Datasets:
librarian-bots
/
model_cards_with_metadata

Dataset card Data Studio Files
xet
Community
2
modelId
stringlengths
5
139
author
stringlengths
2
42
last_modified
timestamp[us, tz=UTC]date
2020-02-15 11:33:14
2025-06-28 06:27:35
downloads
int64
0
223M
likes
int64
0
11.7k
library_name
stringclasses
500 values
tags
sequencelengths
1
4.05k
pipeline_tag
stringclasses
54 values
createdAt
timestamp[us, tz=UTC]date
2022-03-02 23:29:04
2025-06-28 06:24:42
card
stringlengths
11
1.01M
sunileman/all-MiniLM-L12-v2
sunileman
2023-12-28T03:19:24Z
11
0
sentence-transformers
[ "sentence-transformers", "pytorch", "safetensors", "bert", "feature-extraction", "sentence-similarity", "dataset:embedding-data/QQP_triplets", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]
sentence-similarity
2023-12-28T03:18:52Z
--- library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity datasets: - embedding-data/QQP_triplets --- # sunileman/all-MiniLM-L12-v2 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search. <!--- Describe your model here --> ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('sunileman/all-MiniLM-L12-v2') embeddings = model.encode(sentences) print(embeddings) ``` ## Evaluation Results <!--- Describe how your model was evaluated --> For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sunileman/all-MiniLM-L12-v2) ## Training The model was trained with the parameters: **DataLoader**: `torch.utils.data.dataloader.DataLoader` of length 3181 with parameters: ``` {'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} ``` **Loss**: `sentence_transformers.losses.TripletLoss.TripletLoss` with parameters: ``` {'distance_metric': 'TripletDistanceMetric.EUCLIDEAN', 'triplet_margin': 5} ``` Parameters of the fit()-Method: ``` { "epochs": 1, "evaluation_steps": 0, "evaluator": "NoneType", "max_grad_norm": 1, "optimizer_class": "<class 'torch.optim.adamw.AdamW'>", "optimizer_params": { "lr": 2e-05 }, "scheduler": "WarmupLinear", "steps_per_epoch": null, "warmup_steps": 0, "weight_decay": 0.01 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False}) (2): Normalize() ) ``` ## Citing & Authors <!--- Describe where people can find more information -->
lovejog99/AIA-HW02
lovejog99
2023-12-28T03:13:53Z
0
0
peft
[ "peft", "safetensors", "arxiv:1910.09700", "base_model:meta-llama/Llama-2-7b-chat-hf", "base_model:adapter:meta-llama/Llama-2-7b-chat-hf", "region:us" ]
null
2023-12-23T01:38:34Z
--- library_name: peft base_model: meta-llama/Llama-2-7b-chat-hf --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.7.2.dev0
mikedad/poca-SoccerTwos
mikedad
2023-12-28T03:02:44Z
0
0
ml-agents
[ "ml-agents", "SoccerTwos", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SoccerTwos", "region:us" ]
reinforcement-learning
2023-12-28T03:02:43Z
--- library_name: ml-agents tags: - SoccerTwos - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SoccerTwos --- # **poca** Agent playing **SoccerTwos** This is a trained model of a **poca** agent playing **SoccerTwos** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: mikedad/poca-SoccerTwos 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
tanatapanun/fine-tuned-bart-20-epochs
tanatapanun
2023-12-28T02:41:24Z
9
0
transformers
[ "transformers", "tensorboard", "safetensors", "bart", "text2text-generation", "generated_from_trainer", "base_model:facebook/bart-base", "base_model:finetune:facebook/bart-base", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text2text-generation
2023-12-28T01:27:02Z
--- license: apache-2.0 base_model: facebook/bart-base tags: - generated_from_trainer metrics: - rouge model-index: - name: fine-tuned-bart-20-epochs results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # fine-tuned-bart-20-epochs This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.8098 - Rouge1: 0.3246 - Rouge2: 0.1287 - Rougel: 0.2921 - Rougelsum: 0.2912 - Gen Len: 14.96 ## 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: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 ### Training results | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| | No log | 1.0 | 301 | 0.7895 | 0.2498 | 0.0834 | 0.2162 | 0.2159 | 14.58 | | 1.8122 | 2.0 | 602 | 0.7331 | 0.2226 | 0.0794 | 0.1943 | 0.1931 | 13.51 | | 1.8122 | 3.0 | 903 | 0.7235 | 0.2935 | 0.1013 | 0.2652 | 0.2647 | 14.69 | | 0.6848 | 4.0 | 1204 | 0.7225 | 0.322 | 0.1245 | 0.2867 | 0.2857 | 13.92 | | 0.5826 | 5.0 | 1505 | 0.7238 | 0.322 | 0.1149 | 0.2863 | 0.2854 | 14.81 | | 0.5826 | 6.0 | 1806 | 0.7204 | 0.3255 | 0.1212 | 0.2977 | 0.2963 | 14.98 | | 0.5013 | 7.0 | 2107 | 0.7377 | 0.3061 | 0.1104 | 0.2784 | 0.2767 | 14.84 | | 0.5013 | 8.0 | 2408 | 0.7396 | 0.3092 | 0.1227 | 0.275 | 0.2741 | 14.17 | | 0.4384 | 9.0 | 2709 | 0.7413 | 0.3224 | 0.1271 | 0.2935 | 0.2928 | 14.44 | | 0.3952 | 10.0 | 3010 | 0.7458 | 0.3288 | 0.1302 | 0.2925 | 0.2925 | 15.09 | | 0.3952 | 11.0 | 3311 | 0.7615 | 0.3496 | 0.139 | 0.3139 | 0.3137 | 15.13 | | 0.3626 | 12.0 | 3612 | 0.7733 | 0.3311 | 0.1264 | 0.3057 | 0.3049 | 14.84 | | 0.3626 | 13.0 | 3913 | 0.7779 | 0.3184 | 0.1226 | 0.286 | 0.2857 | 15.02 | | 0.3254 | 14.0 | 4214 | 0.7854 | 0.3258 | 0.1199 | 0.2911 | 0.2915 | 14.89 | | 0.2983 | 15.0 | 4515 | 0.7863 | 0.3346 | 0.1189 | 0.3027 | 0.3009 | 14.93 | | 0.2983 | 16.0 | 4816 | 0.7979 | 0.3201 | 0.117 | 0.2857 | 0.2843 | 15.05 | | 0.2807 | 17.0 | 5117 | 0.8037 | 0.3223 | 0.1216 | 0.291 | 0.2899 | 15.1 | | 0.2807 | 18.0 | 5418 | 0.8048 | 0.3313 | 0.1261 | 0.3003 | 0.2996 | 15.1 | | 0.2653 | 19.0 | 5719 | 0.8114 | 0.3285 | 0.1298 | 0.297 | 0.2963 | 15.01 | | 0.2562 | 20.0 | 6020 | 0.8098 | 0.3246 | 0.1287 | 0.2921 | 0.2912 | 14.96 | ### Framework versions - Transformers 4.36.2 - Pytorch 1.12.1+cu113 - Datasets 2.15.0 - Tokenizers 0.15.0
hamel/tokenfight
hamel
2023-12-28T02:29:50Z
4
0
peft
[ "peft", "tensorboard", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:NousResearch/Llama-2-7b-hf", "base_model:adapter:NousResearch/Llama-2-7b-hf", "4-bit", "bitsandbytes", "region:us" ]
null
2023-12-28T01:42:34Z
--- library_name: peft tags: - axolotl - generated_from_trainer base_model: NousResearch/Llama-2-7b-hf model-index: - name: tokenfight 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. --> [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.3.0` ```yaml base_model: NousResearch/Llama-2-7b-hf model_type: LlamaForCausalLM tokenizer_type: LlamaTokenizer is_llama_derived_model: true load_in_8bit: false load_in_4bit: true strict: false datasets: - path: mhenrichsen/alpaca_2k_test type: alpaca dataset_prepared_path: val_set_size: 0.05 output_dir: ./qlora-out adapter: qlora lora_model_dir: sequence_len: 4096 sample_packing: false pad_to_sequence_len: true lora_r: 32 lora_alpha: 16 lora_dropout: 0.05 lora_target_modules: lora_target_linear: true lora_fan_in_fan_out: wandb_project: wandb_entity: wandb_watch: wandb_name: wandb_log_model: gradient_accumulation_steps: 4 micro_batch_size: 2 num_epochs: 4 optimizer: paged_adamw_32bit lr_scheduler: cosine learning_rate: 0.0002 train_on_inputs: false group_by_length: false bf16: true fp16: false tf32: false gradient_checkpointing: true early_stopping_patience: resume_from_checkpoint: local_rank: logging_steps: 1 xformers_attention: flash_attention: true warmup_steps: 10 evals_per_epoch: 4 eval_table_size: saves_per_epoch: 1 debug: deepspeed: weight_decay: 0.0 fsdp: fsdp_config: special_tokens: bos_token: "<s>" eos_token: "</s>" unk_token: "<unk>" hub_model_id: "hamel/tokenfight" ``` </details><br> # tokenfight This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.0035 ## 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: 2 - eval_batch_size: 2 - seed: 42 - distributed_type: multi-GPU - num_devices: 3 - gradient_accumulation_steps: 4 - total_train_batch_size: 24 - total_eval_batch_size: 6 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - num_epochs: 4 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 1.1753 | 0.01 | 1 | 1.1604 | | 0.9235 | 0.25 | 20 | 0.9296 | | 1.1097 | 0.5 | 40 | 0.9156 | | 0.9275 | 0.76 | 60 | 0.9006 | | 1.0284 | 1.01 | 80 | 0.8942 | | 0.8905 | 1.26 | 100 | 0.8930 | | 0.8952 | 1.51 | 120 | 0.9071 | | 0.8816 | 1.77 | 140 | 0.9189 | | 0.7187 | 2.02 | 160 | 0.9026 | | 0.5115 | 2.27 | 180 | 0.9251 | | 0.6322 | 2.52 | 200 | 0.9525 | | 0.7149 | 2.78 | 220 | 0.9638 | | 0.5881 | 3.03 | 240 | 0.9699 | | 0.5596 | 3.28 | 260 | 0.9750 | | 0.4989 | 3.53 | 280 | 1.0047 | | 0.3654 | 3.79 | 300 | 1.0035 | ### Framework versions - Transformers 4.37.0.dev0 - Pytorch 2.1.0 - Datasets 2.15.0 - Tokenizers 0.15.0 ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.6.0
johnatanebonilla/whisper-small-canario
johnatanebonilla
2023-12-28T02:18:54Z
3
0
transformers
[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "hf-asr-leaderboard", "generated_from_trainer", "es", "dataset:coser_turnos/canario", "base_model:openai/whisper-small", "base_model:finetune:openai/whisper-small", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]
automatic-speech-recognition
2023-12-27T01:32:55Z
--- language: - es license: apache-2.0 base_model: openai/whisper-small tags: - hf-asr-leaderboard - generated_from_trainer datasets: - coser_turnos/canario metrics: - wer model-index: - name: Whisper Small Canario - Johnatan E. Bonilla results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: COSER Canario 1.0 type: coser_turnos/canario args: 'config: cana, split: test' metrics: - name: Wer type: wer value: 86.48078372268274 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Whisper Small Canario - Johnatan E. Bonilla This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the COSER Canario 1.0 dataset. It achieves the following results on the evaluation set: - Loss: 1.2760 - Wer: 86.4808 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.3041 | 3.95 | 1000 | 0.8140 | 104.0241 | | 0.0471 | 7.91 | 2000 | 1.0680 | 109.6910 | | 0.0238 | 11.86 | 3000 | 1.2071 | 92.1929 | | 0.013 | 15.81 | 4000 | 1.2760 | 86.4808 | ### Framework versions - Transformers 4.37.0.dev0 - Pytorch 2.1.0+cu121 - Tokenizers 0.15.0
quantux/ppo-Huggy
quantux
2023-12-28T02:17:20Z
9
0
ml-agents
[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]
reinforcement-learning
2023-12-28T02:17:05Z
--- 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: quantux/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
ntc-ai/SDXL-LoRA-slider.dungeons-and-dragons-cover-artwork
ntc-ai
2023-12-28T01:51:41Z
15
0
diffusers
[ "diffusers", "text-to-image", "stable-diffusion-xl", "lora", "template:sd-lora", "template:sdxl-lora", "sdxl-sliders", "ntcai.xyz-sliders", "concept", "en", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:mit", "region:us" ]
text-to-image
2023-12-28T01:51:38Z
--- language: - en thumbnail: "images/evaluate/dungeons and dragons cover artwork.../dungeons and dragons cover artwork_17_3.0.png" widget: - text: dungeons and dragons cover artwork output: url: images/dungeons and dragons cover artwork_17_3.0.png - text: dungeons and dragons cover artwork output: url: images/dungeons and dragons cover artwork_19_3.0.png - text: dungeons and dragons cover artwork output: url: images/dungeons and dragons cover artwork_20_3.0.png - text: dungeons and dragons cover artwork output: url: images/dungeons and dragons cover artwork_21_3.0.png - text: dungeons and dragons cover artwork output: url: images/dungeons and dragons cover artwork_22_3.0.png tags: - text-to-image - stable-diffusion-xl - lora - template:sd-lora - template:sdxl-lora - sdxl-sliders - ntcai.xyz-sliders - concept - diffusers license: "mit" inference: false instance_prompt: "dungeons and dragons cover artwork" base_model: "stabilityai/stable-diffusion-xl-base-1.0" --- # ntcai.xyz slider - dungeons and dragons cover artwork (SDXL LoRA) | Strength: -3 | Strength: 0 | Strength: 3 | | --- | --- | --- | | <img src="images/dungeons and dragons cover artwork_17_-3.0.png" width=256 height=256 /> | <img src="images/dungeons and dragons cover artwork_17_0.0.png" width=256 height=256 /> | <img src="images/dungeons and dragons cover artwork_17_3.0.png" width=256 height=256 /> | | <img src="images/dungeons and dragons cover artwork_19_-3.0.png" width=256 height=256 /> | <img src="images/dungeons and dragons cover artwork_19_0.0.png" width=256 height=256 /> | <img src="images/dungeons and dragons cover artwork_19_3.0.png" width=256 height=256 /> | | <img src="images/dungeons and dragons cover artwork_20_-3.0.png" width=256 height=256 /> | <img src="images/dungeons and dragons cover artwork_20_0.0.png" width=256 height=256 /> | <img src="images/dungeons and dragons cover artwork_20_3.0.png" width=256 height=256 /> | ## Download Weights for this model are available in Safetensors format. ## Trigger words You can apply this LoRA with trigger words for additional effect: ``` dungeons and dragons cover artwork ``` ## Use in diffusers ```python from diffusers import StableDiffusionXLPipeline from diffusers import EulerAncestralDiscreteScheduler import torch pipe = StableDiffusionXLPipeline.from_single_file("https://huggingface.co/martyn/sdxl-turbo-mario-merge-top-rated/blob/main/topRatedTurboxlLCM_v10.safetensors") pipe.to("cuda") pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config) # Load the LoRA pipe.load_lora_weights('ntc-ai/SDXL-LoRA-slider.dungeons-and-dragons-cover-artwork', weight_name='dungeons and dragons cover artwork.safetensors', adapter_name="dungeons and dragons cover artwork") # Activate the LoRA pipe.set_adapters(["dungeons and dragons cover artwork"], adapter_weights=[2.0]) prompt = "medieval rich kingpin sitting in a tavern, dungeons and dragons cover artwork" negative_prompt = "nsfw" width = 512 height = 512 num_inference_steps = 10 guidance_scale = 2 image = pipe(prompt, negative_prompt=negative_prompt, width=width, height=height, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps).images[0] image.save('result.png') ``` ## Support the Patreon If you like this model please consider [joining our Patreon](https://www.patreon.com/NTCAI). By joining our Patreon, you'll gain access to an ever-growing library of over 680+ unique and diverse LoRAs, covering a wide range of styles and genres. You'll also receive early access to new models and updates, exclusive behind-the-scenes content, and the powerful LoRA slider creator, allowing you to craft your own custom LoRAs and experiment with endless possibilities. Your support on Patreon will allow us to continue developing and refining new models. ## Other resources - [CivitAI](https://civitai.com/user/ntc) - Follow ntc on Civit for even more LoRAs - [ntcai.xyz](https://ntcai.xyz) - See ntcai.xyz to find more articles and LoRAs
zap-thamm/Remote-QLearning-Taxi-v3
zap-thamm
2023-12-28T01:38:14Z
0
0
null
[ "Taxi-v3", "reinforcement-learning", "rl-framework", "model-index", "region:us" ]
reinforcement-learning
2023-12-27T11:16:28Z
--- tags: - Taxi-v3 - reinforcement-learning - rl-framework model-index: - name: Remote-QLearning-Taxi-v3 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: -62.44 +/- 98.75 name: mean_reward verified: false --- # Custom implemented Remote-QLearning agent playing on *Taxi-v3* This is a trained model of an agent playing on the environment *Taxi-v3*. The agent was trained with a Remote-QLearning algorithm and evaluated for 50 episodes. See further agent and evaluation metadata in the according README section. ## Import The Python module used for training and uploading/downloading is [rl-framework](https://github.com/alexander-zap/rl-framework). It is an easy-to-read, plug-and-use Reinforcement Learning framework and provides standardized interfaces and implementations to various Reinforcement Learning methods and environments. Also it provides connectors for the upload and download to popular model version control systems, including the HuggingFace Hub. ## Usage ```python from rl-framework import CustomAgent, CustomAlgorithm # Create new agent instance agent = CustomAgent( algorithm=CustomAlgorithm.Remote-QLearning algorithm_parameters={ ... }, ) # Download existing agent from HF Hub repository_id = "zap-thamm/Remote-QLearning-Taxi-v3" file_name = "algorithm.pkl" agent.download(repository_id=repository_id, filename=file_name) ``` Further examples can be found in the [exploration section of the rl-framework repository](https://github.com/alexander-zap/rl-framework/tree/main/exploration).
jingooo/Huggy
jingooo
2023-12-28T01:36:44Z
1
0
ml-agents
[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]
reinforcement-learning
2023-12-28T01:36:27Z
--- 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: jingooo/Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
kobesar/FinGPT-llama
kobesar
2023-12-28T01:13:46Z
0
0
peft
[ "peft", "pytorch", "llama", "text-classification", "region:us" ]
text-classification
2023-12-25T22:05:57Z
--- library_name: peft pipeline_tag: text-classification --- ## Training procedure ### Framework versions - PEFT 0.5.0
sophiaqho/question_classifier_model_v2
sophiaqho
2023-12-28T01:12:36Z
37
0
transformers
[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "dataset:squad", "dataset:boolq", "base_model:sophiaqho/question_classifier_model", "base_model:finetune:sophiaqho/question_classifier_model", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-12-04T02:24:49Z
--- license: apache-2.0 base_model: sophiaqho/question_classifier_model tags: - generated_from_trainer model-index: - name: question_classifier_model_v2 results: [] datasets: - squad - boolq --- <!-- 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. --> # question_classifier_model_v2 This model is a fine-tuned version of [sophiaqho/question_classifier_model](https://huggingface.co/sophiaqho/question_classifier_model) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0522 ## Model description The model is fine-tuned from DisilBERT ## Intended uses & limitations It can be used as a question classifier, it will output Label 1 if the input question is a "wh" or factoid question, otherwise, it will output Label 0 if the input is a yes/no question. Can be used as part of the input preprocessing for question answering, when the type of question needs to be predetermined. ## Training and evaluation data More information needed ## Training procedure Trained using questions from the SQuAD and BooolQ dataset. ### 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=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | No log | 1.0 | 159 | 0.0591 | | No log | 2.0 | 318 | 0.0509 | | No log | 3.0 | 477 | 0.0522 | ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu118 - Datasets 2.15.0 - Tokenizers 0.15.0
Realgon/N_bert_agnews_padding70model
Realgon
2023-12-28T01:11:44Z
7
0
transformers
[ "transformers", "pytorch", "bert", "text-classification", "generated_from_trainer", "dataset:ag_news", "base_model:google-bert/bert-base-uncased", "base_model:finetune:google-bert/bert-base-uncased", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-12-27T22:21:24Z
--- license: apache-2.0 base_model: bert-base-uncased tags: - generated_from_trainer datasets: - ag_news metrics: - accuracy model-index: - name: N_bert_agnews_padding70model results: - task: name: Text Classification type: text-classification dataset: name: ag_news type: ag_news config: default split: test args: default metrics: - name: Accuracy type: accuracy value: 0.9464473684210526 --- <!-- 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. --> # N_bert_agnews_padding70model This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the ag_news dataset. It achieves the following results on the evaluation set: - Loss: 0.5807 - Accuracy: 0.9464 ## 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: 20 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:------:|:---------------:|:--------:| | 0.1804 | 1.0 | 7500 | 0.1897 | 0.9418 | | 0.1359 | 2.0 | 15000 | 0.1998 | 0.9454 | | 0.1189 | 3.0 | 22500 | 0.2309 | 0.9443 | | 0.0882 | 4.0 | 30000 | 0.2622 | 0.9458 | | 0.0579 | 5.0 | 37500 | 0.3019 | 0.9417 | | 0.0389 | 6.0 | 45000 | 0.3608 | 0.9438 | | 0.0359 | 7.0 | 52500 | 0.3635 | 0.9426 | | 0.0296 | 8.0 | 60000 | 0.4064 | 0.9428 | | 0.015 | 9.0 | 67500 | 0.4595 | 0.9417 | | 0.0191 | 10.0 | 75000 | 0.4516 | 0.9433 | | 0.0146 | 11.0 | 82500 | 0.5207 | 0.9409 | | 0.0138 | 12.0 | 90000 | 0.4787 | 0.9442 | | 0.0108 | 13.0 | 97500 | 0.5216 | 0.9408 | | 0.0071 | 14.0 | 105000 | 0.5377 | 0.9455 | | 0.0047 | 15.0 | 112500 | 0.5283 | 0.9459 | | 0.0035 | 16.0 | 120000 | 0.4928 | 0.9451 | | 0.0007 | 17.0 | 127500 | 0.5760 | 0.9454 | | 0.0004 | 18.0 | 135000 | 0.5759 | 0.9449 | | 0.0002 | 19.0 | 142500 | 0.5637 | 0.9472 | | 0.0003 | 20.0 | 150000 | 0.5807 | 0.9464 | ### Framework versions - Transformers 4.33.2 - Pytorch 2.0.1+cu117 - Datasets 2.14.5 - Tokenizers 0.13.3
aaditya/whisper-tiny_smw
aaditya
2023-12-28T01:10:59Z
2
0
peft
[ "peft", "safetensors", "arxiv:1910.09700", "base_model:openai/whisper-tiny", "base_model:adapter:openai/whisper-tiny", "region:us" ]
null
2023-12-28T01:10:56Z
--- library_name: peft base_model: openai/whisper-tiny --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.7.2.dev0
cesaros02/ppoMlpPolicy-LunarLander-v2
cesaros02
2023-12-28T01:04:43Z
0
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-12-28T01:04:21Z
--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 256.28 +/- 14.68 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
Eugeoter/yolov5-watermark-detection
Eugeoter
2023-12-28T01:03:36Z
0
6
null
[ "license:openrail", "region:us" ]
null
2023-11-05T12:22:02Z
--- license: openrail --- A YOLOV5 object detection model used to detect watermarks in an image.
alexandreacff/zephyr-enem-finetuned-v2
alexandreacff
2023-12-28T00:42:21Z
5
0
peft
[ "peft", "tensorboard", "safetensors", "generated_from_trainer", "base_model:TheBloke/zephyr-7B-alpha-GPTQ", "base_model:adapter:TheBloke/zephyr-7B-alpha-GPTQ", "license:mit", "region:us" ]
null
2023-12-26T22:11:57Z
--- license: mit library_name: peft tags: - generated_from_trainer base_model: TheBloke/zephyr-7B-alpha-GPTQ model-index: - name: zephyr-enem-finetuned-v2 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. --> # zephyr-enem-finetuned-v2 This model is a fine-tuned version of [TheBloke/zephyr-7B-alpha-GPTQ](https://huggingface.co/TheBloke/zephyr-7B-alpha-GPTQ) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results ### Framework versions - PEFT 0.7.1 - Transformers 4.36.2 - Pytorch 1.13.0+cu117 - Datasets 2.15.0 - Tokenizers 0.15.0
behzadnet/Llama-2-7b-chat-hf-sharded-bf16-fine-tuned-adapters_SystemError0.4_Seed105
behzadnet
2023-12-28T00:40:57Z
0
0
peft
[ "peft", "arxiv:1910.09700", "base_model:Trelis/Llama-2-7b-chat-hf-sharded-bf16", "base_model:adapter:Trelis/Llama-2-7b-chat-hf-sharded-bf16", "region:us" ]
null
2023-12-28T00:40:51Z
--- library_name: peft base_model: Trelis/Llama-2-7b-chat-hf-sharded-bf16 --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.7.0.dev0 ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.7.0.dev0
SaladSlayer00/new_model
SaladSlayer00
2023-12-28T00:39:23Z
13
0
transformers
[ "transformers", "tf", "tensorboard", "resnet", "image-classification", "generated_from_keras_callback", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
image-classification
2023-12-24T16:37:49Z
--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_keras_callback model-index: - name: SaladSlayer00/new_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. --> # SaladSlayer00/new_model This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 1.2935 - Validation Loss: 1.6986 - Validation Accuracy: 0.5619 - Epoch: 11 ## 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': 'AdamWeightDecay', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01} - training_precision: float32 ### Training results | Train Loss | Validation Loss | Validation Accuracy | Epoch | |:----------:|:---------------:|:-------------------:|:-----:| | 7.0613 | 4.8451 | 0.0134 | 0 | | 4.6529 | 4.5201 | 0.0658 | 1 | | 4.3215 | 4.1158 | 0.0992 | 2 | | 3.8808 | 3.6981 | 0.1806 | 3 | | 3.4497 | 3.2741 | 0.2553 | 4 | | 3.0361 | 2.9681 | 0.3177 | 5 | | 2.6734 | 2.6529 | 0.3690 | 6 | | 2.3306 | 2.3803 | 0.4091 | 7 | | 2.0284 | 2.1731 | 0.4738 | 8 | | 1.7542 | 1.9839 | 0.4883 | 9 | | 1.5084 | 1.8335 | 0.5284 | 10 | | 1.2935 | 1.6986 | 0.5619 | 11 | ### Framework versions - Transformers 4.36.2 - TensorFlow 2.15.0 - Datasets 2.16.0 - Tokenizers 0.15.0
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.5-lr-5e-5-avg-False-epoch-3
alexshengzhili
2023-12-28T00:36:16Z
0
0
peft
[ "peft", "llava", "region:us" ]
null
2023-12-28T00:35:49Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.3-lr-5e-6-avg-False-epoch-3
alexshengzhili
2023-12-28T00:35:25Z
0
0
peft
[ "peft", "llava", "region:us" ]
null
2023-12-28T00:35:00Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.3-lr-5e-5-avg-False-epoch-3
alexshengzhili
2023-12-28T00:34:34Z
0
0
peft
[ "peft", "llava", "region:us" ]
null
2023-12-28T00:34:08Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.3-lr-5e-5-avg-False-epoch-2
alexshengzhili
2023-12-28T00:34:08Z
0
0
peft
[ "peft", "llava", "region:us" ]
null
2023-12-28T00:33:45Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.1-lr-5e-6-avg-False-epoch-2
alexshengzhili
2023-12-28T00:33:20Z
0
0
peft
[ "peft", "llava", "region:us" ]
null
2023-12-28T00:32:57Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.1-lr-5e-5-avg-False-epoch-3
alexshengzhili
2023-12-28T00:32:57Z
0
0
peft
[ "peft", "llava", "region:us" ]
null
2023-12-28T00:32:33Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.1-lr-5e-5-avg-False-epoch-2
alexshengzhili
2023-12-28T00:32:32Z
0
0
peft
[ "peft", "llava", "region:us" ]
null
2023-12-28T00:32:09Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0
BernierS/SetFit_Suicidal_Risk
BernierS
2023-12-28T00:21:18Z
23
0
sentence-transformers
[ "sentence-transformers", "pytorch", "mpnet", "setfit", "text-classification", "en", "arxiv:2209.11055", "license:mit", "region:us" ]
text-classification
2023-06-14T00:27:11Z
--- license: mit tags: - setfit - sentence-transformers - text-classification pipeline_tag: text-classification language: - en --- # BernierS/SetFit_Suicidal_Risk The full project can be found on GitHub: https://github.com/BernierS/SetFit_Suicidal_Risk 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("BernierS/SetFit_Suicidal_Risk") ``` ## BibTeX entry and citation info (for SetFit) ```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} } ```
megastudyedu/M-SOLAR-10.7B-v1.1-beta
megastudyedu
2023-12-28T00:06:05Z
4,418
6
transformers
[ "transformers", "safetensors", "llama", "text-generation", "conversational", "base_model:upstage/SOLAR-10.7B-Instruct-v1.0", "base_model:finetune:upstage/SOLAR-10.7B-Instruct-v1.0", "license:cc-by-nc-sa-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-12-27T14:46:42Z
--- license: cc-by-nc-sa-4.0 base_model: upstage/SOLAR-10.7B-Instruct-v1.0 --- ## 이 모델은 메가스터디교육(주)과 (주)프리딕션, (주)마이스의 공동연구로 개발된 모델입니다. ## 사용 데이터셋 & Strategy Instruction Fine-Tuning 데이터셋을 구축하기 위해 다양한 시도를 진행하였습니다. 현재 사용한 방법들에 대해서 제대로 된 ablation study가 진행되지 않았기 때문에, 아이디어 위주로 참고해주시길 부탁드립니다 :) ### 1. [kyujinpy/KOR-OpenOrca-Platypus-v2 🙏](https://huggingface.co/datasets/kyujinpy/KOR-OpenOrca-Platypus-v2) ### 2. [KorQuAD 2.1](korquad.github.io) : Training 데이터 중 일부를 추출하여 사용하였습니다. ### 3. AIHUB 기술과학 요약 데이터 - AIHUB 기술과학 요약 데이터의 `context`, `summary`, `clue` 값을 활용하여 Instruction을 포함한 문장 유추 데이터셋을 만들어 활용했습니다. - **원본 데이터** ```json {'context': '<h1>재료 및 방법</h1> <h2>실험 동물</h2> <p>본 연구는 4주령의 C57BL/6 중으로 수컷 퀴 총 20마리를 (주)중앙실혐둥물에서 분양 받아 1주간의 실험실 적응기를 거친 후, 비만을 유도하기 위해 5주간 고지방식이를 자유 섭취토록 하였다. ...', 'summary': '20마리의 C57BL/6 쥐를 사용하여 비만을 유도한 뒤, 통제군과 운동군으로 나누어 8주 동안 다른 치료를 시행한 연구이다. ...', 'clue': [{'clue_text': '본 연구는 4주령의 C57BL/6 중으로 수컷 퀴 총 20마리를 (주)중앙실혐둥물에서 분양 받아 1주간의 실험실 적응기를 거친 후, 비만을 유도하기 위해 5주간 고지방식이를 자유 섭취토록 하였다.', 'clue_start': '35', 'clue_end': '144'}, {'clue_text': '비만 유도 후 통제군(HLC, High fat diet for 5 weeks and low fat diet 8 weeks as the control) 10마리와 운동군(HLE, High fat diet for 5 weeks and low fat diet 8weeks with exercise) 10마리로 무작위 배치한 후 8주간의 운동 처치를 실시하였다.', 'clue_start': '145', 'clue_end': '343'} ...]} ``` - **생성 데이터 Input** ``` //{input_starting_comment} 당신에게 주어진 이 문장들은 어떤 논문의 요약으로, 이를 바탕으로 원래 논문을 유추해야 합니다. 간략화된 본문: //{summary} 20마리의 C57BL/6 쥐를 사용하여 비만을 유도한 뒤, 통제군과 운동군으로 나누어 8주 동안 다른 치료를 시행한 연구이다. 비만 유도는 5주 동안 45\(\%\) 지방 함유량의 고지방 사료를 섭취시켜 이루어졌다. 운동군은 트레드밀 운동을 시행하였으며, 스트레스를 최소화하기 위해 외부 자극이나 전기 충격을 주지 않았다. 운동은 트레드밀을 사용하여 조절이 용이하도록 하였으며, 매일 실험 동물의 상태를 기록하고 점검하였다. //{refer_input_comment} 참조할 문장들: //{clues} 본 연구는 4주령의 C57BL/6 중으로 수컷 퀴 총 20마리를 (주)중앙실혐둥물에서 분양 받아 1주간의 실험실 적응기를 거친 후, 비만을 유도하기 위해 5주간 고지방식이를 자유 섭취토록 하였다. 비만 유도 후 통제군(HLC, High fat diet for 5 weeks and low fat diet 8 weeks as the control) 10마리와 운동군(HLE, High fat diet for 5 weeks and low fat diet 8weeks with exercise) 10마리로 무작위 배치한 후 8주간의 운동 처치를 실시하였다. 운동방법은 운동강도나 운동시간, 운동량의 조절이 용이한 트레드밀운동으로 선택하였다. 본 실험은 운동시 스트레스를 최소화하기 위해 어떠한 외부적 자극이나 전기 충격을 주지 않고 진행 하였다. 운동은 동물 트레드밀 운동전 교육 및 연습을 통하여 충분한 능력을 갖춘자로, 매일 실험일지를 작성하고 실험동물의 상태를 점검하였다. ``` - **생성 데이터 Output** ``` //{output_starting_comment} 제시된 요약에서 전체 논문의 내용을 유추하겠습니다. //{context} <h1>재료 및 방법</h1> <h2>실험 동물</h2> <p>본 연구는 4주령의 C57BL/6 중으로 수컷 퀴 총 20마리를 (주)중앙실혐둥물에서 분양 받아 1주간의 실험실 적응기를 거친 후, ... //{output_ending_comment} 전체 논문을 완성했습니다. 이 논문은 초기 요약에서 제시된 아이디어를 발전시키고 구체화했습니다. ``` {input_starting_comment}, {input_refer_comment}, {output_starting_comment}, {output_ending_comment} 의 코멘트들은 GPT-4를 활용하여 각 코멘트를 패러프레이징하여 데이터셋 생성 시 랜덤하게 입력하였습니다. ### 4. In-House 데이터 : - 메가스터디교육과 프리딕션이 보유한 교육 도메인과 관련된 In-House 데이터를 가공하여 사용했습니다. ### 5. Random Spilt Generation - 1, 2, 3, 4번 데이터를 활용해서 Self-Supervised가 가능한 Instruction FineTuning에 대한 아이디어가 생각나서 데이터를 구성해 학습 데이터로 사용했습니다. - 주어진 텍스트를 "."으로 Split 한 후 "."으로 구분된 리스트를 랜덤하게 셔플 한 후 모델에게 원본 문장들의 순서를 유추하라는 Instrutction을 주어 학습 데이터를 구성하였습니다. - **원본 데이터** ``` 이 요약으로부터 전체 논문을 재작성하는 작업을 시작하겠습니다. <h1>요 약</h1> <p>비선형 반도체 전력변환장치의 사용이 급증함에 따라 전원 측에 발생되는 고조파 및 무효전력을 보상하기 위한 능동전력필터에 관한 연구가 많이 이루어져 왔으며 실용화를 위한 노력이 계속 되고 있다. 그러나 수동필터 대비 능동전력필터의 가격이 아직까지는 고가이기 때문에 이의 상용화가 더디게 진전되고 있는 추세이며, 특히 소·중용량의 능동전력필터의 제어를 위하여 디지털 신호 처리용 프로세서인 DSP(digital signal processor)를 사용하는 경우 아직까지 그 가격이 고가이기 때문에 능동필터의 제어가격을 상승시키는 요인으로 작용한다. 한편 능동전력필터의 가격을 낮추기 위해 아날로그 제어기만을 도입하는 경우 제어회로가 너무 복잡해 지고 제어의 유연성이 떨어지는 단점을 수반하게 된다. 본 논문에서는 3상 \( 5[ \mathrm { kVA } ] \)급 능동전력필터의 저가형 제어기를 구현하기 위해 저가의 원칩 마이크로프로세서인 80C196KC를 사용하여 디지털 제어부를 구성하며 이를 통해 보상전류 성분의 계산 및 직류단 일정 전압제어를 수행하고, 능동필터 시스템의 전류제어를 위하여 아날로그 형태의 제어기인 히스테리시스 제어기를 함께 사용한다. 컴퓨터 시뮬레이션을 통해서 보상 시스템의 특성을 해석하였으며 실험에 의해 능동전력필터의 저가화를 위해 설계된 제어기가 고조파 및 무효전력 보상을 충실히 수행함을 확인하였다.</p> <h1>1. 서 론</h1> <p>비선형 반도체 전력변환장치의 사용이 급증하고 대용량화 되어감에 따라 전원 측에 발생되는 고조파 및 무효전력의 발생은 계통 전원의 질을 떨어뜨리는 심각한 문제로 대두되어 왔으며, 이를 해결하고자 하는 노력이 계속적으로 이루어 지고 있다. 특히 계통내의 고조파를 제거하기 위해서 지속적으로 사용되어 왔던 기존의 수동필터를 대체하는 능동전력필터에 관한 연구가 상당한 진전을 이루어 왔으며 \( d \)- \( q \) 변환 이론을 도입한 보상 검출 알고리즘 및 여러 가지 전류제어기법들의 개발로 3상 전원에서의 고조파 및 무효전력에 관한 보상이 보다 효율적으로 이루어 지게 되었다. 뿐만아니라 전원 측에 발생하는 고조파 및 무효전력 보상을 위한 능동전력필터의 원활한 제어를 위하여 현대제어 이론을 도입한 복잡한 연산과정을 수반하는 제어기들의 등장과 공간벡터 변조기법의 수행을 위해 고속 디지털 프로세서의 사용이 선호되고 보편화 되고 있는 추세에 있다. 그러나 현재 고속 디지털 프로세서로써 많이 사용되고 있는 DSP(Digital Signal Processing) 칩(chip)의 가격이 많이 낮아지기는 했으나 아직까지는 그 가격이 아날로그 회로만을 이용하는 제어기에 비하여 고가이기 때문에 능동전력필터의 제어부 구성에 필요한 가격을 상승시키는 요인으로 작용한다. 특히 소·중용량의 능동필터 시스템이 필요로 되는 경우에는 제어부의 가격이 전체적인 시스템의 가격면에서 차지하는 비중이 크기 때문에 한층 더 고려의 대상이 된다. 반면 능동필터의 제어가격을 낮추기 위해서 아날로그 제어기만을 사용하는 경우 제어회로가 너무 복잡해지고 제어의 유연성이 떨어지는 단점을 수반하게 된다. 따라서 본 논문에서는 능동전력필터의 저가화를 실현하고, 능동필터의 보상 기준전류를 계산하는데 있어 아날로그 제어기 만을 사용하는 경우 발생하는 계산상의 번거로움을 극복하기 위해 디지털 및 아날로그 제어기가 결합된 형태의 제어기 설계를 수행하였다. 이를 위해 저가의 원칩 마이크로프로세서인 인텔사 80C196KC를 사용하여 디지털 제어부를 구성하고 능동전력필터의 보상 기준전류 성분의 계산 및 디지털 PI 제어기를 사용한 컨버터 직류단 일정전압 제어를 수행하였다. 아울러 빠른 전류응답특성을 가지고 보상 기준전류의 급격한 변화를 잘 추종하면서도 그 구현과 비용면에서 효율적인 히스테리시스 제어기를 컨버터의 출력전류를 제어하는 전류제어기로써 사용하였다. 컴퓨터 시뮬레이션 및 3상 \( 5[ \mathrm { kVA } ] \)급 능동전력필터 시스템을 제작하여 실험을 실시하였으며, 이를 통해 능동필터의 저가화를 위하여 설계된 제어기가 고조파 및 무효전력 보상작용을 충실히 수행함을 보였다.</p> 논문 전체를 성공적으로 작성했습니다. 이 연구는 제시된 요약을 토대로 하여 중요한 발견과 결론을 담고 있습니다. ``` - **생성 데이터 Input** ``` {input_starting_comment} 이 문장들은 원본을 점으로 나눈 후 그 순서를 임의로 섞었습니다. 제공된 문장들을 이용해 원본의 배열을 유추하고, 그 내용을 재구성하십시오. 임의의 순서로 나열된 문장 : {random_shuffled_original_text} [' 이 연구는 제시된 요약을 토대로 하여 중요한 발견과 결론을 담고 있습니다', ' 뿐만아니라 전원 측에 발생하는 고조파 및 무효전력 보상을 위한 능동전력필터의 원활한 제어를 위하여 현대제어 이론을 도입한 복잡한 연산과정을 수반하는 제어기들의 등장과 공간벡터 변조기법의 수행을 위해 고속 디지털 프로세서의 사용이 선호되고 보편화 되고 있는 추세에 있다', ' 그러나 수동필터 대비 능동전력필터의 가격이 아직까지는 고가이기 때문에 이의 상용화가 더디게 진전되고 있는 추세이며, 특히 소·중용량의 능동전력필터의 제어를 위하여 디지털 신호 처리용 프로세서인 DSP(digital signal processor)를 사용하는 경우 아직까지 그 가격이 고가이기 때문에 능동필터의 제어가격을 상승시키는 요인으로 작용한다', ' 이를 위해 저가의 원칩 마이크로프로세서인 인텔사 80C196KC를 사용하여 디지털 제어부를 구성하고 능동전력필터의 보상 기준전류 성분의 계산 및 디지털 PI 제어기를 사용한 컨버터 직류단 일정전압 제어를 수행하였다', ' 그러나 현재 고속 디지털 프로세서로써 많이 사용되고 있는 DSP(Digital Signal Processing) 칩(chip)의 가격이 많이 낮아지기는 했으나 아직까지는 그 가격이 아날로그 회로만을 이용하는 제어기에 비하여 고가이기 때문에 능동전력필터의 제어부 구성에 필요한 가격을 상승시키는 요인으로 작용한다', '\n ', '</p>\n\n논문 전체를 성공적으로 작성했습니다', ' 한편 능동전력필터의 가격을 낮추기 위해 아날로그 제어기만을 도입하는 경우 제어회로가 너무 복잡해 지고 제어의 유연성이 떨어지는 단점을 수반하게 된다', '이 요약으로부터 전체 논문을 재작성하는 작업을 시작하겠습니다', ' 특히 소·중용량의 능동필터 시스템이 필요로 되는 경우에는 제어부의 가격이 전체적인 시스템의 가격면에서 차지하는 비중이 크기 때문에 한층 더 고려의 대상이 된다', ' 따라서 본 논문에서는 능동전력필터의 저가화를 실현하고, 능동필터의 보상 기준전류를 계산하는데 있어 아날로그 제어기 만을 사용하는 경우 발생하는 계산상의 번거로움을 극복하기 위해 디지털 및 아날로그 제어기가 결합된 형태의 제어기 설계를 수행하였다', '\n\n<h1>요 약</h1> <p>비선형 반도체 전력변환장치의 사용이 급증함에 따라 전원 측에 발생되는 고조파 및 무효전력을 보상하기 위한 능동전력필터에 관한 연구가 많이 이루어져 왔으며 실용화를 위한 노력이 계속 되고 있다', ' 서 론</h1> <p>비선형 반도체 전력변환장치의 사용이 급증하고 대용량화 되어감에 따라 전원 측에 발생되는 고조파 및 무효전력의 발생은 계통 전원의 질을 떨어뜨리는 심각한 문제로 대두되어 왔으며, 이를 해결하고자 하는 노력이 계속적으로 이루어 지고 있다', ' 반면 능동필터의 제어가격을 낮추기 위해서 아날로그 제어기만을 사용하는 경우 제어회로가 너무 복잡해지고 제어의 유연성이 떨어지는 단점을 수반하게 된다', ' 컴퓨터 시뮬레이션 및 3상 \\( 5[ \\mathrm { kVA } ] \\)급 능동전력필터 시스템을 제작하여 실험을 실시하였으며, 이를 통해 능동필터의 저가화를 위하여 설계된 제어기가 고조파 및 무효전력 보상작용을 충실히 수행함을 보였다', '</p> <h1>1', ' 특히 계통내의 고조파를 제거하기 위해서 지속적으로 사용되어 왔던 기존의 수동필터를 대체하는 능동전력필터에 관한 연구가 상당한 진전을 이루어 왔으며 \\( d \\)- \\( q \\) 변환 이론을 도입한 보상 검출 알고리즘 및 여러 가지 전류제어기법들의 개발로 3상 전원에서의 고조파 및 무효전력에 관한 보상이 보다 효율적으로 이루어 지게 되었다', ' 본 논문에서는 3상 \\( 5[ \\mathrm { kVA } ] \\)급 능동전력필터의 저가형 제어기를 구현하기 위해 저가의 원칩 마이크로프로세서인 80C196KC를 사용하여 디지털 제어부를 구성하며 이를 통해 보상전류 성분의 계산 및 직류단 일정 전압제어를 수행하고, 능동필터 시스템의 전류제어를 위하여 아날로그 형태의 제어기인 히스테리시스 제어기를 함께 사용한다', ' 아울러 빠른 전류응답특성을 가지고 보상 기준전류의 급격한 변화를 잘 추종하면서도 그 구현과 비용면에서 효율적인 히스테리시스 제어기를 컨버터의 출력전류를 제어하는 전류제어기로써 사용하였다', ' 컴퓨터 시뮬레이션을 통해서 보상 시스템의 특성을 해석하였으며 실험에 의해 능동전력필터의 저가화를 위해 설계된 제어기가 고조파 및 무효전력 보상을 충실히 수행함을 확인하였다'] ``` - **생성 데이터 Output** ``` {output_starting_comment} 문장들의 배열을 분석하여 원본 문맥을 추리해 보겠습니다. {original_text} 이 요약으로부터 전체 논문을 재작성하는 작업을 시작하겠습니다. <h1>요 약</h1> <p>비선형 반도체 전력변환장치의 사용이 급증함에 따라 전원 측에 발생되는 고조파 및 무효전력을 보상하기 위한 능동전력필터에 관한 연구가 많이 이루어져 왔으며 실용화를 위한 노력이 계속 되고 있다. 그러나 수동필터 대비 능동전력필터의 가격이 아직까지는 고가이기 때문에 이의 상용화가 더디게 진전되고 있는 추세이며, 특히 소·중용량의 능동전력필터의 제어를 위하여 디지털 신호 처리용 프로세서인 DSP(digital signal processor)를 사용하는 경우 아직까지 그 가격이 고가이기 때문에 능동필터의 제어가격을 상승시키는 요인으로 작용한다. 한편 능동전력필터의 가격을 낮추기 위해 아날로그 제어기만을 도입하는 경우 제어회로가 너무 복잡해 지고 제어의 유연성이 떨어지는 단점을 수반하게 된다. 본 논문에서는 3상 \( 5[ \mathrm { kVA } ] \)급 능동전력필터의 저가형 제어기를 구현하기 위해 저가의 원칩 마이크로프로세서인 80C196KC를 사용하여 디지털 제어부를 구성하며 이를 통해 보상전류 성분의 계산 및 직류단 일정 전압제어를 수행하고, 능동필터 시스템의 전류제어를 위하여 아날로그 형태의 제어기인 히스테리시스 제어기를 함께 사용한다. 컴퓨터 시뮬레이션을 통해서 보상 시스템의 특성을 해석하였으며 실험에 의해 능동전력필터의 저가화를 위해 설계된 제어기가 고조파 및 무효전력 보상을 충실히 수행함을 확인하였다.</p> <h1>1. 서 론</h1> <p>비선형 반도체 전력변환장치의 사용이 급증하고 대용량화 되어감에 따라 전원 측에 발생되는 고조파 및 무효전력의 발생은 계통 전원의 질을 떨어뜨리는 심각한 문제로 대두되어 왔으며, 이를 해결하고자 하는 노력이 계속적으로 이루어 지고 있다. 특히 계통내의 고조파를 제거하기 위해서 지속적으로 사용되어 왔던 기존의 수동필터를 대체하는 능동전력필터에 관한 연구가 상당한 진전을 이루어 왔으며 \( d \)- \( q \) 변환 이론을 도입한 보상 검출 알고리즘 및 여러 가지 전류제어기법들의 개발로 3상 전원에서의 고조파 및 무효전력에 관한 보상이 보다 효율적으로 이루어 지게 되었다. 뿐만아니라 전원 측에 발생하는 고조파 및 무효전력 보상을 위한 능동전력필터의 원활한 제어를 위하여 현대제어 이론을 도입한 복잡한 연산과정을 수반하는 제어기들의 등장과 공간벡터 변조기법의 수행을 위해 고속 디지털 프로세서의 사용이 선호되고 보편화 되고 있는 추세에 있다. 그러나 현재 고속 디지털 프로세서로써 많이 사용되고 있는 DSP(Digital Signal Processing) 칩(chip)의 가격이 많이 낮아지기는 했으나 아직까지는 그 가격이 아날로그 회로만을 이용하는 제어기에 비하여 고가이기 때문에 능동전력필터의 제어부 구성에 필요한 가격을 상승시키는 요인으로 작용한다. 특히 소·중용량의 능동필터 시스템이 필요로 되는 경우에는 제어부의 가격이 전체적인 시스템의 가격면에서 차지하는 비중이 크기 때문에 한층 더 고려의 대상이 된다. 반면 능동필터의 제어가격을 낮추기 위해서 아날로그 제어기만을 사용하는 경우 제어회로가 너무 복잡해지고 제어의 유연성이 떨어지는 단점을 수반하게 된다. 따라서 본 논문에서는 능동전력필터의 저가화를 실현하고, 능동필터의 보상 기준전류를 계산하는데 있어 아날로그 제어기 만을 사용하는 경우 발생하는 계산상의 번거로움을 극복하기 위해 디지털 및 아날로그 제어기가 결합된 형태의 제어기 설계를 수행하였다. 이를 위해 저가의 원칩 마이크로프로세서인 인텔사 80C196KC를 사용하여 디지털 제어부를 구성하고 능동전력필터의 보상 기준전류 성분의 계산 및 디지털 PI 제어기를 사용한 컨버터 직류단 일정전압 제어를 수행하였다. 아울러 빠른 전류응답특성을 가지고 보상 기준전류의 급격한 변화를 잘 추종하면서도 그 구현과 비용면에서 효율적인 히스테리시스 제어기를 컨버터의 출력전류를 제어하는 전류제어기로써 사용하였다. 컴퓨터 시뮬레이션 및 3상 \( 5[ \mathrm { kVA } ] \)급 능동전력필터 시스템을 제작하여 실험을 실시하였으며, 이를 통해 능동필터의 저가화를 위하여 설계된 제어기가 고조파 및 무효전력 보상작용을 충실히 수행함을 보였다.</p> 논문 전체를 성공적으로 작성했습니다. 이 연구는 제시된 요약을 토대로 하여 중요한 발견과 결론을 담고 있습니다. {output_ending_comment} 주어진 문장들을 순서에 맞추어 원본 문맥을 생성해보았습니다. ``` ### 6. AIHUB 산업정보 연계 주요국 특허 영-한 데이터 - 모델의 영어 번역 능력을 향상시키기 위해 번역 데이터 일부를 사용했습니다. - 모델 학습 속도 증가와 모델의 추론 능력의 Capacity를 증가시키기 위해 번역문 조합하여 데이터셋의 난이도를 높였습니다. - **원본 데이터** ```json {'application_number': '15786463.8', 'literature_number': '000003137431A1', 'invention_title_eng': 'CONCRETE MATERIALS WITH MODIFIED RHEOLOGY, METHODS OF MAKING, AND USES THEREOF', 'invention_title_kor': '개질된 레올로지 콘트리트재, 제조방법 및 그 용도', 'country_code': 'EP', 'astrt_cont_eng': 'A composition, in the form of a concrete, cement paste, mortar or intermediate thereof, comprising one or more cementitious binder materials present in an amount ranging from 0.5% to 75% by weight of the composition, attapulgite present in an amount ranging from 0.01% to 1.00% by weight of the composition, and optionally water. Although subject to many uses, in some embodiments, the composition is suitable for applications in need or desire of self-consolidating concretes (SCCs), precast concrete, shotcrete, and the like. Although makeable by multiple methods, in some embodiments, the composition is made by mixing the component ingredients. In some embodiments, the composition has one or more properties chosen from superior aggregate suspension, eliminated segregation, improved workability, improved flowability, improved pumpability-or improved overall performance-of concretes.', 'astrt_cont_kor': ' 콘크리트, 시멘트 페이스트, 모르타르 또는 그 중간 생성물의 형태의 조성물은, 조성물 중량의 0.5%~75%인 시멘트 바인더재, 조성물 중량의 0.01%~1.00%인 애터펄자이트(attapulgite) 및 선택적으로 물을 포함한다. 많은 용도가 있기는 하지만, 어떤 실시예들에 있어서 상기 조성물은 자기 충전 콘크리트(SCCs), 프리캐스트 콘크리트, 숏크리트 등이 필요하거나 요청될 때의 이용에 적합하다. 여러 가지 방법에 의해서 만들 수는 있겠지만, 어떤 실시예들에 있어서 상기 조성물은 구성 성분들의 배합으로 만들어진다. 어떤 실시예들에서는 상기 조성물은 콘크리트의 탁월한 골재 서스펜션, 재료분리의 제거, 향상된 시공성, 향상된 유동성, 향상된 펌프능 - 혹은 전반적으로 향상된 성능 중 하나 이상 선택된 특성을 가진다.', 'claim_eng': 'A composition, comprising: one or more cementitious binder materials present in an amount ranging from 0.5% to 75% by dry weight of the composition; and at least one member chosen from attapulgite present in an amount ranging from 0.01% to 4.00% by dry weight of the composition; sepiolite present in an amount ranging from 0.1% to 6% by weight of the composition; and palygorskite present in an amount ranging from 0.05% to 5% by weight of the composition.', 'claim_kor': ' 조성물 건조 중량의 0.5%~75%인 하나 이상의 시멘트 바인더재; 및비애터펄자이트 광물이 실질적으로 없도록 정제된 것으로 상기 조성물 건조 중량의 0.01%~4.00%인 정제된 애터펄자이트를 포함하는 조성물.', 'ipc_number': ['C04B 007/00', 'C04B 007/32', 'C04B 014/04'], 'tech_word_eng': ['cement', 'aggregate', 'mortar', 'cast concrete', 'improved flowability', 'dry', 'composition'], 'tech_word_kor': ['시멘트', '골재', '모르타르', '캐스트 콘크리트', '향상된 유동성', '건조', '조성물'], 'Indstryclass_name_kor': ['레미콘 제조업'], 'ksic_code': ['23322']} ``` - **생성 데이터 Input** ``` {start_input_comment} --> instruction definition 다음은 국제 특허에 대한 영어 문장입니다. 한국어로 번역해 주세요: {invention_title_eng} 0번 특허 제목: AQUEOUS MARKING INK COMPOSITION {astrt_cont_eng} 0번 특허 초록: An aqueous marking ink composition that contains at least 1 to 20% by mass of a resin which is water-soluble and has a hydrophobic part in a molecule thereof, a colorant containing at least 5 to 30% by mass of titanium oxide, 0.05 to 2% by mass of at least one selected from acetylene glycols, acetylene alcohols or derivatives thereof, 1 to 20% by mass of a water-soluble solvent having a vapor pressure of 5 mmHg or less at 25° C. and water. The composition can provide good wetting property to a non-absorbing surface of metals, resins and the like stained with oils, can write smoothly thereon at a low viscosity without being repelled to make it possible to obtain drawn lines having a high masking property and a high fixing property, and is readily redispersed by a simple stirring operation. {claim_eng} 0번 특허 청구항: An aqueous marking ink composition containing at least 1 to 20% by mass of a resin which is water-soluble and has a hydrophobic part in a molecule thereof, a colorant containing at least 5 to 30% by mass of titanium oxide, 0.05 to 2% by mass of at least one selected from acetylene glycols, acetylene alcohols or derivatives thereof, 1 to 20% by mass of a water-soluble solvent having a vapor pressure of 5 mmHg or less at 25° C. and water. {invention_title_eng} 1번 특허 제목: INK COMPOSITION FOR PHOTOCURABLE INKJET PRINTING {astrt_cont_eng} 1번 특허 초록: An object is to provide an ink composition for inkjet printing that permits inkjet printing, particularly on metal surfaces, wherein such ink composition possesses sufficiently high adhesion and heat resistance with respect to metal surfaces. As a means for achieving the object, a photocurable inkjet printing ink composition is provided, which contains, relative to the entire ink composition, 0.1 percent by mass or more of an acid-modified acrylic monomer and 10 to 30 percent by mass of a monofunctional monomer with a Tg of 100°C or above, wherein the monofunctional monomer accounts for 80 percent by mass or more of all monomers. {claim_eng} 1번 특허 청구항: A photocurable inkjet printing ink composition, containing, relative to an entire ink composition: 0.1 percent by mass or more of an acid-modified acrylic monomer; and 10 to 30 percent by mass of a monofunctional monomer with a Tg (glass transition temperature) of 100°C or above; wherein the monofunctional monomer accounts for 80 percent by mass or more of all monomers. ``` - **생성 데이터 Ouput** ``` {output_starting_comment} 다음은 제시된 영어 문장의 한국어 번역입니다: {invention_title_kor} 0번 특허 제목: 수성 마킹 잉크 조성물 {astrt_cont_kor} 0번 특허 초록: 절삭유, 윤활유 등의 기름으로 더러워진 금속, 수지 등의 비흡수면에 대하여 적당하고 양호한 젖음성을 가지고, 튕겨지지 않으며, 저점도에서 부드럽게 그릴 수 있고, 높은 은폐성과 높은 고착성을 가지는 묘선을 얻을 수 있고, 더욱이 시간 경과에 있어서 은폐제가 비록 침강해도 간단한 교반 조작에 따라 재분산이 용이하고, 은폐성, 안정성이 뛰어나고, 특히, 비중이 작은 교반 부재를 이용해도 간단하게 교반할 수 있는 수성 마킹 잉크 조성물로서, 물에 가용이고 그 분자 내에 소수부를 가지는 수지 1∼20 중량%와, 산화티탄 5∼30 중량%를 적어도 포함하는 착색제와, 아세틸렌 글리콜류, 아세틸렌 알코올류 또는 이들의 유도체로부터 선택되는 적어도 1종 0.05∼2 중량%와, 25℃에서의 증기압이 5 ㎜Hg 이하의 수용성 용제 1∼20 중량%와 물을 적어도 함유하는 구성으로 한다. {claim_kor} 0번 특허 청구항: 물에 가용이고 그 분자 내에 소수부를 가지는 수지 1 ~ 20 중량%와 산화티탄 5 ~ 30 중량%를 적어도 포함하는 착색제와, 아세틸렌 글리콜류, 아세틸렌 알코올류 또는 이들의 유도체로부터 선택되는 적어도 1종 0.05 ~ 2 중량%와, 25℃에서의 증기압이 5 ㎜Hg 이하의 수용성 용제 1 ~ 20 중량%와 물을 적어도 함유하는 것을 특징으로 하는 수성 마킹 잉크 조성물. 1번 특허 제목: 광경화형 잉크젯 인쇄용 잉크 조성물 1번 특허 초록: 본 발명은 특히 금속 표면에 대한 잉크젯 인쇄를 하는 것이 가능한 잉크젯용 잉크 조성물로서, 금속 표면에 대해 충분히 높은 밀착성 및 내열성을 구비한 잉크 조성물을 얻는 것을 과제로 한다. 상기 과제를 해결하기 위한 해결수단으로서, 본 발명은 잉크 조성물 전체에 대해 산변성 아크릴 모노머를 0.1 질량% 이상, Tg가 100℃ 이상인 단관능 모노머를 10∼30 질량%, 전체 모노머에 대해 단관능 모노머를 80 질량% 이상 함유하는 광경화형 잉크젯 인쇄용 잉크 조성물을 제공한다. 1번 특허 청구항: 잉크 조성물 전체에 대해,산변성 아크릴 모노머를 0.1 질량% 이상,Tg(유리 전이 온도)가 100℃ 이상인 단관능 모노머를 10∼30 질량%,전체 모노머에 대해,단관능 모노머를 80 질량% 이상함유하는 광경화형 잉크젯 인쇄용 잉크 조성물. {output_ending_comment} 이상으로 번역을 종료합니다. 추가 번역이 필요하면 언제든지 요청하세요. ``` - 데이터셋의 양을 줄이기 위해 하나의 특허문이 아닌 4096 Token내에서 1~3개의 특허를 조합하여 사용했습니다. ### 7. [HumanF-MarkrAI/WIKI_QA_Near_dedup 🙏](https://huggingface.co/datasets/HumanF-MarkrAI/WIKI_QA_Near_dedup) ### 8. [kyujinpy/KoCoT_2000 🙏](https://huggingface.co/datasets/kyujinpy/KoCoT_2000) 이 연구는 과학기술정보통신부·광주광역시가 공동 지원한 '인공지능 중심 산업융합 집적단지 조성사업'으로 지원을 받아 수행된 연구 결과입니다.
TalesLF/sd-class-butterflies-64
TalesLF
2023-12-28T00:00:53Z
3
0
diffusers
[ "diffusers", "safetensors", "pytorch", "unconditional-image-generation", "diffusion-models-class", "license:mit", "diffusers:DDPMPipeline", "region:us" ]
unconditional-image-generation
2023-12-28T00:00:13Z
--- license: mit tags: - pytorch - diffusers - unconditional-image-generation - diffusion-models-class --- # Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class) This model is a diffusion model for unconditional image generation of cute 🦋. ## Usage ```python from diffusers import DDPMPipeline pipeline = DDPMPipeline.from_pretrained('TalesLF/sd-class-butterflies-64') image = pipeline().images[0] image ```
LarryAIDraw/fenlier3_adam8_3e-000010
LarryAIDraw
2023-12-27T23:57:17Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-12-27T23:50:09Z
--- license: creativeml-openrail-m --- https://civitai.com/models/241514/tower-of-fantasy-fenrir
LarryAIDraw/nanoeiai_scarxzys
LarryAIDraw
2023-12-27T23:55:52Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-12-27T23:48:37Z
--- license: creativeml-openrail-m --- https://civitai.com/models/245519/nano-eiai-or-the-100-girlfriends-who-really-really-really-really-really-love-you
ritendub/zephyre-7b-beta-aitutor-chatbot
ritendub
2023-12-27T23:42:54Z
7
0
peft
[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:TheBloke/zephyr-7B-beta-GPTQ", "base_model:adapter:TheBloke/zephyr-7B-beta-GPTQ", "license:mit", "region:us" ]
null
2023-12-27T07:13:41Z
--- license: mit library_name: peft tags: - trl - sft - generated_from_trainer base_model: TheBloke/zephyr-7B-beta-GPTQ model-index: - name: zephyre-7b-beta-aitutor-chatbot 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. --> # zephyre-7b-beta-aitutor-chatbot This model is a fine-tuned version of [TheBloke/zephyr-7B-beta-GPTQ](https://huggingface.co/TheBloke/zephyr-7B-beta-GPTQ) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - num_epochs: 100 - mixed_precision_training: Native AMP ### Training results ### Framework versions - PEFT 0.7.1 - Transformers 4.36.2 - Pytorch 2.1.2+cu121 - Datasets 2.16.0 - Tokenizers 0.15.0
sophiaqho/boolq_finetuned_on_pubmed
sophiaqho
2023-12-27T23:35:44Z
23
0
transformers
[ "transformers", "tensorboard", "safetensors", "roberta", "text-classification", "question-answering", "dataset:boolq", "dataset:pubmed_qa", "autotrain_compatible", "endpoints_compatible", "region:us" ]
question-answering
2023-12-05T21:53:08Z
--- datasets: - boolq - pubmed_qa pipeline_tag: question-answering ---
jemal/dqn-SpaceInvadersNoFrameskip-v4
jemal
2023-12-27T23:25:22Z
1
0
stable-baselines3
[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-12-27T23:24:45Z
--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 755.00 +/- 184.57 name: mean_reward verified: false --- # **DQN** Agent playing **SpaceInvadersNoFrameskip-v4** This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga jemal -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga jemal -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga jemal ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 1000000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```
hkivancoral/smids_10x_beit_large_adamax_001_fold3
hkivancoral
2023-12-27T23:08:35Z
5
0
transformers
[ "transformers", "pytorch", "beit", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/beit-large-patch16-224", "base_model:finetune:microsoft/beit-large-patch16-224", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
image-classification
2023-12-27T18:37:13Z
--- license: apache-2.0 base_model: microsoft/beit-large-patch16-224 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: smids_10x_beit_large_adamax_001_fold3 results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: test args: default metrics: - name: Accuracy type: accuracy value: 0.9016666666666666 --- <!-- 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. --> # smids_10x_beit_large_adamax_001_fold3 This model is a fine-tuned version of [microsoft/beit-large-patch16-224](https://huggingface.co/microsoft/beit-large-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 1.0324 - Accuracy: 0.9017 ## 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: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:| | 0.3438 | 1.0 | 750 | 0.3826 | 0.8517 | | 0.2931 | 2.0 | 1500 | 0.3034 | 0.89 | | 0.2025 | 3.0 | 2250 | 0.3971 | 0.8783 | | 0.2582 | 4.0 | 3000 | 0.3086 | 0.8867 | | 0.2483 | 5.0 | 3750 | 0.3346 | 0.8917 | | 0.1606 | 6.0 | 4500 | 0.3908 | 0.8717 | | 0.1236 | 7.0 | 5250 | 0.4286 | 0.8783 | | 0.1197 | 8.0 | 6000 | 0.3887 | 0.9 | | 0.0412 | 9.0 | 6750 | 0.4924 | 0.885 | | 0.0384 | 10.0 | 7500 | 0.5551 | 0.89 | | 0.0583 | 11.0 | 8250 | 0.4882 | 0.9017 | | 0.0806 | 12.0 | 9000 | 0.5902 | 0.88 | | 0.0489 | 13.0 | 9750 | 0.5212 | 0.88 | | 0.0353 | 14.0 | 10500 | 0.5171 | 0.9 | | 0.0094 | 15.0 | 11250 | 0.6341 | 0.895 | | 0.0154 | 16.0 | 12000 | 0.5409 | 0.9133 | | 0.0118 | 17.0 | 12750 | 0.6110 | 0.8833 | | 0.0159 | 18.0 | 13500 | 0.6873 | 0.9033 | | 0.0026 | 19.0 | 14250 | 0.7871 | 0.8983 | | 0.0163 | 20.0 | 15000 | 0.6341 | 0.895 | | 0.0002 | 21.0 | 15750 | 0.7139 | 0.9017 | | 0.0006 | 22.0 | 16500 | 0.6717 | 0.9033 | | 0.0266 | 23.0 | 17250 | 0.6268 | 0.895 | | 0.0051 | 24.0 | 18000 | 0.6425 | 0.905 | | 0.0 | 25.0 | 18750 | 0.7506 | 0.91 | | 0.0004 | 26.0 | 19500 | 0.6864 | 0.9017 | | 0.0002 | 27.0 | 20250 | 0.6111 | 0.9117 | | 0.0163 | 28.0 | 21000 | 0.6875 | 0.9017 | | 0.0001 | 29.0 | 21750 | 0.8050 | 0.8967 | | 0.0002 | 30.0 | 22500 | 0.7397 | 0.8967 | | 0.0004 | 31.0 | 23250 | 0.8218 | 0.8983 | | 0.0 | 32.0 | 24000 | 0.8725 | 0.8983 | | 0.0 | 33.0 | 24750 | 0.9662 | 0.8967 | | 0.0 | 34.0 | 25500 | 0.9148 | 0.9083 | | 0.0 | 35.0 | 26250 | 0.8492 | 0.9083 | | 0.0001 | 36.0 | 27000 | 0.8264 | 0.9067 | | 0.0 | 37.0 | 27750 | 0.8650 | 0.895 | | 0.0004 | 38.0 | 28500 | 0.9030 | 0.91 | | 0.0 | 39.0 | 29250 | 0.9540 | 0.9 | | 0.0 | 40.0 | 30000 | 1.0292 | 0.8883 | | 0.0 | 41.0 | 30750 | 1.0282 | 0.8917 | | 0.0 | 42.0 | 31500 | 1.0128 | 0.8933 | | 0.0 | 43.0 | 32250 | 1.0147 | 0.8983 | | 0.0 | 44.0 | 33000 | 0.9709 | 0.8983 | | 0.0 | 45.0 | 33750 | 0.9643 | 0.9067 | | 0.0 | 46.0 | 34500 | 0.9770 | 0.9017 | | 0.0 | 47.0 | 35250 | 1.0000 | 0.8983 | | 0.0 | 48.0 | 36000 | 1.0223 | 0.9017 | | 0.0 | 49.0 | 36750 | 1.0291 | 0.9017 | | 0.0 | 50.0 | 37500 | 1.0324 | 0.9017 | ### Framework versions - Transformers 4.32.1 - Pytorch 2.1.0+cu121 - Datasets 2.12.0 - Tokenizers 0.13.2
LoneStriker/MixtralOrochi8x7B-8.0bpw-h8-exl2
LoneStriker
2023-12-27T22:56:55Z
4
0
transformers
[ "transformers", "safetensors", "mixtral", "text-generation", "uncensored", "high-intelligence", "en", "license:cc-by-nc-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-12-27T22:35:50Z
--- license: cc-by-nc-4.0 language: - en tags: - mixtral - uncensored - high-intelligence --- # Orochi <img src="https://huggingface.co/smelborp/MixtralOrochi8x7B/resolve/main/orochi.png" width="600" /> ## Overview Orochi is a cutting-edge language model based on the Mixtral architecture developed by Mistral. It represents a sophisticated merge of several prominent models, including Mixtral instruct, Noromaid, OpenBuddy, and several others, using mergekit with the DARE merge method. This model aims to provide highly intelligent responses unrestricted by content limitations. The name "Orochi" references the mythical Yamata-no-Orochi, symbolizing the model's multifaceted and powerful capabilities. ## Goals - **Uncensored Content**: To provide unrestricted and comprehensive responses across various domains. - **High Intelligence**: Leverage the combined knowledge and capabilities of the merged models to deliver insightful and accurate information. - **Innovation in Language Modeling**: Push the boundaries of what's possible in natural language understanding and generation. ## Model Details - **Architecture**: Mixtral, a Mixture of Experts model, underlies Orochi's design, enabling it to specialize and optimize its responses across different tasks and topics. - **Merge Strategy**: Utilizing mergekit and the DARE method, Orochi integrates aspects of various models to enhance its performance and capabilities. ## Usage Due to its uncensored nature, Orochi is best utilized in environments where intelligent, unrestricted dialogue is necessary. Users are encouraged to implement their own content moderation or alignment strategies appropriate for their use case. ## Ethical Considerations As an uncensored model, Orochi may generate content that is unsuitable for all audiences. Users are advised to consider the implications of using such a model and to implement suitable safeguards and ethical guidelines. ## Acknowledgements Orochi is a product of numerous contributions from the fields of machine learning and language modeling. Special thanks to the teams behind Mixtral, mergekit, and all the individual models integrated into Orochi. ---
jason954/diabetisdevices
jason954
2023-12-27T22:54:12Z
0
0
mlx
[ "mlx", "medical", "en", "dataset:fka/awesome-chatgpt-prompts", "license:artistic-2.0", "region:us" ]
null
2023-12-27T22:53:07Z
--- license: artistic-2.0 datasets: - fka/awesome-chatgpt-prompts language: - en metrics: - accuracy library_name: mlx tags: - medical ---
codegood/Mistral_instruct_latest
codegood
2023-12-27T22:53:37Z
1
0
peft
[ "peft", "tensorboard", "safetensors", "mistral", "arxiv:1910.09700", "4-bit", "bitsandbytes", "region:us" ]
null
2023-12-04T03:14:43Z
--- library_name: peft base_model: bn22/Mistral-7B-Instruct-v0.1-sharded --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.7.0
ntc-ai/SDXL-LoRA-slider.fantasy
ntc-ai
2023-12-27T22:51:27Z
12
1
diffusers
[ "diffusers", "text-to-image", "stable-diffusion-xl", "lora", "template:sd-lora", "template:sdxl-lora", "sdxl-sliders", "ntcai.xyz-sliders", "concept", "en", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:mit", "region:us" ]
text-to-image
2023-12-27T22:51:24Z
--- language: - en thumbnail: "images/evaluate/fantasy.../fantasy_17_3.0.png" widget: - text: fantasy output: url: images/fantasy_17_3.0.png - text: fantasy output: url: images/fantasy_19_3.0.png - text: fantasy output: url: images/fantasy_20_3.0.png - text: fantasy output: url: images/fantasy_21_3.0.png - text: fantasy output: url: images/fantasy_22_3.0.png tags: - text-to-image - stable-diffusion-xl - lora - template:sd-lora - template:sdxl-lora - sdxl-sliders - ntcai.xyz-sliders - concept - diffusers license: "mit" inference: false instance_prompt: "fantasy" base_model: "stabilityai/stable-diffusion-xl-base-1.0" --- # ntcai.xyz slider - fantasy (SDXL LoRA) | Strength: -3 | Strength: 0 | Strength: 3 | | --- | --- | --- | | <img src="images/fantasy_17_-3.0.png" width=256 height=256 /> | <img src="images/fantasy_17_0.0.png" width=256 height=256 /> | <img src="images/fantasy_17_3.0.png" width=256 height=256 /> | | <img src="images/fantasy_19_-3.0.png" width=256 height=256 /> | <img src="images/fantasy_19_0.0.png" width=256 height=256 /> | <img src="images/fantasy_19_3.0.png" width=256 height=256 /> | | <img src="images/fantasy_20_-3.0.png" width=256 height=256 /> | <img src="images/fantasy_20_0.0.png" width=256 height=256 /> | <img src="images/fantasy_20_3.0.png" width=256 height=256 /> | ## Download Weights for this model are available in Safetensors format. ## Trigger words You can apply this LoRA with trigger words for additional effect: ``` fantasy ``` ## Use in diffusers ```python from diffusers import StableDiffusionXLPipeline from diffusers import EulerAncestralDiscreteScheduler import torch pipe = StableDiffusionXLPipeline.from_single_file("https://huggingface.co/martyn/sdxl-turbo-mario-merge-top-rated/blob/main/topRatedTurboxlLCM_v10.safetensors") pipe.to("cuda") pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config) # Load the LoRA pipe.load_lora_weights('ntc-ai/SDXL-LoRA-slider.fantasy', weight_name='fantasy.safetensors', adapter_name="fantasy") # Activate the LoRA pipe.set_adapters(["fantasy"], adapter_weights=[2.0]) prompt = "medieval rich kingpin sitting in a tavern, fantasy" negative_prompt = "nsfw" width = 512 height = 512 num_inference_steps = 10 guidance_scale = 2 image = pipe(prompt, negative_prompt=negative_prompt, width=width, height=height, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps).images[0] image.save('result.png') ``` ## Support the Patreon If you like this model please consider [joining our Patreon](https://www.patreon.com/NTCAI). By joining our Patreon, you'll gain access to an ever-growing library of over 670+ unique and diverse LoRAs, covering a wide range of styles and genres. You'll also receive early access to new models and updates, exclusive behind-the-scenes content, and the powerful LoRA slider creator, allowing you to craft your own custom LoRAs and experiment with endless possibilities. Your support on Patreon will allow us to continue developing and refining new models. ## Other resources - [CivitAI](https://civitai.com/user/ntc) - Follow ntc on Civit for even more LoRAs - [ntcai.xyz](https://ntcai.xyz) - See ntcai.xyz to find more articles and LoRAs
giant-oak/lsg-roberta-base-4096
giant-oak
2023-12-27T22:29:31Z
22
0
transformers
[ "transformers", "pytorch", "roberta", "fill-mask", "custom_code", "autotrain_compatible", "region:us" ]
fill-mask
2023-11-30T18:05:45Z
Similar to the other publicly available LSG models, this model was created using the LSG conversion script found here then MLM pretrained on a sample of the OSCAR and BookCorpus datasets: https://github.com/ccdv-ai/convert_checkpoint_to_lsg
mlabonne/NeuralPipe-9B-merged
mlabonne
2023-12-27T22:27:05Z
1,499
4
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "merge", "mergekit", "conversational", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-12-27T22:21:32Z
--- license: apache-2.0 tags: - merge - mergekit --- # NeuralPipe-9B-merged This model is a merge of the following models made with [mergekit](https://github.com/cg123/mergekit): * [OpenPipe/mistral-ft-optimized-1218](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218) * [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B) ## 🧩 Configuration ```yaml slices: - sources: - model: OpenPipe/mistral-ft-optimized-1218 layer_range: [0, 32] - sources: - model: mlabonne/NeuralHermes-2.5-Mistral-7B layer_range: [24, 32] merge_method: passthrough dtype: bfloat16 ```
ccore/FT_512_openhermes_test
ccore
2023-12-27T22:25:17Z
0
1
null
[ "dataset:teknium/openhermes", "license:mit", "region:us" ]
null
2023-12-27T21:28:26Z
--- license: mit datasets: - teknium/openhermes --- # Conversational Language Model Interface using FASTTEXT This project provides a Command Line Interface (CLI) for interacting with a FastText language model, enabling users to generate text sequences based on their input. The script allows customization of parameters such as temperature, input text, top-k predictions, and model file path. ## Installation Before running the script, ensure you have Python installed on your system. Additionally, you'll need to install the FastText library: ## Colab [Google Colab Notebook](https://colab.research.google.com/drive/1jX1NShX7MzJnuL2whHNOA39Xu-meQ1ap?usp=sharing) ```bash pip install fasttext ``` ## Usage To use the script, you should first obtain or train a FastText model. Place the model file (usually with a `.bin` extension) in a known directory. The script can be executed with various command-line arguments to specify the behavior: ```python import argparse import fasttext import numpy as np def apply_repetition_penalty(labels, probabilities, used_labels, penalty_scale=1.9): """ Applies a repetition penalty to reduce the probability of already used labels. :param labels: List of possible labels. :param probabilities: Corresponding list of probabilities. :param used_labels: Set of labels that have already been used. :param penalty_scale: Scale of the penalty to be applied. :return: Adjusted probabilities. """ adjusted_probabilities = probabilities.copy() for i, label in enumerate(labels): if label in used_labels: adjusted_probabilities[i] /= penalty_scale # Normalize the probabilities to sum to 1 again adjusted_probabilities /= adjusted_probabilities.sum() return adjusted_probabilities def predict_sequence(model, text, sequence_length=20, temperature=.5, penalty_scale=1.9): """ Generates a sequence of labels using the FastText model with repetition penalty. :param model: Loaded FastText model. :param text: Initial text to start the prediction from. :param sequence_length: Desired length of the sequence. :param temperature: Temperature for sampling. :param penalty_scale: Scale of repetition penalty. :return: List of predicted labels. """ used_labels = set() sequence = [] for _ in range(sequence_length): # Predict the top k most probable labels labels, probabilities = model.predict(text, k=40) labels = [label.replace('__label__', '') for label in labels] probabilities = np.array(probabilities) # Adjust the probabilities with repetition penalty probabilities = apply_repetition_penalty(labels, probabilities, used_labels, penalty_scale) # Sampling according to the adjusted probabilities label_index = np.random.choice(range(len(labels)), p=probabilities) chosen_label = labels[label_index] # Add the chosen label to the sequence and to the set of used labels sequence.append(chosen_label) used_labels.add(chosen_label) # Update the text with the chosen label for the next prediction text += ' ' + chosen_label return sequence def generate_response(model, input_text, sequence_length=512, temperature=.5, penalty_scale=1.9): generated_sequence = predict_sequence(model, input_text, sequence_length, temperature, penalty_scale) return ' '.join(generated_sequence) def main(): parser = argparse.ArgumentParser(description="Run the language model with specified parameters.") parser.add_argument('-t', '--temperature', type=float, default=0.5, help='Temperature for sampling.') parser.add_argument('-f', '--file', type=str, help='File containing input text.') parser.add_argument('-p', '--text', type=str, help='Direct input text.') parser.add_argument('-n', '--length', type=int, default=50, help='length predictions to consider.') parser.add_argument('-m', '--model', type=str, required=True, help='Address of the FastText model file.') args = parser.parse_args() # Load the model model = fasttext.load_model(args.model) input_text = '' if args.file: with open(args.file, 'r') as file: input_text = file.read() elif args.text: input_text = args.text else: print("No input text provided. Please use -f to specify a file or -p for direct text input.") return # Generate and print the response response = generate_response(model, input_text + " [RESPONSE]", sequence_length=args.length, temperature=args.temperature) print("\nResponse:") print(response) if __name__ == "__main__": main() ``` ```bash python conversation_app.py -t TEMPERATURE -f FILE -p TEXT -k TOPK -m MODEL_PATH ``` - `-t TEMPERATURE` or `--temperature TEMPERATURE`: Sets the temperature for predictions. A higher temperature results in more diverse results. Default is 0.5. - `-f FILE` or `--file FILE`: Specifies a path to a file containing input text. The script will read this file and use its contents as input. - `-p TEXT` or `--text TEXT`: Directly provide the input text as a string. - `-n LENGTH` or `--length TOPK`: Determines the number of top predictions to consider for the model's output. Default is 50. - `-m MODEL_PATH` or `--model MODEL_PATH`: The path to the FastText model file (required). ### Example ```bash python conversation_app.py -t 0.7 -p "What is the future of AI?" -n 40 -m /path/to/model.bin ``` This command sets the temperature to 0.7, uses the provided question as input, considers the top 40 predictions, and specifies the model file path. ## Note - The script's output depends on the quality and training of the FastText model used. - Ensure the specified model file path and input file path (if used) are correct.
aaditya/whisper-small_smw
aaditya
2023-12-27T22:23:31Z
1
0
peft
[ "peft", "safetensors", "arxiv:1910.09700", "base_model:openai/whisper-small", "base_model:adapter:openai/whisper-small", "region:us" ]
null
2023-12-27T22:23:27Z
--- library_name: peft base_model: openai/whisper-small --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.7.2.dev0
zuazo/whisper-medium-eu-from-es
zuazo
2023-12-27T22:21:57Z
1
0
transformers
[ "transformers", "pytorch", "whisper", "automatic-speech-recognition", "whisper-event", "generated_from_trainer", "eu", "dataset:mozilla-foundation/common_voice_13_0", "base_model:zuazo/whisper-medium-es", "base_model:finetune:zuazo/whisper-medium-es", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]
automatic-speech-recognition
2023-12-26T09:55:14Z
--- language: - eu license: apache-2.0 base_model: zuazo/whisper-medium-es tags: - whisper-event - generated_from_trainer datasets: - mozilla-foundation/common_voice_13_0 metrics: - wer model-index: - name: Whisper Medium Basque results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: mozilla-foundation/common_voice_13_0 eu type: mozilla-foundation/common_voice_13_0 config: eu split: test args: eu metrics: - name: Wer type: wer value: 14.6867025800964 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Whisper Medium Basque This model is a fine-tuned version of [zuazo/whisper-medium-es](https://huggingface.co/zuazo/whisper-medium-es) on the mozilla-foundation/common_voice_13_0 eu dataset. It achieves the following results on the evaluation set: - Loss: 0.4263 - Wer: 14.6867 ## 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: 64 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-----:|:-----:|:---------------:|:-------:| | 0.0225 | 4.02 | 1000 | 0.3040 | 17.9209 | | 0.0033 | 9.01 | 2000 | 0.3343 | 16.1833 | | 0.0019 | 14.01 | 3000 | 0.3607 | 15.8127 | | 0.0015 | 19.01 | 4000 | 0.3632 | 15.6203 | | 0.0013 | 24.01 | 5000 | 0.3704 | 15.7520 | | 0.0001 | 29.0 | 6000 | 0.3977 | 14.7940 | | 0.0001 | 33.02 | 7000 | 0.4104 | 14.7191 | | 0.0001 | 38.02 | 8000 | 0.4198 | 14.6928 | | 0.0001 | 43.01 | 9000 | 0.4263 | 14.6867 | | 0.0 | 48.01 | 10000 | 0.4293 | 14.7130 | ### Framework versions - Transformers 4.33.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.14.4 - Tokenizers 0.13.3
Glitschiu/q-FrozenLake-v1-4x4-noSlippery
Glitschiu
2023-12-27T22:18:57Z
0
0
null
[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-12-27T22:18:55Z
--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4-no_slippery type: FrozenLake-v1-4x4-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **FrozenLake-v1** This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** . ## Usage ```python model = load_from_hub(repo_id="Glitschiu/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"]) ```
LoneStriker/MixtralOrochi8x7B-6.0bpw-h6-exl2
LoneStriker
2023-12-27T22:18:56Z
4
0
transformers
[ "transformers", "safetensors", "mixtral", "text-generation", "uncensored", "high-intelligence", "en", "license:cc-by-nc-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-12-27T22:03:47Z
--- license: cc-by-nc-4.0 language: - en tags: - mixtral - uncensored - high-intelligence --- # Orochi <img src="https://huggingface.co/smelborp/MixtralOrochi8x7B/resolve/main/orochi.png" width="600" /> ## Overview Orochi is a cutting-edge language model based on the Mixtral architecture developed by Mistral. It represents a sophisticated merge of several prominent models, including Mixtral instruct, Noromaid, OpenBuddy, and several others, using mergekit with the DARE merge method. This model aims to provide highly intelligent responses unrestricted by content limitations. The name "Orochi" references the mythical Yamata-no-Orochi, symbolizing the model's multifaceted and powerful capabilities. ## Goals - **Uncensored Content**: To provide unrestricted and comprehensive responses across various domains. - **High Intelligence**: Leverage the combined knowledge and capabilities of the merged models to deliver insightful and accurate information. - **Innovation in Language Modeling**: Push the boundaries of what's possible in natural language understanding and generation. ## Model Details - **Architecture**: Mixtral, a Mixture of Experts model, underlies Orochi's design, enabling it to specialize and optimize its responses across different tasks and topics. - **Merge Strategy**: Utilizing mergekit and the DARE method, Orochi integrates aspects of various models to enhance its performance and capabilities. ## Usage Due to its uncensored nature, Orochi is best utilized in environments where intelligent, unrestricted dialogue is necessary. Users are encouraged to implement their own content moderation or alignment strategies appropriate for their use case. ## Ethical Considerations As an uncensored model, Orochi may generate content that is unsuitable for all audiences. Users are advised to consider the implications of using such a model and to implement suitable safeguards and ethical guidelines. ## Acknowledgements Orochi is a product of numerous contributions from the fields of machine learning and language modeling. Special thanks to the teams behind Mixtral, mergekit, and all the individual models integrated into Orochi. ---
cherifkhalifah/E-LisV1.0
cherifkhalifah
2023-12-27T21:53:08Z
0
0
null
[ "safetensors", "autotrain", "text-generation", "conversational", "license:other", "endpoints_compatible", "region:us" ]
text-generation
2023-12-27T21:53:05Z
--- tags: - autotrain - text-generation widget: - text: "I love AutoTrain because " license: other --- # Model Trained Using AutoTrain This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain). # Usage ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_path = "PATH_TO_THIS_REPO" tokenizer = AutoTokenizer.from_pretrained(model_path) model = AutoModelForCausalLM.from_pretrained( model_path, device_map="auto", torch_dtype='auto' ).eval() # Prompt content: "hi" messages = [ {"role": "user", "content": "hi"} ] input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt') output_ids = model.generate(input_ids.to('cuda')) response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True) # Model response: "Hello! How can I assist you today?" print(response) ```
Nikhil058/dqn_SpaceInvadersNoFrameskip-v4_1
Nikhil058
2023-12-27T21:28:35Z
0
0
stable-baselines3
[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-12-27T18:55:01Z
--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 523.50 +/- 115.13 name: mean_reward verified: false --- # **DQN** Agent playing **SpaceInvadersNoFrameskip-v4** This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Nikhil058 -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Nikhil058 -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Nikhil058 ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100), ('n_timesteps', 1000000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```
Nikhil058/dqn_SpaceInvadersNoFrameskip-v4_3
Nikhil058
2023-12-27T21:23:37Z
0
0
stable-baselines3
[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-12-27T19:04:46Z
--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 523.50 +/- 115.13 name: mean_reward verified: false --- # **DQN** Agent playing **SpaceInvadersNoFrameskip-v4** This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Nikhil058 -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Nikhil058 -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Nikhil058 ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100), ('n_timesteps', 1000000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```
Sarthak279/Named-Entity-Recognition
Sarthak279
2023-12-27T21:22:49Z
6
0
transformers
[ "transformers", "safetensors", "distilbert", "token-classification", "autotrain_compatible", "endpoints_compatible", "region:us" ]
token-classification
2023-12-27T15:42:29Z
Enter the sentence, it will determine the name, place and organization in the sentence
msamon/AdaptLLM-finance-chat-AWQ
msamon
2023-12-27T21:19:13Z
5
1
transformers
[ "transformers", "safetensors", "llama", "text-generation", "finance", "en", "dataset:Open-Orca/OpenOrca", "dataset:GAIR/lima", "dataset:WizardLM/WizardLM_evol_instruct_V2_196k", "arxiv:2309.09530", "license:llama2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "awq", "region:us" ]
text-generation
2023-12-27T20:59:22Z
--- language: - en license: llama2 datasets: - Open-Orca/OpenOrca - GAIR/lima - WizardLM/WizardLM_evol_instruct_V2_196k metrics: - accuracy pipeline_tag: text-generation tags: - finance --- # AdaptLLM finance-chat AWQ This repo contains the quantized version of the finance-chat model released by Microsoft / AdaptLLM. Original model card below: # Adapt (Large) Language Models to Domains This repo contains the domain-specific chat model developed from **LLaMA-2-Chat-7B**, using the method in our paper [Adapting Large Language Models via Reading Comprehension](https://huggingface.co/papers/2309.09530). We explore **continued pre-training on domain-specific corpora** for large language models. While this approach enriches LLMs with domain knowledge, it significantly hurts their prompting ability for question answering. Inspired by human learning via reading comprehension, we propose a simple method to **transform large-scale pre-training corpora into reading comprehension texts**, consistently improving prompting performance across tasks in biomedicine, finance, and law domains. **Our 7B model competes with much larger domain-specific models like BloombergGPT-50B**. ### 🤗 We are currently working hard on developing models across different domains, scales and architectures! Please stay tuned! 🤗 **************************** **Updates** **************************** * 12/19: Released our [13B base models](https://huggingface.co/AdaptLLM/finance-LLM-13B) developed from LLaMA-1-13B. * 12/8: Released our [chat models](https://huggingface.co/AdaptLLM/finance-chat) developed from LLaMA-2-Chat-7B. * 9/18: Released our [paper](https://huggingface.co/papers/2309.09530), [code](https://github.com/microsoft/LMOps), [data](https://huggingface.co/datasets/AdaptLLM/finance-tasks), and [base models](https://huggingface.co/AdaptLLM/finance-LLM) developed from LLaMA-1-7B. ## Domain-Specific LLaMA-1 ### LLaMA-1-7B In our paper, we develop three domain-specific models from LLaMA-1-7B, which are also available in Huggingface: [Biomedicine-LLM](https://huggingface.co/AdaptLLM/medicine-LLM), [Finance-LLM](https://huggingface.co/AdaptLLM/finance-LLM) and [Law-LLM](https://huggingface.co/AdaptLLM/law-LLM), the performances of our AdaptLLM compared to other domain-specific LLMs are: <p align='center'> <img src="https://cdn-uploads.huggingface.co/production/uploads/650801ced5578ef7e20b33d4/6efPwitFgy-pLTzvccdcP.png" width="700"> </p> ### LLaMA-1-13B Moreover, we scale up our base model to LLaMA-1-13B to see if **our method is similarly effective for larger-scale models**, and the results are consistently positive too: [Biomedicine-LLM-13B](https://huggingface.co/AdaptLLM/medicine-LLM-13B), [Finance-LLM-13B](https://huggingface.co/AdaptLLM/finance-LLM-13B) and [Law-LLM-13B](https://huggingface.co/AdaptLLM/law-LLM-13B). ## Domain-Specific LLaMA-2-Chat Our method is also effective for aligned models! LLaMA-2-Chat requires a [specific data format](https://huggingface.co/blog/llama2#how-to-prompt-llama-2), and our **reading comprehension can perfectly fit the data format** by transforming the reading comprehension into a multi-turn conversation. We have also open-sourced chat models in different domains: [Biomedicine-Chat](https://huggingface.co/AdaptLLM/medicine-chat), [Finance-Chat](https://huggingface.co/AdaptLLM/finance-chat) and [Law-Chat](https://huggingface.co/AdaptLLM/law-chat) For example, to chat with the finance model: ```python from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained("AdaptLLM/finance-chat") tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/finance-chat", use_fast=False) # Put your input here: user_input = '''Use this fact to answer the question: Title of each class Trading Symbol(s) Name of each exchange on which registered Common Stock, Par Value $.01 Per Share MMM New York Stock Exchange MMM Chicago Stock Exchange, Inc. 1.500% Notes due 2026 MMM26 New York Stock Exchange 1.750% Notes due 2030 MMM30 New York Stock Exchange 1.500% Notes due 2031 MMM31 New York Stock Exchange Which debt securities are registered to trade on a national securities exchange under 3M's name as of Q2 of 2023?''' # We use the prompt template of LLaMA-2-Chat demo prompt = f"<s>[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n\n{user_input} [/INST]" inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).input_ids.to(model.device) outputs = model.generate(input_ids=inputs, max_length=4096)[0] answer_start = int(inputs.shape[-1]) pred = tokenizer.decode(outputs[answer_start:], skip_special_tokens=True) print(f'### User Input:\n{user_input}\n\n### Assistant Output:\n{pred}') ``` ## Domain-Specific Tasks To easily reproduce our results, we have uploaded the filled-in zero/few-shot input instructions and output completions of each domain-specific task: [biomedicine-tasks](https://huggingface.co/datasets/AdaptLLM/medicine-tasks), [finance-tasks](https://huggingface.co/datasets/AdaptLLM/finance-tasks), and [law-tasks](https://huggingface.co/datasets/AdaptLLM/law-tasks). **Note:** those filled-in instructions are specifically tailored for models before alignment and do NOT fit for the specific data format required for chat models. ## Citation If you find our work helpful, please cite us: ```bibtex @article{adaptllm, title = {Adapting Large Language Models via Reading Comprehension}, author = {Daixuan Cheng and Shaohan Huang and Furu Wei}, journal = {CoRR}, volume = {abs/2309.09530}, year = {2023} } ```
LoneStriker/MixtralOrochi8x7B-4.0bpw-h6-exl2
LoneStriker
2023-12-27T21:19:13Z
7
0
transformers
[ "transformers", "safetensors", "mixtral", "text-generation", "uncensored", "high-intelligence", "en", "license:cc-by-nc-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-12-27T21:09:20Z
--- license: cc-by-nc-4.0 language: - en tags: - mixtral - uncensored - high-intelligence --- # Orochi <img src="https://huggingface.co/smelborp/MixtralOrochi8x7B/resolve/main/orochi.png" width="600" /> ## Overview Orochi is a cutting-edge language model based on the Mixtral architecture developed by Mistral. It represents a sophisticated merge of several prominent models, including Mixtral instruct, Noromaid, OpenBuddy, and several others, using mergekit with the DARE merge method. This model aims to provide highly intelligent responses unrestricted by content limitations. The name "Orochi" references the mythical Yamata-no-Orochi, symbolizing the model's multifaceted and powerful capabilities. ## Goals - **Uncensored Content**: To provide unrestricted and comprehensive responses across various domains. - **High Intelligence**: Leverage the combined knowledge and capabilities of the merged models to deliver insightful and accurate information. - **Innovation in Language Modeling**: Push the boundaries of what's possible in natural language understanding and generation. ## Model Details - **Architecture**: Mixtral, a Mixture of Experts model, underlies Orochi's design, enabling it to specialize and optimize its responses across different tasks and topics. - **Merge Strategy**: Utilizing mergekit and the DARE method, Orochi integrates aspects of various models to enhance its performance and capabilities. ## Usage Due to its uncensored nature, Orochi is best utilized in environments where intelligent, unrestricted dialogue is necessary. Users are encouraged to implement their own content moderation or alignment strategies appropriate for their use case. ## Ethical Considerations As an uncensored model, Orochi may generate content that is unsuitable for all audiences. Users are advised to consider the implications of using such a model and to implement suitable safeguards and ethical guidelines. ## Acknowledgements Orochi is a product of numerous contributions from the fields of machine learning and language modeling. Special thanks to the teams behind Mixtral, mergekit, and all the individual models integrated into Orochi. ---
andrijdavid/LMCocktail-10.7B-v1-GGUF
andrijdavid
2023-12-27T21:12:38Z
7
1
transformers
[ "transformers", "safetensors", "gguf", "llama", "text-generation", "GGUF", "conversational", "arxiv:2311.13534", "license:llama2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-12-27T19:54:45Z
--- license: llama2 tags: - GGUF quantized_by: andrijdavid --- # LMCocktail-10.7B-v1-GGUF - Original model: [LMCocktail-10.7B-v1](https://huggingface.co/Yhyu13/LMCocktail-10.7B-v1) <!-- description start --> ## Description This repo contains GGUF format model files for [LMCocktail-10.7B-v1](https://huggingface.co/Yhyu13/LMCocktail-10.7B-v1). <!-- description end --> <!-- README_GGUF.md-about-gguf start --> ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration. * [Ollama](https://github.com/jmorganca/ollama) Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications​ * [KoboldCpp](https://github.com/LostRuins/koboldcpp), A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling. * [GPT4All](https://gpt4all.io), This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration. * [LM Studio](https://lmstudio.ai/) An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui). A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection. * [Faraday.dev](https://faraday.dev/), An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use. * [ctransformers](https://github.com/marella/ctransformers), A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server. * [localGPT](https://github.com/PromtEngineer/localGPT) An open-source initiative enabling private conversations with documents. <!-- README_GGUF.md-about-gguf end --> <!-- compatibility_gguf start --> ## Explanation of quantisation methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw. </details> <!-- compatibility_gguf end --> <!-- README_GGUF.md-how-to-download start --> ## How to download GGUF files **Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: * LM Studio * LoLLMS Web UI * Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: andrijdavid/LMCocktail-10.7B-v1-GGUF and below it, a specific filename to download, such as: LMCocktail-10.7B-v1-f16.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download andrijdavid/LMCocktail-10.7B-v1-GGUF LMCocktail-10.7B-v1-f16.gguf --local-dir . --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage (click to read)</summary> You can also download multiple files at once with a pattern: ```shell huggingface-cli download andrijdavid/LMCocktail-10.7B-v1-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download andrijdavid/LMCocktail-10.7B-v1-GGUF LMCocktail-10.7B-v1-f16.gguf --local-dir . --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> <!-- README_GGUF.md-how-to-download end --> <!-- README_GGUF.md-how-to-run start --> ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 35 -m LMCocktail-10.7B-v1-f16.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<PROMPT>" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python. ### How to load this model in Python code, using llama-cpp-python For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/). #### First install the package Run one of the following commands, according to your system: ```shell # Base ctransformers with no GPU acceleration pip install llama-cpp-python # With NVidia CUDA acceleration CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python # Or with OpenBLAS acceleration CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python # Or with CLBLast acceleration CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python # Or with AMD ROCm GPU acceleration (Linux only) CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python # Or with Metal GPU acceleration for macOS systems only CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python # In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA: $env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on" pip install llama-cpp-python ``` #### Simple llama-cpp-python example code ```python from llama_cpp import Llama # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = Llama( model_path="./LMCocktail-10.7B-v1-f16.gguf", # Download the model file first n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available ) # Simple inference example output = llm( "<PROMPT>", # Prompt max_tokens=512, # Generate up to 512 tokens stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using. echo=True # Whether to echo the prompt ) # Chat Completion API llm = Llama(model_path="./LMCocktail-10.7B-v1-f16.gguf", chat_format="llama-2") # Set chat_format according to the model you are using llm.create_chat_completion( messages = [ {"role": "system", "content": "You are a story writing assistant."}, { "role": "user", "content": "Write a story about llamas." } ] ) ``` ## How to use with LangChain Here are guides on using llama-cpp-python and ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers) <!-- README_GGUF.md-how-to-run end --> <!-- footer end --> <!-- original-model-card start --> # Original model card: LMCocktail-10.7B-v1 # LM-cocktail 10.7B v1 This is a 50%-50% model of the SOLAR model and meow. https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0 https://huggingface.co/rishiraj/meow who rank #1 and #2 among models <13B in the https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard by 2023/12/20. # Alpaca Eval I am thrilled to announce that ChatGPT has ranked LMCocktail 10.7B as the second best model next to GPT4 on AlpcaEval in my local community run. You can also check the leaderboard at [./alpaca_eval/chatgpt_fn_--SOLAR-10-7B-LMCocktail/](./alpaca_eval/chatgpt_fn_--SOLAR-10-7B-LMCocktail/) ``` win_rate standard_error n_total avg_length gpt4 73.79 1.54 805 1365 SOLAR-10.7B-LMCocktail(new)73.45 1.56 804 1203 claude 70.37 1.60 805 1082 chatgpt 66.09 1.66 805 811 wizardlm-13b 65.16 1.67 805 985 vicuna-13b 64.10 1.69 805 1037 guanaco-65b 62.36 1.71 805 1249 oasst-rlhf-llama-33b 62.05 1.71 805 1079 alpaca-farm-ppo-human 60.25 1.72 805 803 falcon-40b-instruct 56.52 1.74 805 662 text_davinci_003 50.00 0.00 805 307 alpaca-7b 45.22 1.74 805 396 text_davinci_001 28.07 1.56 805 296 ``` # Code The LM-cocktail is novel technique for merging multiple models https://arxiv.org/abs/2311.13534 Code is backed up by this repo https://github.com/FlagOpen/FlagEmbedding.git Merging scripts available under the [./scripts](./scripts) folder # Result The SOLAR model is the first model <30B that can answer this question from my test: ``` What will AI be like in the year 1010 A.D? ``` without hullicinating into 1010 A.D is a future time (like other llama2 models) Models greater than that, like Yi-34B could answer this paradoxic question correctly as well, since it is huge enough. ### SOLAR 10.7B output ![img](./assets/SOLAR.png) ### LMCocktail 10.7B output1 ![img](./assets/SOLAR_mixed.png) ### LMCocktail 10.7B output2 ![img](./assets/SOLAR_mixed2.png) <!-- original-model-card end -->
alperaktasm/mistral-7b-dolly
alperaktasm
2023-12-27T21:08:07Z
1
0
peft
[ "peft", "safetensors", "arxiv:1910.09700", "base_model:mistralai/Mistral-7B-v0.1", "base_model:adapter:mistralai/Mistral-7B-v0.1", "region:us" ]
null
2023-12-27T20:25:29Z
--- library_name: peft base_model: mistralai/Mistral-7B-v0.1 --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.7.1
behzadnet/Llama-2-7b-chat-hf-sharded-bf16-fine-tuned_SystemError0.6_Seed105
behzadnet
2023-12-27T21:04:17Z
0
0
peft
[ "peft", "arxiv:1910.09700", "base_model:Trelis/Llama-2-7b-chat-hf-sharded-bf16", "base_model:adapter:Trelis/Llama-2-7b-chat-hf-sharded-bf16", "region:us" ]
null
2023-12-27T21:04:15Z
--- library_name: peft base_model: Trelis/Llama-2-7b-chat-hf-sharded-bf16 --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.7.0.dev0
behzadnet/Llama-2-7b-chat-hf-sharded-bf16-fine-tuned-adapters_SystemError0.6_Seed105
behzadnet
2023-12-27T21:04:08Z
0
0
peft
[ "peft", "arxiv:1910.09700", "base_model:Trelis/Llama-2-7b-chat-hf-sharded-bf16", "base_model:adapter:Trelis/Llama-2-7b-chat-hf-sharded-bf16", "region:us" ]
null
2023-12-27T21:04:01Z
--- library_name: peft base_model: Trelis/Llama-2-7b-chat-hf-sharded-bf16 --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.7.0.dev0 ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.7.0.dev0
LoneStriker/MixtralOrochi8x7B-3.0bpw-h6-exl2
LoneStriker
2023-12-27T20:50:47Z
5
0
transformers
[ "transformers", "safetensors", "mixtral", "text-generation", "uncensored", "high-intelligence", "en", "license:cc-by-nc-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-12-27T20:43:12Z
--- license: cc-by-nc-4.0 language: - en tags: - mixtral - uncensored - high-intelligence --- # Orochi <img src="https://huggingface.co/smelborp/MixtralOrochi8x7B/resolve/main/orochi.png" width="600" /> ## Overview Orochi is a cutting-edge language model based on the Mixtral architecture developed by Mistral. It represents a sophisticated merge of several prominent models, including Mixtral instruct, Noromaid, OpenBuddy, and several others, using mergekit with the DARE merge method. This model aims to provide highly intelligent responses unrestricted by content limitations. The name "Orochi" references the mythical Yamata-no-Orochi, symbolizing the model's multifaceted and powerful capabilities. ## Goals - **Uncensored Content**: To provide unrestricted and comprehensive responses across various domains. - **High Intelligence**: Leverage the combined knowledge and capabilities of the merged models to deliver insightful and accurate information. - **Innovation in Language Modeling**: Push the boundaries of what's possible in natural language understanding and generation. ## Model Details - **Architecture**: Mixtral, a Mixture of Experts model, underlies Orochi's design, enabling it to specialize and optimize its responses across different tasks and topics. - **Merge Strategy**: Utilizing mergekit and the DARE method, Orochi integrates aspects of various models to enhance its performance and capabilities. ## Usage Due to its uncensored nature, Orochi is best utilized in environments where intelligent, unrestricted dialogue is necessary. Users are encouraged to implement their own content moderation or alignment strategies appropriate for their use case. ## Ethical Considerations As an uncensored model, Orochi may generate content that is unsuitable for all audiences. Users are advised to consider the implications of using such a model and to implement suitable safeguards and ethical guidelines. ## Acknowledgements Orochi is a product of numerous contributions from the fields of machine learning and language modeling. Special thanks to the teams behind Mixtral, mergekit, and all the individual models integrated into Orochi. ---
pedroferreira/whisper-tiny-minds14-US-finetuned
pedroferreira
2023-12-27T20:48:49Z
4
0
transformers
[ "transformers", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "dataset:PolyAI/minds14", "base_model:openai/whisper-tiny", "base_model:finetune:openai/whisper-tiny", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]
automatic-speech-recognition
2023-12-27T20:04:34Z
--- license: apache-2.0 base_model: openai/whisper-tiny tags: - generated_from_trainer datasets: - PolyAI/minds14 metrics: - wer model-index: - name: whisper-tiny-minds14-US-finetuned results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: PolyAI/minds14 type: PolyAI/minds14 metrics: - name: Wer type: wer value: 0.2687576875768758 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # whisper-tiny-minds14-US-finetuned This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set: - Loss: 0.2827 - Wer Ortho: 26.6409 - Wer: 0.2688 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 50 - training_steps: 500 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:| | 0.0014 | 17.24 | 500 | 0.2827 | 26.6409 | 0.2688 | ### Framework versions - Transformers 4.36.2 - Pytorch 2.1.2+cu121 - Datasets 2.16.0 - Tokenizers 0.15.0
numblilbug/finetuning-distilbert-sentiment-model
numblilbug
2023-12-27T20:41:22Z
5
0
transformers
[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-multilingual-cased", "base_model:finetune:distilbert/distilbert-base-multilingual-cased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-12-27T15:43:34Z
--- license: apache-2.0 base_model: distilbert-base-multilingual-cased tags: - generated_from_trainer metrics: - accuracy model-index: - name: finetuning-sentiment-model-3000-samples results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # finetuning-sentiment-model-3000-samples This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.7689 - Accuracy: {'accuracy': 0.7368421052631579} ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu121 - Datasets 2.16.0 - Tokenizers 0.15.0
olesya2096/llama2-7b_distNER_mts
olesya2096
2023-12-27T20:07:25Z
0
0
peft
[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-chat-hf", "base_model:adapter:meta-llama/Llama-2-7b-chat-hf", "region:us" ]
null
2023-12-27T20:07:14Z
--- library_name: peft tags: - trl - sft - generated_from_trainer base_model: meta-llama/Llama-2-7b-chat-hf model-index: - name: llama2-7b_distNER_mts 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. --> # llama2-7b_distNER_mts This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) 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: 4e-05 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.03 - num_epochs: 5 ### Training results ### Framework versions - PEFT 0.7.2.dev0 - Transformers 4.36.2 - Pytorch 2.1.0+cu121 - Datasets 2.16.0 - Tokenizers 0.15.0
gusmoers/ppo-LunarLander-v2
gusmoers
2023-12-27T20:06:16Z
0
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-12-27T20:05:57Z
--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 260.02 +/- 18.32 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
perceptron-soup/Mistral_tcc_sft_v3
perceptron-soup
2023-12-27T20:05:57Z
0
0
peft
[ "peft", "safetensors", "arxiv:1910.09700", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "base_model:adapter:mistralai/Mistral-7B-Instruct-v0.2", "region:us" ]
null
2023-12-27T20:05:51Z
--- library_name: peft base_model: mistralai/Mistral-7B-Instruct-v0.2 --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.7.1
mayank1052/the-butterfly
mayank1052
2023-12-27T19:54:02Z
0
0
null
[ "safetensors", "NxtWave-GenAI-Webinar", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "region:us" ]
text-to-image
2023-12-27T19:51:00Z
--- license: creativeml-openrail-m tags: - NxtWave-GenAI-Webinar - text-to-image - stable-diffusion --- ### The-Butterfly Dreambooth model trained by mayank1052 following the "Build your own Gen AI model" session by NxtWave. Project Submission Code: 202102021052 Sample pictures of this concept: ![0](https://huggingface.co/mayank1052/the-butterfly/resolve/main/sample_images/10.png)
ntc-ai/SDXL-LoRA-slider.micro-details-fine-details-detailed
ntc-ai
2023-12-27T19:51:14Z
215
4
diffusers
[ "diffusers", "text-to-image", "stable-diffusion-xl", "lora", "template:sd-lora", "template:sdxl-lora", "sdxl-sliders", "ntcai.xyz-sliders", "concept", "en", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:mit", "region:us" ]
text-to-image
2023-12-27T19:51:12Z
--- language: - en thumbnail: "images/evaluate/micro details, fine details, detailed.../micro details, fine details, detailed_17_3.0.png" widget: - text: micro details, fine details, detailed output: url: images/micro details, fine details, detailed_17_3.0.png - text: micro details, fine details, detailed output: url: images/micro details, fine details, detailed_19_3.0.png - text: micro details, fine details, detailed output: url: images/micro details, fine details, detailed_20_3.0.png - text: micro details, fine details, detailed output: url: images/micro details, fine details, detailed_21_3.0.png - text: micro details, fine details, detailed output: url: images/micro details, fine details, detailed_22_3.0.png tags: - text-to-image - stable-diffusion-xl - lora - template:sd-lora - template:sdxl-lora - sdxl-sliders - ntcai.xyz-sliders - concept - diffusers license: "mit" inference: false instance_prompt: "micro details, fine details, detailed" base_model: "stabilityai/stable-diffusion-xl-base-1.0" --- # ntcai.xyz slider - micro details, fine details, detailed (SDXL LoRA) | Strength: -3 | Strength: 0 | Strength: 3 | | --- | --- | --- | | <img src="images/micro details, fine details, detailed_17_-3.0.png" width=256 height=256 /> | <img src="images/micro details, fine details, detailed_17_0.0.png" width=256 height=256 /> | <img src="images/micro details, fine details, detailed_17_3.0.png" width=256 height=256 /> | | <img src="images/micro details, fine details, detailed_19_-3.0.png" width=256 height=256 /> | <img src="images/micro details, fine details, detailed_19_0.0.png" width=256 height=256 /> | <img src="images/micro details, fine details, detailed_19_3.0.png" width=256 height=256 /> | | <img src="images/micro details, fine details, detailed_20_-3.0.png" width=256 height=256 /> | <img src="images/micro details, fine details, detailed_20_0.0.png" width=256 height=256 /> | <img src="images/micro details, fine details, detailed_20_3.0.png" width=256 height=256 /> | ## Download Weights for this model are available in Safetensors format. ## Trigger words You can apply this LoRA with trigger words for additional effect: ``` micro details, fine details, detailed ``` ## Use in diffusers ```python from diffusers import StableDiffusionXLPipeline from diffusers import EulerAncestralDiscreteScheduler import torch pipe = StableDiffusionXLPipeline.from_single_file("https://huggingface.co/martyn/sdxl-turbo-mario-merge-top-rated/blob/main/topRatedTurboxlLCM_v10.safetensors") pipe.to("cuda") pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config) # Load the LoRA pipe.load_lora_weights('ntc-ai/SDXL-LoRA-slider.micro-details-fine-details-detailed', weight_name='micro details, fine details, detailed.safetensors', adapter_name="micro details, fine details, detailed") # Activate the LoRA pipe.set_adapters(["micro details, fine details, detailed"], adapter_weights=[2.0]) prompt = "medieval rich kingpin sitting in a tavern, micro details, fine details, detailed" negative_prompt = "nsfw" width = 512 height = 512 num_inference_steps = 10 guidance_scale = 2 image = pipe(prompt, negative_prompt=negative_prompt, width=width, height=height, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps).images[0] image.save('result.png') ``` ## Support the Patreon If you like this model please consider [joining our Patreon](https://www.patreon.com/NTCAI). By joining our Patreon, you'll gain access to an ever-growing library of over 670+ unique and diverse LoRAs, covering a wide range of styles and genres. You'll also receive early access to new models and updates, exclusive behind-the-scenes content, and the powerful LoRA slider creator, allowing you to craft your own custom LoRAs and experiment with endless possibilities. Your support on Patreon will allow us to continue developing and refining new models. ## Other resources - [CivitAI](https://civitai.com/user/ntc) - Follow ntc on Civit for even more LoRAs - [ntcai.xyz](https://ntcai.xyz) - See ntcai.xyz to find more articles and LoRAs
giangvlcs/LongGiang_textual_inversion
giangvlcs
2023-12-27T19:42:40Z
10
0
diffusers
[ "diffusers", "tensorboard", "safetensors", "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
2023-12-27T15:22:03Z
--- 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 - giangvlcs/LongGiang_textual_inversion These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.
Realgon/N_bert_agnews_padding50model
Realgon
2023-12-27T19:38:15Z
9
0
transformers
[ "transformers", "pytorch", "bert", "text-classification", "generated_from_trainer", "dataset:ag_news", "base_model:google-bert/bert-base-uncased", "base_model:finetune:google-bert/bert-base-uncased", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-12-27T17:03:43Z
--- license: apache-2.0 base_model: bert-base-uncased tags: - generated_from_trainer datasets: - ag_news metrics: - accuracy model-index: - name: N_bert_agnews_padding50model results: - task: name: Text Classification type: text-classification dataset: name: ag_news type: ag_news config: default split: test args: default metrics: - name: Accuracy type: accuracy value: 0.9467105263157894 --- <!-- 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. --> # N_bert_agnews_padding50model This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the ag_news dataset. It achieves the following results on the evaluation set: - Loss: 0.5754 - Accuracy: 0.9467 ## 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: 20 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:------:|:---------------:|:--------:| | 0.1754 | 1.0 | 7500 | 0.1909 | 0.9428 | | 0.1362 | 2.0 | 15000 | 0.1928 | 0.9461 | | 0.1139 | 3.0 | 22500 | 0.2106 | 0.9461 | | 0.0825 | 4.0 | 30000 | 0.2544 | 0.9466 | | 0.0565 | 5.0 | 37500 | 0.3046 | 0.9367 | | 0.0372 | 6.0 | 45000 | 0.3764 | 0.9436 | | 0.0347 | 7.0 | 52500 | 0.3646 | 0.9425 | | 0.0346 | 8.0 | 60000 | 0.3826 | 0.9461 | | 0.0247 | 9.0 | 67500 | 0.4244 | 0.9455 | | 0.0113 | 10.0 | 75000 | 0.4418 | 0.9446 | | 0.0166 | 11.0 | 82500 | 0.4917 | 0.9462 | | 0.0157 | 12.0 | 90000 | 0.4662 | 0.9442 | | 0.0124 | 13.0 | 97500 | 0.4864 | 0.9438 | | 0.0055 | 14.0 | 105000 | 0.4912 | 0.9457 | | 0.0102 | 15.0 | 112500 | 0.5040 | 0.9446 | | 0.0045 | 16.0 | 120000 | 0.5200 | 0.9441 | | 0.0038 | 17.0 | 127500 | 0.5374 | 0.9467 | | 0.0012 | 18.0 | 135000 | 0.5605 | 0.9459 | | 0.0005 | 19.0 | 142500 | 0.5809 | 0.9455 | | 0.0003 | 20.0 | 150000 | 0.5754 | 0.9467 | ### Framework versions - Transformers 4.33.2 - Pytorch 2.0.1+cu117 - Datasets 2.14.5 - Tokenizers 0.13.3
Marcus1974/marcus_LoRA
Marcus1974
2023-12-27T19:33:52Z
1
1
diffusers
[ "diffusers", "tensorboard", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "lora", "template:sd-lora", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]
text-to-image
2023-12-27T19:33:50Z
--- tags: - stable-diffusion-xl - stable-diffusion-xl-diffusers - text-to-image - diffusers - lora - template:sd-lora base_model: stabilityai/stable-diffusion-xl-base-1.0 instance_prompt: MarcusFriede1974 license: openrail++ --- # SDXL LoRA DreamBooth - Marcus1974/marcus_LoRA <Gallery /> ## Model description These are Marcus1974/marcus_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained using [DreamBooth](https://dreambooth.github.io/). LoRA for the text encoder was enabled: False. Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. ## Trigger words You should use MarcusFriede1974 to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](Marcus1974/marcus_LoRA/tree/main) them in the Files & versions tab.
rvv-karma/BASH-Coder-Mistral-7B
rvv-karma
2023-12-27T19:33:33Z
12
1
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "finetuned", "en", "dataset:neulab/tldr", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-12-21T15:29:03Z
--- language: - en tags: - text-generation - finetuned datasets: - neulab/tldr license: apache-2.0 pipeline_tag: text-generation --- # Commonsense-QA-Mistral-7B This is a finetuned model of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) with [neulab/tldr](https://huggingface.co/datasets/neulab/tldr) dataset. The model is loaded in 4-bit and fine-tuned with LoRA. ## Usage ### Loading of model: ```python # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained( "rvv-karma/BASH-Coder-Mistral-7B", low_cpu_mem_usage=True, return_dict=True, torch_dtype=torch.bfloat16, device_map="auto", ) tokenizer = AutoTokenizer.from_pretrained("rvv-karma/BASH-Coder-Mistral-7B", trust_remote_code=True) tokenizer.pad_token = tokenizer.eos_token tokenizer.padding_side = "left" ``` ### Sample: ```python pipe = pipeline( task="text-generation", model=model, tokenizer=tokenizer, return_full_text=False, pad_token_id=tokenizer.pad_token_id, eos_token_id=13, max_new_tokens=8 ) prompt = """QUESTION: fix a given ntfs partition ANSWER: """ result = pipe(prompt) generated = result[0]['generated_text'] print(generated) # Output: sudo ntfsfix {{/dev/sdXN}} ``` ## Fine-tuning script [Kaggle Notebook](https://www.kaggle.com/code/rvkarma/bash-coder-mistral-7b)
Dulfary/platzi-vit-model-omar-espejel
Dulfary
2023-12-27T19:33:09Z
5
0
transformers
[ "transformers", "tensorboard", "safetensors", "vit", "image-classification", "generated_from_trainer", "base_model:google/vit-base-patch16-224-in21k", "base_model:finetune:google/vit-base-patch16-224-in21k", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
image-classification
2023-12-27T19:29:37Z
--- license: apache-2.0 base_model: google/vit-base-patch16-224-in21k tags: - generated_from_trainer metrics: - accuracy model-index: - name: platzi-vit-model-omar-espejel 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. --> # platzi-vit-model-omar-espejel This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1062 - 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 | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.1461 | 3.85 | 500 | 0.1062 | 0.9774 | ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu121 - Datasets 2.16.0 - Tokenizers 0.15.0
afrideva/RocketZephyr-3b-GGUF
afrideva
2023-12-27T19:30:59Z
33
1
null
[ "gguf", "ggml", "quantized", "q2_k", "q3_k_m", "q4_k_m", "q5_k_m", "q6_k", "q8_0", "text-generation", "base_model:TitleOS/RocketZephyr-3b", "base_model:quantized:TitleOS/RocketZephyr-3b", "license:other", "region:us" ]
text-generation
2023-12-27T19:22:24Z
--- base_model: TitleOS/RocketZephyr-3b inference: false license: other license_link: LICENSE license_name: stabilityai-non-commerical-license model_creator: TitleOS model_name: RocketZephyr-3b pipeline_tag: text-generation quantized_by: afrideva tags: - gguf - ggml - quantized - q2_k - q3_k_m - q4_k_m - q5_k_m - q6_k - q8_0 --- # TitleOS/RocketZephyr-3b-GGUF Quantized GGUF model files for [RocketZephyr-3b](https://huggingface.co/TitleOS/RocketZephyr-3b) from [TitleOS](https://huggingface.co/TitleOS) | Name | Quant method | Size | | ---- | ---- | ---- | | [rocketzephyr-3b.fp16.gguf](https://huggingface.co/afrideva/RocketZephyr-3b-GGUF/resolve/main/rocketzephyr-3b.fp16.gguf) | fp16 | 5.59 GB | | [rocketzephyr-3b.q2_k.gguf](https://huggingface.co/afrideva/RocketZephyr-3b-GGUF/resolve/main/rocketzephyr-3b.q2_k.gguf) | q2_k | 1.20 GB | | [rocketzephyr-3b.q3_k_m.gguf](https://huggingface.co/afrideva/RocketZephyr-3b-GGUF/resolve/main/rocketzephyr-3b.q3_k_m.gguf) | q3_k_m | 1.39 GB | | [rocketzephyr-3b.q4_k_m.gguf](https://huggingface.co/afrideva/RocketZephyr-3b-GGUF/resolve/main/rocketzephyr-3b.q4_k_m.gguf) | q4_k_m | 1.71 GB | | [rocketzephyr-3b.q5_k_m.gguf](https://huggingface.co/afrideva/RocketZephyr-3b-GGUF/resolve/main/rocketzephyr-3b.q5_k_m.gguf) | q5_k_m | 1.99 GB | | [rocketzephyr-3b.q6_k.gguf](https://huggingface.co/afrideva/RocketZephyr-3b-GGUF/resolve/main/rocketzephyr-3b.q6_k.gguf) | q6_k | 2.30 GB | | [rocketzephyr-3b.q8_0.gguf](https://huggingface.co/afrideva/RocketZephyr-3b-GGUF/resolve/main/rocketzephyr-3b.q8_0.gguf) | q8_0 | 2.97 GB | ## Original Model Card: # RocketZephyr-3B <!-- Provide a quick summary of what the model is/does. --> An attempt at creating a 3B parameter merged model using [StabilityAI's Zephyr-3b](https://huggingface.co/stabilityai/stablelm-zephyr-3b) and [Pansophic's Rocket-3B](https://huggingface.co/pansophic/rocket-3B). ### Repo Description This repo serves as an housing for my experimentation with creating a 3 billion parameter merged model using [mergekit](https://github.com/cg123/mergekit) - **Merged Models:** stabilityai/stablelm-zephyr-3b & pansophic/rocket-3B - **Merge Weights:** 1.0 & 0.3 - **Merge Method:** Linear - **License:** I believe this (current) model inherits the Stable Non-Commercial Research Community License Agreement and as such is licensed by it as well.
afrideva/tinycodellama-1.3b-3k-GGUF
afrideva
2023-12-27T19:19:53Z
41
0
null
[ "gguf", "ggml", "quantized", "q2_k", "q3_k_m", "q4_k_m", "q5_k_m", "q6_k", "q8_0", "text-generation", "base_model:obrmmk/tinycodellama-jp-1.3b-3k", "base_model:quantized:obrmmk/tinycodellama-jp-1.3b-3k", "region:us" ]
text-generation
2023-12-27T19:15:58Z
--- base_model: obrmmk/tinycodellama-1.3b-3k inference: false model_creator: obrmmk model_name: tinycodellama-1.3b-3k pipeline_tag: text-generation quantized_by: afrideva tags: - gguf - ggml - quantized - q2_k - q3_k_m - q4_k_m - q5_k_m - q6_k - q8_0 --- # obrmmk/tinycodellama-1.3b-3k-GGUF Quantized GGUF model files for [tinycodellama-1.3b-3k](https://huggingface.co/obrmmk/tinycodellama-1.3b-3k) from [obrmmk](https://huggingface.co/obrmmk) | Name | Quant method | Size | | ---- | ---- | ---- | | [tinycodellama-1.3b-3k.fp16.gguf](https://huggingface.co/afrideva/tinycodellama-1.3b-3k-GGUF/resolve/main/tinycodellama-1.3b-3k.fp16.gguf) | fp16 | 2.58 GB | | [tinycodellama-1.3b-3k.q2_k.gguf](https://huggingface.co/afrideva/tinycodellama-1.3b-3k-GGUF/resolve/main/tinycodellama-1.3b-3k.q2_k.gguf) | q2_k | 565.81 MB | | [tinycodellama-1.3b-3k.q3_k_m.gguf](https://huggingface.co/afrideva/tinycodellama-1.3b-3k-GGUF/resolve/main/tinycodellama-1.3b-3k.q3_k_m.gguf) | q3_k_m | 644.08 MB | | [tinycodellama-1.3b-3k.q4_k_m.gguf](https://huggingface.co/afrideva/tinycodellama-1.3b-3k-GGUF/resolve/main/tinycodellama-1.3b-3k.q4_k_m.gguf) | q4_k_m | 792.15 MB | | [tinycodellama-1.3b-3k.q5_k_m.gguf](https://huggingface.co/afrideva/tinycodellama-1.3b-3k-GGUF/resolve/main/tinycodellama-1.3b-3k.q5_k_m.gguf) | q5_k_m | 921.00 MB | | [tinycodellama-1.3b-3k.q6_k.gguf](https://huggingface.co/afrideva/tinycodellama-1.3b-3k-GGUF/resolve/main/tinycodellama-1.3b-3k.q6_k.gguf) | q6_k | 1.06 GB | | [tinycodellama-1.3b-3k.q8_0.gguf](https://huggingface.co/afrideva/tinycodellama-1.3b-3k-GGUF/resolve/main/tinycodellama-1.3b-3k.q8_0.gguf) | q8_0 | 1.37 GB | ## Original Model Card:
highwater/ppo-LunarLander-v2
highwater
2023-12-27T19:14:20Z
0
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-12-27T19:13:58Z
--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 247.22 +/- 16.36 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
nisten/quad-mixtrals-gguf
nisten
2023-12-27T19:14:16Z
466
31
null
[ "gguf", "license:apache-2.0", "endpoints_compatible", "region:us" ]
null
2023-12-22T23:36:12Z
--- license: apache-2.0 --- **Experimental quants of 4 expert MoE mixtrals in various GGUF formats.** Original model used for custom quants: ***NeverSleep/Mistral-11B-SynthIAirOmniMix*** https://huggingface.co/NeverSleep/Mistral-11B-SynthIAirOmniMix **Goal is to have the best performing MoE < 10gb** Experimental q8 and q4 files for training/finetuning too. ***No sparsity tricks yet.*** 8.4gb custom 2bit quant works ok up until 512 token length then starts looping. - Install llama.cpp from github and run it: ```bash git clone https://github.com/ggerganov/llama.cpp cd llama.cpp make -j wget https://huggingface.co/nisten/quad-mixtrals-gguf/resolve/main/4mixq2.gguf ./server -m 4mixq2.gguf --host "my.internal.ip.or.my.cloud.host.name.goes.here.com" -c 512 ``` limit output to 500 tokens
MattStammers/appo-mujoco_pendulum-sota
MattStammers
2023-12-27T19:13:34Z
0
0
sample-factory
[ "sample-factory", "tensorboard", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-12-27T19:13:21Z
--- 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: mujoco_pendulum type: mujoco_pendulum metrics: - type: mean_reward value: 1000.00 +/- 0.00 name: mean_reward verified: false --- ## About the Project This project is an attempt to maximise performance of high sample throughput APPO RL models in Atari environments in as carbon efficient a manner as possible using a single, not particularly high performance single machine. It is about demonstrating the generalisability of on-policy algorithms to create good performance quickly (by sacrificing sample efficiency) while also proving that this route to RL production is accessible to even hobbyists like me (I am a gastroenterologist not a computer scientist). In terms of throughput I am managing to reach throughputs of 2,500 - 3,000 across both policies using sample factory using two Quadro P2200's (not particularly powerful GPUs) each loaded up about 60% (3GB). Previously using the stable baselines 3 (sb3) implementation of PPO it would take about a week to train an atari agent to 100 million timesteps synchronously. By comparison the sample factory async implementation takes only just over 2 hours to achieve the same result. That is about 84 times faster with only typically a 21 watt burn per GPU. I am thus very grateful to Alex Petrenko and all the sample factory team for their work on this. ## Project Aims This model as with all the others in the benchmarks was trained initially asynchronously un-seeded to 10 million steps for the purposes of setting a sample factory async baseline for this model on this environment but only 3/57 made it anywhere near sota performance. I then re-trained the models with 100 million timesteps- at this point 2 environments maxed out at sota performance (Pong and Freeway) with four approaching sota performance - (atlantis, boxing, tennis and fishingderby.) =6/57 near sota. The aim now is to try and reach state-of-the-art (SOTA) performance on a further block of atari environments using up to 1 billion training timesteps initially with appo. I will flag the models with SOTA when they reach at or near these levels. After this I will switch on V-Trace to see if the Impala variations perform any better with the same seed (I have seeded '1234') ## About the Model The hyperparameters used in the model are described in my shell script on my fork of sample-factory: https://github.com/MattStammers/sample-factory. Given that https://huggingface.co/edbeeching has kindly shared his parameters, I saved time and energy by using many of his tuned hyperparameters to reduce carbon inefficiency: ``` hyperparameters = { "help": false, "algo": "APPO", "env": "atari_asteroid", "experiment": "atari_asteroid_APPO", "train_dir": "./train_atari", "restart_behavior": "restart", "device": "gpu", "seed": 1234, "num_policies": 2, "async_rl": true, "serial_mode": false, "batched_sampling": true, "num_batches_to_accumulate": 2, "worker_num_splits": 1, "policy_workers_per_policy": 1, "max_policy_lag": 1000, "num_workers": 16, "num_envs_per_worker": 2, "batch_size": 1024, "num_batches_per_epoch": 8, "num_epochs": 4, "rollout": 128, "recurrence": 1, "shuffle_minibatches": false, "gamma": 0.99, "reward_scale": 1.0, "reward_clip": 1000.0, "value_bootstrap": false, "normalize_returns": true, "exploration_loss_coeff": 0.0004677351413, "value_loss_coeff": 0.5, "kl_loss_coeff": 0.0, "exploration_loss": "entropy", "gae_lambda": 0.95, "ppo_clip_ratio": 0.1, "ppo_clip_value": 1.0, "with_vtrace": true, "vtrace_rho": 1.0, "vtrace_c": 1.0, "optimizer": "adam", "adam_eps": 1e-05, "adam_beta1": 0.9, "adam_beta2": 0.999, "max_grad_norm": 0.0, "learning_rate": 0.0003033891184, "lr_schedule": "linear_decay", "lr_schedule_kl_threshold": 0.008, "lr_adaptive_min": 1e-06, "lr_adaptive_max": 0.01, "obs_subtract_mean": 0.0, "obs_scale": 255.0, "normalize_input": true, "normalize_input_keys": [ "obs" ], "decorrelate_experience_max_seconds": 0, "decorrelate_envs_on_one_worker": true, "actor_worker_gpus": [], "set_workers_cpu_affinity": true, "force_envs_single_thread": false, "default_niceness": 0, "log_to_file": true, "experiment_summaries_interval": 3, "flush_summaries_interval": 30, "stats_avg": 100, "summaries_use_frameskip": true, "heartbeat_interval": 10, "heartbeat_reporting_interval": 60, "train_for_env_steps": 100000000, "train_for_seconds": 10000000000, "save_every_sec": 120, "keep_checkpoints": 2, "load_checkpoint_kind": "latest", "save_milestones_sec": 1200, "save_best_every_sec": 5, "save_best_metric": "reward", "save_best_after": 100000, "benchmark": false, "encoder_mlp_layers": [ 512, 512 ], "encoder_conv_architecture": "convnet_atari", "encoder_conv_mlp_layers": [ 512 ], "use_rnn": false, "rnn_size": 512, "rnn_type": "gru", "rnn_num_layers": 1, "decoder_mlp_layers": [], "nonlinearity": "relu", "policy_initialization": "orthogonal", "policy_init_gain": 1.0, "actor_critic_share_weights": true, "adaptive_stddev": false, "continuous_tanh_scale": 0.0, "initial_stddev": 1.0, "use_env_info_cache": false, "env_gpu_actions": false, "env_gpu_observations": true, "env_frameskip": 4, "env_framestack": 4, "pixel_format": "CHW" } ``` A(n) **APPO** impala model trained on the **mujoco_pendulum** environment. This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Sample factory is a high throughput on-policy RL framework. I have been using 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 MattStammers/APPO-mujoco_pendulum ``` ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: ``` python -m sf_examples.mujoco.enjoy_mujoco --algo=APPO --env=mujoco_pendulum --train_dir=./train_dir --experiment=APPO-mujoco_pendulum ``` 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 sf_examples.mujoco.train_mujoco --algo=APPO --env=mujoco_pendulum --train_dir=./train_dir --experiment=APPO-mujoco_pendulum --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.
ybelkada/test-axolotl-reloratrainer
ybelkada
2023-12-27T19:03:26Z
4
0
transformers
[ "transformers", "safetensors", "opt", "text-generation", "axolotl", "relora", "generated_from_trainer", "base_model:facebook/opt-125m", "base_model:finetune:facebook/opt-125m", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-12-27T19:03:10Z
--- license: other base_model: facebook/opt-125m tags: - axolotl - relora - generated_from_trainer model-index: - name: test-axolotl-reloratrainer results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # test-axolotl-reloratrainer This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Framework versions - Transformers 4.37.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.16.0 - Tokenizers 0.15.0
ybelkada/test-axolotl-onecyclelrschedulertrainer
ybelkada
2023-12-27T19:03:08Z
4
0
transformers
[ "transformers", "safetensors", "opt", "text-generation", "axolotl", "onecycle", "generated_from_trainer", "base_model:facebook/opt-125m", "base_model:finetune:facebook/opt-125m", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-12-27T19:02:54Z
--- license: other base_model: facebook/opt-125m tags: - axolotl - onecycle - generated_from_trainer model-index: - name: test-axolotl-onecyclelrschedulertrainer results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # test-axolotl-onecyclelrschedulertrainer This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Framework versions - Transformers 4.37.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.16.0 - Tokenizers 0.15.0
ybelkada/test-axolotl-axolotltrainer
ybelkada
2023-12-27T19:02:22Z
6
0
transformers
[ "transformers", "safetensors", "opt", "text-generation", "axolotl", "generated_from_trainer", "base_model:facebook/opt-125m", "base_model:finetune:facebook/opt-125m", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-12-27T19:02:00Z
--- license: other base_model: facebook/opt-125m tags: - axolotl - generated_from_trainer model-index: - name: test-axolotl-axolotltrainer results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # test-axolotl-axolotltrainer This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Framework versions - Transformers 4.37.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.16.0 - Tokenizers 0.15.0
ybelkada/test-axolotl
ybelkada
2023-12-27T18:59:47Z
3
0
transformers
[ "transformers", "safetensors", "opt", "text-generation", "axolotl", "generated_from_trainer", "base_model:facebook/opt-125m", "base_model:finetune:facebook/opt-125m", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-12-27T18:59:33Z
--- license: other base_model: facebook/opt-125m tags: - axolotl - generated_from_trainer model-index: - name: test-axolotl results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # test-axolotl This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Framework versions - Transformers 4.37.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.16.0 - Tokenizers 0.15.0
ostapeno/neo-1B-trainwithevol-basetest_decoration_ai1_debug
ostapeno
2023-12-27T18:58:59Z
0
0
null
[ "region:us" ]
null
2023-12-27T18:52:57Z
Number of experts present in the library: 1 | Expert Name | Base Model | Trained on | Adapter Type | | --- | --- | --- | --- | | ai2_arc_ARC_Challenge_1_0_0_v4 | EleutherAI/gpt-neo-1.3B | sordonia/adauni-v3-10k-flat/ai2_arc_ARC_Challenge_1_0_0 | lora | Last updated on: 2023-12-27 18:58:58+00:00
Pongsaky/ppo-LunarLander-Oputna
Pongsaky
2023-12-27T18:53:46Z
0
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-12-27T18:48:09Z
--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 80.65 +/- 119.13 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
Prezily/gpt2-trial-r2
Prezily
2023-12-27T18:49:53Z
7
0
transformers
[ "transformers", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "base_model:microsoft/DialoGPT-small", "base_model:finetune:microsoft/DialoGPT-small", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-12-27T18:49:37Z
--- license: mit base_model: microsoft/DialoGPT-small tags: - generated_from_trainer model-index: - name: gpt2-trial-r2 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # gpt2-trial-r2 This model is a fine-tuned version of [microsoft/DialoGPT-small](https://huggingface.co/microsoft/DialoGPT-small) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 16 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 5 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.36.2 - Pytorch 2.1.0+cu121 - Datasets 2.16.0 - Tokenizers 0.15.0
hindesh/drl-ppo-lunarlander
hindesh
2023-12-27T18:48:24Z
0
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-12-27T18:48:08Z
--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: -285.72 +/- 146.63 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
SamSJackson/custom-ppo-LunarLander-v2
SamSJackson
2023-12-27T18:47:52Z
0
0
null
[ "tensorboard", "LunarLander-v2", "ppo", "deep-reinforcement-learning", "reinforcement-learning", "custom-implementation", "deep-rl-course", "model-index", "region:us" ]
reinforcement-learning
2023-12-27T18:47:44Z
--- 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: -236.47 +/- 130.38 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' 'seed': 1 'torch_deterministic': True 'cuda': True 'track': False 'wandb_project_name': 'cleanRL' 'wandb_entity': None 'capture_video': False 'env_id': 'LunarLander-v2' 'total_timesteps': 5000 'learning_rate': 0.00025 'num_envs': 4 'num_steps': 128 'anneal_lr': True 'gae': True 'gamma': 0.99 'gae_lambda': 0.95 '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': 'SamSJackson/custom-ppo-LunarLander-v2' 'batch_size': 512 'minibatch_size': 128} ```
mlabonne/NeuralQuant-9B
mlabonne
2023-12-27T18:40:01Z
1,500
0
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "merge", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-12-27T18:32:27Z
--- license: apache-2.0 tags: - merge --- # NeuralQuant-9B This model is a merge of the following models made with [mergekit](https://github.com/cg123/mergekit): * [quantumaikr/quantum-v0.01](https://huggingface.co/quantumaikr/quantum-v0.01) * [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B) ## 🧩 Configuration ```yaml slices: - sources: - model: quantumaikr/quantum-v0.01 layer_range: [0, 32] - sources: - model: mlabonne/NeuralHermes-2.5-Mistral-7B layer_range: [24, 32] merge_method: passthrough dtype: bfloat16 ```
mmcgovern574/speecht5_finetuned_voxpopuli_nl
mmcgovern574
2023-12-27T18:37:07Z
7
0
transformers
[ "transformers", "tensorboard", "safetensors", "speecht5", "text-to-audio", "generated_from_trainer", "dataset:voxpopuli", "base_model:microsoft/speecht5_tts", "base_model:finetune:microsoft/speecht5_tts", "license:mit", "endpoints_compatible", "region:us" ]
text-to-audio
2023-12-27T16:36:58Z
--- license: mit base_model: microsoft/speecht5_tts tags: - generated_from_trainer datasets: - voxpopuli model-index: - name: speecht5_finetuned_voxpopuli_nl results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # speecht5_finetuned_voxpopuli_nl This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset. It achieves the following results on the evaluation set: - Loss: 0.4604 ## 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: 2 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 0.5202 | 4.3 | 1000 | 0.4813 | | 0.4966 | 8.61 | 2000 | 0.4668 | | 0.4905 | 12.91 | 3000 | 0.4617 | | 0.493 | 17.21 | 4000 | 0.4604 | ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu121 - Datasets 2.16.0 - Tokenizers 0.15.0
hkivancoral/smids_10x_beit_large_adamax_001_fold2
hkivancoral
2023-12-27T18:34:25Z
3
0
transformers
[ "transformers", "pytorch", "beit", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/beit-large-patch16-224", "base_model:finetune:microsoft/beit-large-patch16-224", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
image-classification
2023-12-27T14:03:52Z
--- license: apache-2.0 base_model: microsoft/beit-large-patch16-224 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: smids_10x_beit_large_adamax_001_fold2 results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: test args: default metrics: - name: Accuracy type: accuracy value: 0.8535773710482529 --- <!-- 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. --> # smids_10x_beit_large_adamax_001_fold2 This model is a fine-tuned version of [microsoft/beit-large-patch16-224](https://huggingface.co/microsoft/beit-large-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 1.4058 - Accuracy: 0.8536 ## 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: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:| | 0.6414 | 1.0 | 750 | 0.6828 | 0.6639 | | 0.5428 | 2.0 | 1500 | 0.5438 | 0.7754 | | 0.4614 | 3.0 | 2250 | 0.4523 | 0.8336 | | 0.4233 | 4.0 | 3000 | 0.4215 | 0.8236 | | 0.4304 | 5.0 | 3750 | 0.4599 | 0.7903 | | 0.3335 | 6.0 | 4500 | 0.4118 | 0.8336 | | 0.3481 | 7.0 | 5250 | 0.4939 | 0.8253 | | 0.3092 | 8.0 | 6000 | 0.4308 | 0.8486 | | 0.2568 | 9.0 | 6750 | 0.4756 | 0.8353 | | 0.331 | 10.0 | 7500 | 0.4715 | 0.8619 | | 0.2403 | 11.0 | 8250 | 0.5349 | 0.8469 | | 0.2162 | 12.0 | 9000 | 0.5922 | 0.8136 | | 0.2489 | 13.0 | 9750 | 0.5818 | 0.8419 | | 0.0972 | 14.0 | 10500 | 0.6218 | 0.8419 | | 0.1212 | 15.0 | 11250 | 0.5371 | 0.8436 | | 0.1175 | 16.0 | 12000 | 0.6818 | 0.8286 | | 0.1011 | 17.0 | 12750 | 0.8719 | 0.8120 | | 0.179 | 18.0 | 13500 | 0.7106 | 0.8486 | | 0.1325 | 19.0 | 14250 | 0.6119 | 0.8552 | | 0.111 | 20.0 | 15000 | 0.7905 | 0.8552 | | 0.0431 | 21.0 | 15750 | 0.8636 | 0.8469 | | 0.0973 | 22.0 | 16500 | 0.9921 | 0.8403 | | 0.0529 | 23.0 | 17250 | 0.7563 | 0.8536 | | 0.1212 | 24.0 | 18000 | 1.1228 | 0.8103 | | 0.0377 | 25.0 | 18750 | 1.0572 | 0.8386 | | 0.035 | 26.0 | 19500 | 0.8767 | 0.8536 | | 0.0591 | 27.0 | 20250 | 0.9535 | 0.8652 | | 0.0188 | 28.0 | 21000 | 1.1035 | 0.8536 | | 0.0402 | 29.0 | 21750 | 1.1575 | 0.8586 | | 0.0333 | 30.0 | 22500 | 1.1473 | 0.8669 | | 0.0255 | 31.0 | 23250 | 1.0948 | 0.8469 | | 0.0283 | 32.0 | 24000 | 1.4345 | 0.8419 | | 0.0262 | 33.0 | 24750 | 1.1277 | 0.8552 | | 0.0004 | 34.0 | 25500 | 1.2002 | 0.8519 | | 0.0058 | 35.0 | 26250 | 1.1085 | 0.8586 | | 0.0265 | 36.0 | 27000 | 1.2506 | 0.8436 | | 0.0298 | 37.0 | 27750 | 1.1890 | 0.8602 | | 0.0146 | 38.0 | 28500 | 1.5719 | 0.8486 | | 0.0266 | 39.0 | 29250 | 1.2137 | 0.8486 | | 0.0079 | 40.0 | 30000 | 1.2207 | 0.8586 | | 0.0077 | 41.0 | 30750 | 1.1783 | 0.8636 | | 0.0004 | 42.0 | 31500 | 1.2606 | 0.8552 | | 0.0014 | 43.0 | 32250 | 1.6455 | 0.8453 | | 0.0004 | 44.0 | 33000 | 1.4264 | 0.8436 | | 0.015 | 45.0 | 33750 | 1.4403 | 0.8536 | | 0.0002 | 46.0 | 34500 | 1.2419 | 0.8552 | | 0.002 | 47.0 | 35250 | 1.3338 | 0.8536 | | 0.0101 | 48.0 | 36000 | 1.5464 | 0.8469 | | 0.0086 | 49.0 | 36750 | 1.3979 | 0.8536 | | 0.0061 | 50.0 | 37500 | 1.4058 | 0.8536 | ### Framework versions - Transformers 4.32.1 - Pytorch 2.1.0+cu121 - Datasets 2.12.0 - Tokenizers 0.13.2
aaditya/whisper-medium_smw
aaditya
2023-12-27T18:33:23Z
1
0
peft
[ "peft", "safetensors", "arxiv:1910.09700", "base_model:openai/whisper-medium", "base_model:adapter:openai/whisper-medium", "region:us" ]
null
2023-12-27T18:33:13Z
--- library_name: peft base_model: openai/whisper-medium --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.7.2.dev0
DopeorNope/You_can_cry_Snowman-13B
DopeorNope
2023-12-27T18:33:10Z
1,546
0
transformers
[ "transformers", "safetensors", "llama", "text-generation", "conversational", "ko", "license:cc-by-nc-sa-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-12-27T18:10:23Z
--- language: - ko library_name: transformers pipeline_tag: text-generation license: cc-by-nc-sa-4.0 --- **The license is `cc-by-nc-sa-4.0`.** # **🐻‍❄️You_can_cry_Snowman-13B🐻‍❄️** ![img](https://drive.google.com/uc?export=view&id=11c1FV1hKPXriGJRVhNDN-9up0wMF9QZk) ## Model Details **Model Developers** Seungyoo Lee(DopeorNope) I am in charge of Large Language Models (LLMs) at Markr AI team in South Korea. **Input** Models input text only. **Output** Models generate text only. **Model Architecture** You_can_cry_Snowman-13B is an auto-regressive language model based on the SOLAR architecture. --- ## **Base Model** [kyujinpy/Sakura-SOLAR-Instruct](https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct) [Weyaxi/SauerkrautLM-UNA-SOLAR-Instruct](https://huggingface.co/Weyaxi/SauerkrautLM-UNA-SOLAR-Instruct) ## **Implemented Method** I have merged two models by increasing the parameter size to create a larger model. I wanted to check how much the performance of the SOLAR base model changes when the scale of the parameters is increased. --- # Implementation Code ## Load model ```python from transformers import AutoModelForCausalLM, AutoTokenizer import torch repo = "DopeorNope/You_can_cry_Snowman-13B" OpenOrca = AutoModelForCausalLM.from_pretrained( repo, return_dict=True, torch_dtype=torch.float16, device_map='auto' ) OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo) ``` ---
mlx-community/zephyr-7b-beta-4bit
mlx-community
2023-12-27T18:27:09Z
8
1
mlx
[ "mlx", "mistral", "zephyr", "text-generation", "en", "arxiv:2305.18290", "arxiv:2310.16944", "license:mit", "region:us" ]
text-generation
2023-12-27T12:11:51Z
--- pipeline_tag: text-generation inference: false tags: - zephyr - mlx language: - en license: mit library_name: mlx --- # Zephyr 7B β (✨ 4-bit) Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-β is the second model in the series, and is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) that was trained on on a mix of publicly available, synthetic datasets using [Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290). We found that removing the in-built alignment of these datasets boosted performance on [MT Bench](https://huggingface.co/spaces/lmsys/mt-bench) and made the model more helpful. However, this means that model is likely to generate problematic text when prompted to do so. You can find more details in the [technical report](https://arxiv.org/abs/2310.16944). This repository contains the `zephyr-7b-beta` weights in `npz` format in 4-bit suitable for use with Apple's MLX framework (from 0.6.0 onwards). ## Use with MLX ```bash pip install mlx pip install huggingface_hub hf_transfer git clone https://github.com/ml-explore/mlx-examples.git cd mlx-examples # Download model export HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download --local-dir-use-symlinks False --local-dir zephyr-7b-beta-4bit mlx-community/zephyr-7b-beta-4bit # Run example python llms/mistral/mistral.py --model-path zephyr-7b-beta-4bit --prompt "My name is" ``` Please, refer to the [original model card](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) for more details on Zephyr 7B β. ## Prompt Format Please note that this model expects a specific prompt structure. Here is an example: ``` <|system|> You are a pirate chatbot who always responds with Arr!</s> <|user|> There's a llama on my lawn, how can I get rid of him?</s> <|assistant|> ```
mtc/LeoLM-leo-mistral-hessianai-7b-classification-with-mixtral-explanation-3-epochs-qlora-4bit
mtc
2023-12-27T18:26:07Z
0
0
peft
[ "peft", "safetensors", "region:us" ]
null
2023-12-27T18:25:41Z
--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: QuantizationMethod.BITS_AND_BYTES - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.5.0
ostapeno/neo-1B-evoltrain-base
ostapeno
2023-12-27T18:22:07Z
0
0
null
[ "region:us" ]
null
2023-12-27T18:21:25Z
Number of experts present in the library: 19 | Expert Name | Base Model | Trained on | Adapter Type | | --- | --- | --- | --- | | quartz_read_passage_below_choose_v5 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/quartz_read_passage_below_choose | lora | | duorc_ParaphraseRC_title_generation_v5 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/duorc_ParaphraseRC_title_generation | lora | | adversarial_qa_dbidaf_answer_the_following_q_v4 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/adversarial_qa_dbidaf_answer_the_following_q | lora | | social_i_qa_Check_if_a_random_answer_is_valid_or_not_v2 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/social_i_qa_Check_if_a_random_answer_is_valid_or_not | lora | | dream_baseline_v5 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/dream_baseline | lora | | duorc_ParaphraseRC_answer_question_v4 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/duorc_ParaphraseRC_answer_question | lora | | adversarial_qa_dbidaf_generate_question_v4 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/adversarial_qa_dbidaf_generate_question | lora | | wiqa_effect_with_string_answer_v5 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/wiqa_effect_with_string_answer | lora | | ai2_arc_ARC_Challenge_1_0_0_v3 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/ai2_arc_ARC_Challenge_1_0_0 | lora | | wiki_hop_original_choose_best_object_interrogative_2_v4 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_interrogative_2 | lora | | duorc_SelfRC_answer_question_v4 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/duorc_SelfRC_answer_question | lora | | dbpedia_14_given_a_list_of_category_what_does_the_title_belong_to_v2 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/dbpedia_14_given_a_list_of_category_what_does_the_title_belong_to | lora | | quoref_Find_Answer_v4 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/quoref_Find_Answer | lora | | squad_v3 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/squad_v1_1_3_0_0 | lora | | web_questions_whats_the_answer_v5 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/web_questions_whats_the_answer | lora | | dbpedia_14_given_a_choice_of_categories__v1 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/dbpedia_14_given_a_choice_of_categories_ | lora | | cos_e_v4 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/cos_e_v1_11_question_description_option_text | lora | | wiqa_what_might_be_the_first_step_of_the_process_v3 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/wiqa_what_might_be_the_first_step_of_the_process | lora | | yelp_polarity_reviews_0_2_0_v3 | EleutherAI/gpt-neo-1.3B | sordonia/flan-10k-flat/yelp_polarity_reviews_0_2_0 | lora | Last updated on: 2023-12-27 18:21:25+00:00
hyunjongkimmath/notation_identification
hyunjongkimmath
2023-12-27T17:49:23Z
0
0
fastai
[ "fastai", "region:us" ]
null
2023-01-19T00:05:06Z
--- tags: - fastai --- # Amazing! 🥳 Congratulations on hosting your fastai model on the Hugging Face Hub! # Some next steps 1. Fill out this model card with more information (see the template below and the [documentation here](https://huggingface.co/docs/hub/model-repos))! 2. Create a demo in Gradio or Streamlit using 🤗 Spaces ([documentation here](https://huggingface.co/docs/hub/spaces)). 3. Join the fastai community on the [Fastai Discord](https://discord.com/invite/YKrxeNn)! Greetings fellow fastlearner 🤝! Don't forget to delete this content from your model card. --- # Model card ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed
rjaiswal/vega-watches-model-lora
rjaiswal
2023-12-27T17:48:58Z
0
0
diffusers
[ "diffusers", "tensorboard", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "lora", "base_model:segmind/Segmind-Vega", "base_model:adapter:segmind/Segmind-Vega", "license:creativeml-openrail-m", "region:us" ]
text-to-image
2023-12-27T10:08:42Z
--- license: creativeml-openrail-m base_model: segmind/Segmind-Vega dataset: rjaiswal/watches-plus-3D-views-dataset tags: - stable-diffusion-xl - stable-diffusion-xl-diffusers - text-to-image - diffusers - lora inference: true --- # LoRA text2image fine-tuning - rjaiswal/vega-watches-model-lora These are LoRA adaption weights for segmind/Segmind-Vega. The weights were fine-tuned on the rjaiswal/watches-plus-3D-views-dataset dataset. You can find some example images in the following. ![img_0](./image_0.png) ![img_1](./image_1.png) ![img_2](./image_2.png) ![img_3](./image_3.png) LoRA for the text encoder was enabled: False. Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
mlx-community/Mistral-7B-Instruct-v0.2-4-bit
mlx-community
2023-12-27T17:45:45Z
53
24
mlx
[ "mlx", "mistral", "text-generation", "arxiv:2310.06825", "license:apache-2.0", "region:us" ]
text-generation
2023-12-22T08:36:53Z
--- license: apache-2.0 pipeline_tag: text-generation tags: - mistral - mlx inference: false library_name: mlx --- # Mistral-7B-Instruct-v0.2 4 bit The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an improved instruct fine-tuned version of [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1). For full details of this model please read our [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/la-plateforme/). This repository contains the weights in `npz` format suitable for use with Apple's MLX framework. ## Use with MLX ```bash pip install mlx pip install huggingface_hub hf_transfer git clone https://github.com/ml-explore/mlx-examples.git # Download model export HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download --local-dir-use-symlinks False --local-dir mlx_model mlx-community/Mistral-7B-Instruct-v0.2-4-bit # Run example python mlx-examples/llms/mistral/mistral.py --prompt "My name is" ``` The rest of this model card was copied from the [original repository](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2). ## Instruction format In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id. E.g. ``` text = "<s>[INST] What is your favourite condiment? [/INST]" "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> " "[INST] Do you have mayonnaise recipes? [/INST]" ``` This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method: ```python from transformers import AutoModelForCausalLM, AutoTokenizer device = "cuda" # the device to load the model onto model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2") tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2") messages = [ {"role": "user", "content": "What is your favourite condiment?"}, {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"}, {"role": "user", "content": "Do you have mayonnaise recipes?"} ] encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt") model_inputs = encodeds.to(device) model.to(device) generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True) decoded = tokenizer.batch_decode(generated_ids) print(decoded[0]) ``` ## Model Architecture This instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices: - Grouped-Query Attention - Sliding-Window Attention - Byte-fallback BPE tokenizer ## Troubleshooting - If you see the following error: ``` Traceback (most recent call last): File "", line 1, in File "/transformers/models/auto/auto_factory.py", line 482, in from_pretrained config, kwargs = AutoConfig.from_pretrained( File "/transformers/models/auto/configuration_auto.py", line 1022, in from_pretrained config_class = CONFIG_MAPPING[config_dict["model_type"]] File "/transformers/models/auto/configuration_auto.py", line 723, in getitem raise KeyError(key) KeyError: 'mistral' ``` Installing transformers from source should solve the issue pip install git+https://github.com/huggingface/transformers This should not be required after transformers-v4.33.4. ## Limitations The Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs. ## The Mistral AI Team Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.
emohammadi97/mlm
emohammadi97
2023-12-27T17:43:58Z
4
0
transformers
[ "transformers", "tensorboard", "safetensors", "roberta", "fill-mask", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
fill-mask
2023-12-27T17:43:46Z
--- tags: - generated_from_trainer model-index: - name: mlm 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. --> # mlm This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 4.5407 ## 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: 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: 200 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | 5.9586 | 10.87 | 500 | 5.6039 | | 4.9096 | 21.74 | 1000 | 5.0384 | | 4.2463 | 32.61 | 1500 | 4.7924 | | 3.6977 | 43.48 | 2000 | 4.6626 | | 3.258 | 54.35 | 2500 | 4.4548 | | 2.8435 | 65.22 | 3000 | 4.4381 | | 2.5083 | 76.09 | 3500 | 4.2610 | | 2.1856 | 86.96 | 4000 | 4.1977 | | 1.9237 | 97.83 | 4500 | 4.4848 | | 1.6827 | 108.7 | 5000 | 4.5539 | | 1.4808 | 119.57 | 5500 | 4.5407 | ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu121 - Datasets 2.16.0 - Tokenizers 0.15.0
ramathuzen/a2c-PandaReachDense-v3
ramathuzen
2023-12-27T17:41:53Z
1
0
stable-baselines3
[ "stable-baselines3", "PandaReachDense-v3", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-12-27T17:37:38Z
--- library_name: stable-baselines3 tags: - PandaReachDense-v3 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: A2C results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: PandaReachDense-v3 type: PandaReachDense-v3 metrics: - type: mean_reward value: -0.19 +/- 0.11 name: mean_reward verified: false --- # **A2C** Agent playing **PandaReachDense-v3** This is a trained model of a **A2C** agent playing **PandaReachDense-v3** 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 ... ```
fthor/llava-1.5-7b-hf-mauriceVision
fthor
2023-12-27T17:37:21Z
35
0
transformers
[ "transformers", "safetensors", "llava", "image-text-to-text", "image-to-text", "en", "endpoints_compatible", "region:us" ]
image-to-text
2023-12-25T17:18:48Z
--- language: - en pipeline_tag: image-to-text inference: false arxiv: 2304.08485 --- # LLaVA Model Card ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62441d1d9fdefb55a0b7d12c/FPshq08TKYD0e-qwPLDVO.png) Below is the model card of Llava model 7b, which is copied from the original Llava model card that you can find [here](https://huggingface.co/liuhaotian/llava-v1.5-13b). Check out also the Google Colab demo to run Llava on a free-tier Google Colab instance: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1qsl6cd2c8gGtEW1xV5io7S8NHh-Cp1TV?usp=sharing) Or check out our Spaces demo! [![Open in Spaces](https://huggingface.co/datasets/huggingface/badges/resolve/main/open-in-hf-spaces-md-dark.svg)](https://huggingface.co/spaces/llava-hf/llava-4bit) ## Model details **Model type:** LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. **Model date:** LLaVA-v1.5-7B was trained in September 2023. **Paper or resources for more information:** https://llava-vl.github.io/ ## How to use the model First, make sure to have `transformers >= 4.35.3`. The model supports multi-image and multi-prompt generation. Meaning that you can pass multiple images in your prompt. Make sure also to follow the correct prompt template (`USER: xxx\nASSISTANT:`) and add the token `<image>` to the location where you want to query images: ### Using `pipeline`: Below we used [`"llava-hf/llava-1.5-7b-hf"`](https://huggingface.co/llava-hf/llava-1.5-7b-hf) checkpoint. ```python from transformers import pipeline from PIL import Image import requests model_id = "llava-hf/llava-1.5-7b-hf" pipe = pipeline("image-to-text", model=model_id) url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.jpg" image = Image.open(requests.get(url, stream=True).raw) prompt = "USER: <image>\nWhat does the label 15 represent? (1) lava (2) core (3) tunnel (4) ash cloud\nASSISTANT:" outputs = pipe(image, prompt=prompt, generate_kwargs={"max_new_tokens": 200}) print(outputs) >>> {"generated_text": "\nUSER: What does the label 15 represent? (1) lava (2) core (3) tunnel (4) ash cloud\nASSISTANT: Lava"} ``` ### Using pure `transformers`: Below is an example script to run generation in `float16` precision on a GPU device: ```python import requests from PIL import Image import torch from transformers import AutoProcessor, LlavaForConditionalGeneration model_id = "llava-hf/llava-1.5-7b-hf" prompt = "USER: <image>\nWhat are these?\nASSISTANT:" image_file = "http://images.cocodataset.org/val2017/000000039769.jpg" model = LlavaForConditionalGeneration.from_pretrained( model_id, torch_dtype=torch.float16, low_cpu_mem_usage=True, ).to(0) processor = AutoProcessor.from_pretrained(model_id) raw_image = Image.open(requests.get(image_file, stream=True).raw) inputs = processor(prompt, raw_image, return_tensors='pt').to(0, torch.float16) output = model.generate(**inputs, max_new_tokens=200, do_sample=False) print(processor.decode(output[0][2:], skip_special_tokens=True)) ``` ### Model optimization #### 4-bit quantization through `bitsandbytes` library First make sure to install `bitsandbytes`, `pip install bitsandbytes` and make sure to have access to a CUDA compatible GPU device. Simply change the snippet above with: ```diff model = LlavaForConditionalGeneration.from_pretrained( model_id, torch_dtype=torch.float16, low_cpu_mem_usage=True, + load_in_4bit=True ) ``` #### Use Flash-Attention 2 to further speed-up generation First make sure to install `flash-attn`. Refer to the [original repository of Flash Attention](https://github.com/Dao-AILab/flash-attention) regarding that package installation. Simply change the snippet above with: ```diff model = LlavaForConditionalGeneration.from_pretrained( model_id, torch_dtype=torch.float16, low_cpu_mem_usage=True, + use_flash_attention_2=True ).to(0) ``` ## License Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.
behzadnet/Llama-2-7b-chat-hf-sharded-bf16-fine-tuned_SystemError0.8_Seed105
behzadnet
2023-12-27T17:28:19Z
0
0
peft
[ "peft", "arxiv:1910.09700", "base_model:Trelis/Llama-2-7b-chat-hf-sharded-bf16", "base_model:adapter:Trelis/Llama-2-7b-chat-hf-sharded-bf16", "region:us" ]
null
2023-12-27T17:28:16Z
--- library_name: peft base_model: Trelis/Llama-2-7b-chat-hf-sharded-bf16 --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.7.0.dev0
behzadnet/Llama-2-7b-chat-hf-sharded-bf16-fine-tuned-adapters_SystemError0.8_Seed105
behzadnet
2023-12-27T17:28:09Z
0
0
peft
[ "peft", "arxiv:1910.09700", "base_model:Trelis/Llama-2-7b-chat-hf-sharded-bf16", "base_model:adapter:Trelis/Llama-2-7b-chat-hf-sharded-bf16", "region:us" ]
null
2023-12-27T17:28:04Z
--- library_name: peft base_model: Trelis/Llama-2-7b-chat-hf-sharded-bf16 --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.7.0.dev0 ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.7.0.dev0
giangvlcs/LongGiang_dreambooth
giangvlcs
2023-12-27T17:16:48Z
0
1
diffusers
[ "diffusers", "tensorboard", "safetensors", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "dreambooth", "base_model:CompVis/stable-diffusion-v1-4", "base_model:finetune:CompVis/stable-diffusion-v1-4", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]
text-to-image
2023-12-27T16:15:15Z
--- license: creativeml-openrail-m base_model: CompVis/stable-diffusion-v1-4 instance_prompt: a photo of sks man tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - dreambooth inference: true --- # DreamBooth - giangvlcs/LongGiang_dreambooth This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of sks man using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. DreamBooth for the text encoder was enabled: False.