 0.6611 - Accuracy: 0.5984 ## 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: 4e-05 - train_batch_size: 128 - eval_batch_size: 128 - seed: 10 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.6862 | 1.0 | 819 | 0.6995 | 0.5513 | | 0.6677 | 2.0 | 1638 | 0.6624 | 0.5949 | | 0.6553 | 3.0 | 2457 | 0.6611 | 0.5984 | | 0.6426 | 4.0 | 3276 | 0.6866 | 0.5762 | | 0.6244 | 5.0 | 4095 | 0.6751 | 0.5951 | | 0.6136 | 6.0 | 4914 | 0.6903 | 0.5728 | | 0.6036 | 7.0 | 5733 | 0.7188 | 0.5731 | | 0.5855 | 8.0 | 6552 | 0.7175 | 0.5825 | ### Framework versions - Transformers 4.30.2 - Pytorch 1.14.0a0+410ce96 - Datasets 2.12.0 - Tokenizers 0.13.3
dappradar/setfit-collections-multilabel
dappradar
2023-06-14T19:31:53Z
3
0
sentence-transformers
[ "sentence-transformers", "pytorch", "mpnet", "setfit", "text-classification", "arxiv:2209.11055", "license:apache-2.0", "endpoints_compatible", "region:us" ]
text-classification
2023-06-13T22:16:10Z
--- license: apache-2.0 tags: - setfit - sentence-transformers - text-classification pipeline_tag: text-classification --- # dappradar/setfit-collections-multilabel 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("dappradar/setfit-collections-multilabel") # 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} } ```
abulatk1n/distilbert-base-uncased-tweets-disaster
abulatk1n
2023-06-14T19:25:47Z
103
0
transformers
[ "transformers", "pytorch", "tensorboard", "distilbert", "text-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-13T21:52:43Z
--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy - f1 - precision - recall model-index: - name: distilbert-base-uncased-tweets-disaster results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-tweets-disaster 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: 0.6060 - Accuracy: 0.8189 - F1: 0.8180 - Precision: 0.7945 - Recall: 0.7484 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| | 0.1515 | 1.0 | 113 | 0.5913 | 0.8215 | 0.8197 | 0.8129 | 0.7290 | | 0.1317 | 2.0 | 226 | 0.6060 | 0.8189 | 0.8180 | 0.7945 | 0.7484 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.0 - Tokenizers 0.13.3
leonelhs/faceparser
leonelhs
2023-06-14T19:10:37Z
18
0
transformers
[ "transformers", "vision", "image-segmentation", "makeup", "license:mit", "endpoints_compatible", "region:us" ]
image-segmentation
2023-06-07T21:57:30Z
--- license: mit tags: - vision - image-segmentation - makeup --- ### This is an non official Face Parser model mirror. Reasons of this copy is because AI models can be very fragmented, and its hard to keeping point to an official source. Meanwhile this concern will be solved, the projects listed here, will be using this repo. ### [Face Shine](https://github.com/leonelhs/face-shine) Face Shine Is a backend server for photo enhancement and restoration. ### [Super Face](https://github.com/leonelhs/SuperFace/) Super Face is a Python QT frontend for Face Shine server. <img src="https://drive.google.com/uc?export=view&id=1D7hpjQSlUkzfTba-E5Ul4Rb1c8lYkFj5"/> <img src="https://drive.google.com/uc?export=view&id=1oKpJe-Ff3SeEekhGVRP1Ap3eIFqt0c8u"/>
cambridgeltl/SapBERT-from-PubMedBERT-fulltext
cambridgeltl
2023-06-14T19:03:02Z
1,698,560
43
transformers
[ "transformers", "pytorch", "tf", "jax", "safetensors", "bert", "feature-extraction", "biomedical", "lexical semantics", "bionlp", "biology", "science", "embedding", "entity linking", "en", "arxiv:2010.11784", "license:apache-2.0", "endpoints_compatible", "region:us" ]
feature-extraction
2022-03-02T23:29:05Z
--- license: apache-2.0 language: - en tags: - biomedical - lexical semantics - bionlp - biology - science - embedding - entity linking --- --- datasets: - UMLS **[news]** A cross-lingual extension of SapBERT will appear in the main onference of **ACL 2021**! <br> **[news]** SapBERT will appear in the conference proceedings of **NAACL 2021**! ### SapBERT-PubMedBERT SapBERT by [Liu et al. (2020)](https://arxiv.org/pdf/2010.11784.pdf). Trained with [UMLS](https://www.nlm.nih.gov/research/umls/licensedcontent/umlsknowledgesources.html) 2020AA (English only), using [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) as the base model. ### Expected input and output The input should be a string of biomedical entity names, e.g., "covid infection" or "Hydroxychloroquine". The [CLS] embedding of the last layer is regarded as the output. #### Extracting embeddings from SapBERT The following script converts a list of strings (entity names) into embeddings. ```python import numpy as np import torch from tqdm.auto import tqdm from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("cambridgeltl/SapBERT-from-PubMedBERT-fulltext") model = AutoModel.from_pretrained("cambridgeltl/SapBERT-from-PubMedBERT-fulltext").cuda() # replace with your own list of entity names all_names = ["covid-19", "Coronavirus infection", "high fever", "Tumor of posterior wall of oropharynx"] bs = 128 # batch size during inference all_embs = [] for i in tqdm(np.arange(0, len(all_names), bs)): toks = tokenizer.batch_encode_plus(all_names[i:i+bs], padding="max_length", max_length=25, truncation=True, return_tensors="pt") toks_cuda = {} for k,v in toks.items(): toks_cuda[k] = v.cuda() cls_rep = model(**toks_cuda)[0][:,0,:] # use CLS representation as the embedding all_embs.append(cls_rep.cpu().detach().numpy()) all_embs = np.concatenate(all_embs, axis=0) ``` For more details about training and eval, see SapBERT [github repo](https://github.com/cambridgeltl/sapbert). ### Citation ```bibtex @inproceedings{liu-etal-2021-self, title = "Self-Alignment Pretraining for Biomedical Entity Representations", author = "Liu, Fangyu and Shareghi, Ehsan and Meng, Zaiqiao and Basaldella, Marco and Collier, Nigel", booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies", month = jun, year = "2021", address = "Online", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/2021.naacl-main.334", pages = "4228--4238", abstract = "Despite the widespread success of self-supervised learning via masked language models (MLM), accurately capturing fine-grained semantic relationships in the biomedical domain remains a challenge. This is of paramount importance for entity-level tasks such as entity linking where the ability to model entity relations (especially synonymy) is pivotal. To address this challenge, we propose SapBERT, a pretraining scheme that self-aligns the representation space of biomedical entities. We design a scalable metric learning framework that can leverage UMLS, a massive collection of biomedical ontologies with 4M+ concepts. In contrast with previous pipeline-based hybrid systems, SapBERT offers an elegant one-model-for-all solution to the problem of medical entity linking (MEL), achieving a new state-of-the-art (SOTA) on six MEL benchmarking datasets. In the scientific domain, we achieve SOTA even without task-specific supervision. With substantial improvement over various domain-specific pretrained MLMs such as BioBERT, SciBERTand and PubMedBERT, our pretraining scheme proves to be both effective and robust.", } ```