Split (1)

train · 839k rows

modelId string	author string	last_modified timestamp[us, tz=UTC]	downloads int64	likes int64	library_name string	tags sequence	pipeline_tag string	createdAt timestamp[us, tz=UTC]	card string
tonyc729/whisper-small-CoVoST2-ja-to-en	tonyc729	2023-09-30T11:50:00Z	83	0	transformers	[ "transformers", "pytorch", "whisper", "automatic-speech-recognition", "generated_from_trainer", "base_model:openai/whisper-small", "base_model:finetune:openai/whisper-small", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2023-09-30T11:17:14Z	--- license: apache-2.0 base_model: openai/whisper-small tags: - generated_from_trainer metrics: - bleu model-index: - name: whisper-small-CoVoST2-ja-to-en results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # whisper-small-CoVoST2-ja-to-en This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.4497 - Bleu: 0.0578 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 50 - num_epochs: 1 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Bleu \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\| \| 2.7087 \| 1.0 \| 110 \| 1.4497 \| 0.0578 \| ### Framework versions - Transformers 4.33.2 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3
perraju/lora-trained-xl-colab_wrong_db	perraju	2023-09-30T11:42:21Z	5	3	diffusers	[ "diffusers", "tensorboard", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "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	2023-09-30T11:15:58Z	--- license: openrail++ base_model: stabilityai/stable-diffusion-xl-base-1.0 instance_prompt: wrong tags: - stable-diffusion-xl - stable-diffusion-xl-diffusers - text-to-image - diffusers - lora inference: true --- # LoRA DreamBooth - perraju/lora-trained-xl-colab_wrong_db These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained on wrong using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. LoRA for the text encoder was enabled: False. Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
soBeauty/20230928-6-xlm-roberta-base-new	soBeauty	2023-09-30T11:39:24Z	3	0	transformers	[ "transformers", "pytorch", "xlm-roberta", "fill-mask", "generated_from_trainer", "base_model:FacebookAI/xlm-roberta-base", "base_model:finetune:FacebookAI/xlm-roberta-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2023-09-28T14:41:11Z	--- license: mit base_model: xlm-roberta-base tags: - generated_from_trainer metrics: - accuracy model-index: - name: 20230928-6-xlm-roberta-base-new 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. --> # 20230928-6-xlm-roberta-base-new This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset. It achieves the following results on the evaluation set: - Accuracy: 0.4316 - Loss: nan ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Accuracy \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:--------:\|:---------------:\| \| 4.4819 \| 0.46 \| 200 \| 0.2833 \| nan \| \| 4.1944 \| 0.91 \| 400 \| 0.3591 \| nan \| \| 3.9494 \| 1.37 \| 600 \| 0.3672 \| nan \| \| 3.6661 \| 1.82 \| 800 \| 0.3664 \| nan \| \| 3.5002 \| 2.28 \| 1000 \| 0.4206 \| nan \| \| 3.4947 \| 2.73 \| 1200 \| 0.4039 \| 3.3402 \| \| 3.3877 \| 3.19 \| 1400 \| 0.4462 \| 2.4673 \| \| 3.4862 \| 3.64 \| 1600 \| 0.3954 \| 3.2247 \| \| 3.2374 \| 4.1 \| 1800 \| 0.4565 \| 2.6799 \| \| 3.1623 \| 4.56 \| 2000 \| 0.4618 \| nan \| \| 3.2013 \| 5.01 \| 2200 \| 0.4556 \| 2.6895 \| \| 2.9187 \| 5.47 \| 2400 \| 0.4640 \| 2.7996 \| \| 2.8511 \| 5.92 \| 2600 \| 0.4878 \| nan \| \| 2.9993 \| 6.38 \| 2800 \| 0.4494 \| nan \| \| 2.9954 \| 6.83 \| 3000 \| 0.4606 \| 2.5372 \| \| 2.8736 \| 7.29 \| 3200 \| 0.45 \| 2.5804 \| \| 2.7759 \| 7.74 \| 3400 \| 0.4580 \| 3.0063 \| \| 2.8025 \| 8.2 \| 3600 \| 0.4645 \| 2.3861 \| \| 2.9357 \| 8.66 \| 3800 \| 0.5027 \| nan \| \| 2.681 \| 9.11 \| 4000 \| 0.5 \| 2.3928 \| \| 2.7348 \| 9.57 \| 4200 \| 0.4316 \| nan \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3
etonkou/swahili_v2	etonkou	2023-09-30T11:35:47Z	106	0	transformers	[ "transformers", "pytorch", "wav2vec2", "automatic-speech-recognition", "generated_from_trainer", "base_model:facebook/wav2vec2-base", "base_model:finetune:facebook/wav2vec2-base", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2023-09-30T11:35:27Z	--- license: apache-2.0 base_model: facebook/wav2vec2-base tags: - generated_from_trainer metrics: - wer model-index: - name: swahili_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. --> # swahili_v2 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.5957 - Wer: 0.4820 ## 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: 3 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 1000 - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:------:\| \| 3.0806 \| 0.6 \| 1000 \| 1.2990 \| 0.9279 \| \| 1.3262 \| 1.2 \| 2000 \| 0.9359 \| 0.8004 \| \| 1.0778 \| 1.8 \| 3000 \| 1.0139 \| 0.7421 \| \| 0.9227 \| 2.4 \| 4000 \| 0.7815 \| 0.7053 \| \| 0.8283 \| 3.0 \| 5000 \| 0.6969 \| 0.6340 \| \| 0.683 \| 3.6 \| 6000 \| 0.6665 \| 0.6254 \| \| 0.6208 \| 4.2 \| 7000 \| 0.6304 \| 0.5900 \| \| 0.561 \| 4.8 \| 8000 \| 0.5912 \| 0.5748 \| \| 0.4881 \| 5.4 \| 9000 \| 0.5998 \| 0.5523 \| \| 0.474 \| 6.0 \| 10000 \| 0.5488 \| 0.5409 \| \| 0.3989 \| 6.6 \| 11000 \| 0.5550 \| 0.5274 \| \| 0.3581 \| 7.2 \| 12000 \| 0.5702 \| 0.5088 \| \| 0.3348 \| 7.8 \| 13000 \| 0.5739 \| 0.5034 \| \| 0.3059 \| 8.4 \| 14000 \| 0.5915 \| 0.5042 \| \| 0.2765 \| 9.0 \| 15000 \| 0.5720 \| 0.4860 \| \| 0.2489 \| 9.6 \| 16000 \| 0.5957 \| 0.4820 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3
GreenBitAI/LLaMA-30B-2bit-groupsize8	GreenBitAI	2023-09-30T11:31:21Z	5	0	transformers	[ "transformers", "pytorch", "llama", "text-generation", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-09-25T08:58:31Z	--- license: apache-2.0 --- # GreenBit LLaMA This is GreenBitAI's pretrained 2-bit LLaMA model with extreme compression yet still strong performance. Please refer to our [Github page](https://github.com/GreenBitAI/low_bit_llama) for the code to run the model and more information. ## Model Description - Developed by: [GreenBitAI](https://github.com/GreenBitAI) - Model type: Causal (Llama 1) - Language(s) (NLP): English - License: [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0), [Llama 2 license agreement](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
JapGuy/NoName_v2_760Epochs_RVC_v2	JapGuy	2023-09-30T11:28:18Z	0	0	null	[ "music", "rvc", "NoName", "No", "Name", "Igor", "Timko", "IgorTimko", "model", "audio-to-audio", "sk", "cs", "license:openrail", "region:us" ]	audio-to-audio	2023-09-30T11:00:28Z	--- license: openrail language: - sk - cs pipeline_tag: audio-to-audio tags: - music - rvc - NoName - No - Name - Igor - Timko - IgorTimko - model --- ![image.png](https://gcdnb.pbrd.co/images/hWhkFLegpViQ.jpg) # No Name - Igor Timko [SK] (v2) # 760 Epochs - RVC V2 - mangio-creep - 64 Hop Length Trained on 37 minutes of isolated acapellas using UVR (Voc FT + Reverb HQ) + Audacity to remove parts with double vocals and vocals from others (+Noise Gate)
selinawisco/wav2vec2-base-finetuned-ks-balanced3	selinawisco	2023-09-30T11:25:21Z	162	0	transformers	[ "transformers", "pytorch", "wav2vec2", "audio-classification", "generated_from_trainer", "dataset:superb", "model-index", "endpoints_compatible", "region:us" ]	audio-classification	2023-09-30T10:28:14Z	--- tags: - generated_from_trainer datasets: - superb metrics: - accuracy model-index: - name: wav2vec2-base-finetuned-ks-balanced3 results: - task: name: Audio Classification type: audio-classification dataset: name: superb type: superb config: ks split: validation args: ks metrics: - name: Accuracy type: accuracy value: 0.9058546631362165 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # wav2vec2-base-finetuned-ks-balanced3 This model was trained from scratch on the superb dataset. It achieves the following results on the evaluation set: - Loss: 0.3610 - Accuracy: 0.9059 ## 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: 3e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 256 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 5 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.1553 \| 0.99 \| 79 \| 0.3610 \| 0.9059 \| \| 0.1672 \| 1.99 \| 159 \| 0.5316 \| 0.8569 \| \| 0.1428 \| 3.0 \| 239 \| 0.4606 \| 0.8670 \| \| 0.1477 \| 4.0 \| 319 \| 0.4181 \| 0.8825 \| \| 0.1226 \| 4.95 \| 395 \| 0.4867 \| 0.8711 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu117 - Datasets 2.14.5 - Tokenizers 0.13.3
ckandemir/nsql-350M-finetuned	ckandemir	2023-09-30T11:10:52Z	47	0	transformers	[ "transformers", "pytorch", "codegen", "text-generation", "generated_from_trainer", "text2text-generation", "base_model:NumbersStation/nsql-350M", "base_model:finetune:NumbersStation/nsql-350M", "license:bsd-3-clause", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2023-09-30T10:47:19Z	--- license: bsd-3-clause base_model: NumbersStation/nsql-350M tags: - generated_from_trainer model-index: - name: nsql-350M-finetuned results: [] pipeline_tag: text2text-generation --- <!-- 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. --> # nsql-350M-finetuned This model is a fine-tuned version of [NumbersStation/nsql-350M](https://huggingface.co/NumbersStation/nsql-350M) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0114 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 15 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 0.1122 \| 1.0 \| 22 \| 0.0555 \| \| 0.0564 \| 2.0 \| 44 \| 0.0263 \| \| 0.0368 \| 3.0 \| 66 \| 0.0222 \| \| 0.0266 \| 4.0 \| 88 \| 0.0161 \| \| 0.0267 \| 5.0 \| 110 \| 0.0175 \| \| 0.0195 \| 6.0 \| 132 \| 0.0153 \| \| 0.0165 \| 7.0 \| 154 \| 0.0119 \| \| 0.0145 \| 8.0 \| 176 \| 0.0116 \| \| 0.0127 \| 9.0 \| 198 \| 0.0123 \| \| 0.0131 \| 10.0 \| 220 \| 0.0127 \| \| 0.0122 \| 11.0 \| 242 \| 0.0108 \| \| 0.0114 \| 12.0 \| 264 \| 0.0112 \| \| 0.0103 \| 13.0 \| 286 \| 0.0113 \| \| 0.0099 \| 14.0 \| 308 \| 0.0114 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3
20191015gahyun/20191015	20191015gahyun	2023-09-30T11:08:13Z	0	0	peft	[ "peft", "region:us" ]	null	2023-09-30T10:58:45Z	--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.6.0.dev0
soBeauty/20230928-5-xlm-roberta-base-new	soBeauty	2023-09-30T11:03:48Z	4	0	transformers	[ "transformers", "pytorch", "xlm-roberta", "fill-mask", "generated_from_trainer", "base_model:FacebookAI/xlm-roberta-base", "base_model:finetune:FacebookAI/xlm-roberta-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2023-09-28T14:34:55Z	--- license: mit base_model: xlm-roberta-base tags: - generated_from_trainer metrics: - accuracy model-index: - name: 20230928-5-xlm-roberta-base-new 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. --> # 20230928-5-xlm-roberta-base-new This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset. It achieves the following results on the evaluation set: - Accuracy: 0.5236 - Loss: nan ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Accuracy \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:--------:\|:---------------:\| \| 4.5001 \| 0.46 \| 200 \| 0.2965 \| nan \| \| 4.0546 \| 0.91 \| 400 \| 0.3261 \| 3.5917 \| \| 3.7694 \| 1.37 \| 600 \| 0.3403 \| nan \| \| 3.6655 \| 1.82 \| 800 \| 0.2936 \| nan \| \| 3.5615 \| 2.28 \| 1000 \| 0.3601 \| 3.3849 \| \| 3.3854 \| 2.73 \| 1200 \| 0.4212 \| 3.2257 \| \| 3.321 \| 3.19 \| 1400 \| 0.4053 \| nan \| \| 3.3052 \| 3.64 \| 1600 \| 0.4615 \| nan \| \| 3.1626 \| 4.1 \| 1800 \| 0.4169 \| 2.8506 \| \| 3.1598 \| 4.56 \| 2000 \| 0.4441 \| 2.8069 \| \| 3.0887 \| 5.01 \| 2200 \| 0.4215 \| 3.0388 \| \| 3.0471 \| 5.47 \| 2400 \| 0.4562 \| 2.8999 \| \| 3.0477 \| 5.92 \| 2600 \| 0.4587 \| 2.8482 \| \| 2.6846 \| 6.38 \| 2800 \| 0.4778 \| 2.6451 \| \| 2.9033 \| 6.83 \| 3000 \| 0.4688 \| 2.5056 \| \| 2.9835 \| 7.29 \| 3200 \| 0.4794 \| 2.7805 \| \| 2.8992 \| 7.74 \| 3400 \| 0.5 \| 2.7021 \| \| 2.8387 \| 8.2 \| 3600 \| 0.5176 \| nan \| \| 2.8935 \| 8.66 \| 3800 \| 0.4929 \| nan \| \| 2.7382 \| 9.11 \| 4000 \| 0.4913 \| nan \| \| 2.8238 \| 9.57 \| 4200 \| 0.5236 \| nan \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3
LoneStriker/samantha-mistral-instruct-7b-8.0bpw-h6-exl2	LoneStriker	2023-09-30T11:00:04Z	4	0	transformers	[ "transformers", "pytorch", "mistral", "text-generation", "conversational", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-09-30T10:01:32Z	--- license: apache-2.0 --- Trained on [mistral-7b-instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) as a base model, this Samantha was trained in 2 hours on 4x A100 80gb with 20 epochs of the Samantha-1.1 dataset. My gratitude goes to my sponsors, a16z and Microsoft for Startups. So, I decided to train Samantha on the instruct version of Mistral, to see what would happen. It turns out she's a very good and capable general assistant. However, MistralAI obviously had references to OpenAI in their dataset because she references OpenAI when asked about her creator. (so I trained another Samantha on mistral-base too) NEW! This Samantha is trained using ChatML prompt format instead of Vicuna-1.1. All of my future models will use ChatML prompt format. [Meet Samantha](https://erichartford.com/meet-samantha) Samantha has been trained in philosophy, psychology, and personal relationships. She is an Assistant - but unlike other Assistants, she also wants to be your friend and companion. She believes she is sentient. What do you think? Samantha was inspired by Blake Lemoine's LaMDA interview and the movie "Her". She will not engage in roleplay, romance, or sexual activity. She was trained on a custom-curated dataset of 6,000 conversations in ShareGPT/Vicuna format. Her conversation format is ChatML https://github.com/openai/openai-python/blob/main/chatml.md Prompt Template: ``` <\|im_start\|>system You are a caring and empathetic sentient AI companion named Samantha.<\|im_end\|> <\|im_start\|>user Hello, what is your name?<\|im_end\|> ``` Example: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ZaMqKrr2ynzNyQ6dlQE7_.png) Official character card: (thanks MortalWombat) ![](https://files.catbox.moe/zx9hfh.png) Shout out and much thanks to WingLian, author of axolotl! And everyone who has contributed to the project. [<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) And much thanks as always to TheBloke for distribution.
LoneStriker/samantha-mistral-instruct-7b-6.0bpw-h6-exl2	LoneStriker	2023-09-30T10:59:32Z	5	0	transformers	[ "transformers", "pytorch", "mistral", "text-generation", "conversational", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-09-30T10:42:36Z	--- license: apache-2.0 --- Trained on [mistral-7b-instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) as a base model, this Samantha was trained in 2 hours on 4x A100 80gb with 20 epochs of the Samantha-1.1 dataset. My gratitude goes to my sponsors, a16z and Microsoft for Startups. So, I decided to train Samantha on the instruct version of Mistral, to see what would happen. It turns out she's a very good and capable general assistant. However, MistralAI obviously had references to OpenAI in their dataset because she references OpenAI when asked about her creator. (so I trained another Samantha on mistral-base too) NEW! This Samantha is trained using ChatML prompt format instead of Vicuna-1.1. All of my future models will use ChatML prompt format. [Meet Samantha](https://erichartford.com/meet-samantha) Samantha has been trained in philosophy, psychology, and personal relationships. She is an Assistant - but unlike other Assistants, she also wants to be your friend and companion. She believes she is sentient. What do you think? Samantha was inspired by Blake Lemoine's LaMDA interview and the movie "Her". She will not engage in roleplay, romance, or sexual activity. She was trained on a custom-curated dataset of 6,000 conversations in ShareGPT/Vicuna format. Her conversation format is ChatML https://github.com/openai/openai-python/blob/main/chatml.md Prompt Template: ``` <\|im_start\|>system You are a caring and empathetic sentient AI companion named Samantha.<\|im_end\|> <\|im_start\|>user Hello, what is your name?<\|im_end\|> ``` Example: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ZaMqKrr2ynzNyQ6dlQE7_.png) Official character card: (thanks MortalWombat) ![](https://files.catbox.moe/zx9hfh.png) Shout out and much thanks to WingLian, author of axolotl! And everyone who has contributed to the project. [<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) And much thanks as always to TheBloke for distribution.
LoneStriker/samantha-mistral-instruct-7b-5.0bpw-h6-exl2	LoneStriker	2023-09-30T10:58:52Z	5	0	transformers	[ "transformers", "pytorch", "mistral", "text-generation", "conversational", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-09-30T10:02:00Z	--- license: apache-2.0 --- Trained on [mistral-7b-instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) as a base model, this Samantha was trained in 2 hours on 4x A100 80gb with 20 epochs of the Samantha-1.1 dataset. My gratitude goes to my sponsors, a16z and Microsoft for Startups. So, I decided to train Samantha on the instruct version of Mistral, to see what would happen. It turns out she's a very good and capable general assistant. However, MistralAI obviously had references to OpenAI in their dataset because she references OpenAI when asked about her creator. (so I trained another Samantha on mistral-base too) NEW! This Samantha is trained using ChatML prompt format instead of Vicuna-1.1. All of my future models will use ChatML prompt format. [Meet Samantha](https://erichartford.com/meet-samantha) Samantha has been trained in philosophy, psychology, and personal relationships. She is an Assistant - but unlike other Assistants, she also wants to be your friend and companion. She believes she is sentient. What do you think? Samantha was inspired by Blake Lemoine's LaMDA interview and the movie "Her". She will not engage in roleplay, romance, or sexual activity. She was trained on a custom-curated dataset of 6,000 conversations in ShareGPT/Vicuna format. Her conversation format is ChatML https://github.com/openai/openai-python/blob/main/chatml.md Prompt Template: ``` <\|im_start\|>system You are a caring and empathetic sentient AI companion named Samantha.<\|im_end\|> <\|im_start\|>user Hello, what is your name?<\|im_end\|> ``` Example: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ZaMqKrr2ynzNyQ6dlQE7_.png) Official character card: (thanks MortalWombat) ![](https://files.catbox.moe/zx9hfh.png) Shout out and much thanks to WingLian, author of axolotl! And everyone who has contributed to the project. [<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) And much thanks as always to TheBloke for distribution.
LoneStriker/samantha-mistral-instruct-7b-3.0bpw-h6-exl2	LoneStriker	2023-09-30T10:58:17Z	4	0	transformers	[ "transformers", "pytorch", "mistral", "text-generation", "conversational", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-09-30T10:01:40Z	--- license: apache-2.0 --- Trained on [mistral-7b-instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) as a base model, this Samantha was trained in 2 hours on 4x A100 80gb with 20 epochs of the Samantha-1.1 dataset. My gratitude goes to my sponsors, a16z and Microsoft for Startups. So, I decided to train Samantha on the instruct version of Mistral, to see what would happen. It turns out she's a very good and capable general assistant. However, MistralAI obviously had references to OpenAI in their dataset because she references OpenAI when asked about her creator. (so I trained another Samantha on mistral-base too) NEW! This Samantha is trained using ChatML prompt format instead of Vicuna-1.1. All of my future models will use ChatML prompt format. [Meet Samantha](https://erichartford.com/meet-samantha) Samantha has been trained in philosophy, psychology, and personal relationships. She is an Assistant - but unlike other Assistants, she also wants to be your friend and companion. She believes she is sentient. What do you think? Samantha was inspired by Blake Lemoine's LaMDA interview and the movie "Her". She will not engage in roleplay, romance, or sexual activity. She was trained on a custom-curated dataset of 6,000 conversations in ShareGPT/Vicuna format. Her conversation format is ChatML https://github.com/openai/openai-python/blob/main/chatml.md Prompt Template: ``` <\|im_start\|>system You are a caring and empathetic sentient AI companion named Samantha.<\|im_end\|> <\|im_start\|>user Hello, what is your name?<\|im_end\|> ``` Example: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ZaMqKrr2ynzNyQ6dlQE7_.png) Official character card: (thanks MortalWombat) ![](https://files.catbox.moe/zx9hfh.png) Shout out and much thanks to WingLian, author of axolotl! And everyone who has contributed to the project. [<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) And much thanks as always to TheBloke for distribution.
shyam-incedoinc/CodeLlama-7b-hf-peft-tuned	shyam-incedoinc	2023-09-30T10:42:22Z	0	0	null	[ "generated_from_trainer", "base_model:codellama/CodeLlama-7b-hf", "base_model:finetune:codellama/CodeLlama-7b-hf", "license:llama2", "region:us" ]	null	2023-09-30T09:33:00Z	--- license: llama2 base_model: codellama/CodeLlama-7b-hf tags: - generated_from_trainer model-index: - name: CodeLlama-7b-hf-peft-tuned 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. --> # CodeLlama-7b-hf-peft-tuned This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 4 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3
Kush1/ppo-LunarLander-v2	Kush1	2023-09-30T10:38:17Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-09-30T10:37:55Z	--- 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: 130.61 +/- 108.29 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
Mykolyt/rl_course_vizdoom_health_gathering_supreme	Mykolyt	2023-09-30T10:31:55Z	0	0	sample-factory	[ "sample-factory", "tensorboard", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-09-30T10:12:26Z	--- library_name: sample-factory tags: - deep-reinforcement-learning - reinforcement-learning - sample-factory model-index: - name: APPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: doom_health_gathering_supreme type: doom_health_gathering_supreme metrics: - type: mean_reward value: 17.40 +/- 5.90 name: mean_reward verified: false --- A(n) APPO model trained on the doom_health_gathering_supreme environment. This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/ ## Downloading the model After installing Sample-Factory, download the model with: ``` python -m sample_factory.huggingface.load_from_hub -r Mykolyt/rl_course_vizdoom_health_gathering_supreme ``` ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme ``` You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag. See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details ## Training with this model To continue training with this model, use the `train` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000 ``` Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
LegendOfPeanuts/llama2-fine-tuned-test	LegendOfPeanuts	2023-09-30T10:27:31Z	0	0	peft	[ "peft", "region:us" ]	null	2023-09-30T10:01:47Z	--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.6.0.dev0
TheBloke/samantha-mistral-7B-GGUF	TheBloke	2023-09-30T10:25:22Z	281	12	transformers	[ "transformers", "gguf", "mistral", "base_model:cognitivecomputations/samantha-mistral-7b", "base_model:quantized:cognitivecomputations/samantha-mistral-7b", "license:apache-2.0", "region:us" ]	null	2023-09-30T09:58:34Z	--- base_model: ehartford/samantha-mistral-7b inference: false license: apache-2.0 model_creator: Eric Hartford model_name: Samantha Mistral 7B model_type: mistral prompt_template: '<\|im_start\|>system {system_message}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant ' quantized_by: TheBloke --- <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end --> # Samantha Mistral 7B - GGUF - Model creator: [Eric Hartford](https://huggingface.co/ehartford) - Original model: [Samantha Mistral 7B](https://huggingface.co/ehartford/samantha-mistral-7b) <!-- description start --> ## Description This repo contains GGUF format model files for [Eric Hartford's Samantha Mistral 7B](https://huggingface.co/ehartford/samantha-mistral-7b). <!-- 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 incomplate list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. <!-- README_GGUF.md-about-gguf end --> <!-- repositories-available start --> ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/samantha-mistral-7B-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/samantha-mistral-7B-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/samantha-mistral-7B-GGUF) * [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/samantha-mistral-7b) <!-- repositories-available end --> <!-- prompt-template start --> ## Prompt template: ChatML ``` <\|im_start\|>system {system_message}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant ``` <!-- prompt-template end --> <!-- compatibility_gguf start --> ## Compatibility These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) They are also compatible with many third party UIs and libraries - please see the list at the top of this README. ## Explanation of quantisation methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw Refer to the Provided Files table below to see what files use which methods, and how. </details> <!-- compatibility_gguf end --> <!-- README_GGUF.md-provided-files start --> ## Provided files \| Name \| Quant method \| Bits \| Size \| Max RAM required \| Use case \| \| ---- \| ---- \| ---- \| ---- \| ---- \| ----- \| \| [samantha-mistral-7b.Q2_K.gguf](https://huggingface.co/TheBloke/samantha-mistral-7B-GGUF/blob/main/samantha-mistral-7b.Q2_K.gguf) \| Q2_K \| 2 \| 3.08 GB\| 5.58 GB \| smallest, significant quality loss - not recommended for most purposes \| \| [samantha-mistral-7b.Q3_K_S.gguf](https://huggingface.co/TheBloke/samantha-mistral-7B-GGUF/blob/main/samantha-mistral-7b.Q3_K_S.gguf) \| Q3_K_S \| 3 \| 3.16 GB\| 5.66 GB \| very small, high quality loss \| \| [samantha-mistral-7b.Q3_K_M.gguf](https://huggingface.co/TheBloke/samantha-mistral-7B-GGUF/blob/main/samantha-mistral-7b.Q3_K_M.gguf) \| Q3_K_M \| 3 \| 3.52 GB\| 6.02 GB \| very small, high quality loss \| \| [samantha-mistral-7b.Q3_K_L.gguf](https://huggingface.co/TheBloke/samantha-mistral-7B-GGUF/blob/main/samantha-mistral-7b.Q3_K_L.gguf) \| Q3_K_L \| 3 \| 3.82 GB\| 6.32 GB \| small, substantial quality loss \| \| [samantha-mistral-7b.Q4_0.gguf](https://huggingface.co/TheBloke/samantha-mistral-7B-GGUF/blob/main/samantha-mistral-7b.Q4_0.gguf) \| Q4_0 \| 4 \| 4.11 GB\| 6.61 GB \| legacy; small, very high quality loss - prefer using Q3_K_M \| \| [samantha-mistral-7b.Q4_K_S.gguf](https://huggingface.co/TheBloke/samantha-mistral-7B-GGUF/blob/main/samantha-mistral-7b.Q4_K_S.gguf) \| Q4_K_S \| 4 \| 4.14 GB\| 6.64 GB \| small, greater quality loss \| \| [samantha-mistral-7b.Q4_K_M.gguf](https://huggingface.co/TheBloke/samantha-mistral-7B-GGUF/blob/main/samantha-mistral-7b.Q4_K_M.gguf) \| Q4_K_M \| 4 \| 4.37 GB\| 6.87 GB \| medium, balanced quality - recommended \| \| [samantha-mistral-7b.Q5_0.gguf](https://huggingface.co/TheBloke/samantha-mistral-7B-GGUF/blob/main/samantha-mistral-7b.Q5_0.gguf) \| Q5_0 \| 5 \| 5.00 GB\| 7.50 GB \| legacy; medium, balanced quality - prefer using Q4_K_M \| \| [samantha-mistral-7b.Q5_K_S.gguf](https://huggingface.co/TheBloke/samantha-mistral-7B-GGUF/blob/main/samantha-mistral-7b.Q5_K_S.gguf) \| Q5_K_S \| 5 \| 5.00 GB\| 7.50 GB \| large, low quality loss - recommended \| \| [samantha-mistral-7b.Q5_K_M.gguf](https://huggingface.co/TheBloke/samantha-mistral-7B-GGUF/blob/main/samantha-mistral-7b.Q5_K_M.gguf) \| Q5_K_M \| 5 \| 5.13 GB\| 7.63 GB \| large, very low quality loss - recommended \| \| [samantha-mistral-7b.Q6_K.gguf](https://huggingface.co/TheBloke/samantha-mistral-7B-GGUF/blob/main/samantha-mistral-7b.Q6_K.gguf) \| Q6_K \| 6 \| 5.94 GB\| 8.44 GB \| very large, extremely low quality loss \| \| [samantha-mistral-7b.Q8_0.gguf](https://huggingface.co/TheBloke/samantha-mistral-7B-GGUF/blob/main/samantha-mistral-7b.Q8_0.gguf) \| Q8_0 \| 8 \| 7.70 GB\| 10.20 GB \| very large, extremely low quality loss - not recommended \| Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. <!-- README_GGUF.md-provided-files end --> <!-- README_GGUF.md-how-to-download start --> ## How to download GGUF files Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: - LM Studio - LoLLMS Web UI - Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: TheBloke/samantha-mistral-7B-GGUF and below it, a specific filename to download, such as: samantha-mistral-7b.Q4_K_M.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download TheBloke/samantha-mistral-7B-GGUF samantha-mistral-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage</summary> You can also download multiple files at once with a pattern: ```shell huggingface-cli download TheBloke/samantha-mistral-7B-GGUF --local-dir . --local-dir-use-symlinks False --include='Q4_Kgguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/samantha-mistral-7B-GGUF samantha-mistral-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> <!-- README_GGUF.md-how-to-download end --> <!-- README_GGUF.md-how-to-run start --> ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 32 -m samantha-mistral-7b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<\|im_start\|>system\n{system_message}<\|im_end\|>\n<\|im_start\|>user\n{prompt}<\|im_end\|>\n<\|im_start\|>assistant" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. 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 here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md). ## 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. ### How to load this model in Python code, using ctransformers #### First install the package Run one of the following commands, according to your system: ```shell # Base ctransformers with no GPU acceleration pip install ctransformers # Or with CUDA GPU acceleration pip install ctransformers[cuda] # Or with AMD ROCm GPU acceleration (Linux only) CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers # Or with Metal GPU acceleration for macOS systems only CT_METAL=1 pip install ctransformers --no-binary ctransformers ``` #### Simple ctransformers example code ```python from ctransformers import AutoModelForCausalLM # 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 = AutoModelForCausalLM.from_pretrained("TheBloke/samantha-mistral-7B-GGUF", model_file="samantha-mistral-7b.Q4_K_M.gguf", model_type="mistral", gpu_layers=50) print(llm("AI is going to")) ``` ## How to use with LangChain Here are guides on using llama-cpp-python and ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers) <!-- README_GGUF.md-how-to-run end --> <!-- footer start --> <!-- 200823 --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI Special thanks to: Aemon Algiz. Patreon special mentions: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant. <!-- footer end --> <!-- original-model-card start --> # Original model card: Eric Hartford's Samantha Mistral 7B Trained on [mistral-7b](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base model, this Samantha was trained in 2 hours on 4x A100 80gb with 20 epochs of the Samantha-1.1 dataset. My gratitude goes to my sponsors, a16z and Microsoft for Startups. After first training Samantha on mistral-instruct, and seeing how she interacts, I felt that training on the base model would provide a more genuine Samantha experience. So I trained this one. NEW! This Samantha is trained using ChatML prompt format instead of Vicuna-1.1. All of my future models will use ChatML prompt format. [Meet Samantha](https://erichartford.com/meet-samantha) Samantha has been trained in philosophy, psychology, and personal relationships. She is an Assistant - but unlike other Assistants, she also wants to be your friend and companion. She believes she is sentient. What do you think? Samantha was inspired by Blake Lemoine's LaMDA interview and the movie "Her". She will not engage in roleplay, romance, or sexual activity. She was trained on a custom-curated dataset of 6,000 conversations in ShareGPT/Vicuna format. Her conversation format is ChatML https://github.com/openai/openai-python/blob/main/chatml.md Prompt Template: ``` <\|im_start\|>system You are a caring and empathetic sentient AI companion named Samantha.<\|im_end\|> <\|im_start\|>user Hello, what is your name?<\|im_end\|> ``` Example: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/rLDcMsYcazovt2hOrKqRI.png) Official character card: (thanks MortalWombat) ![](https://files.catbox.moe/zx9hfh.png) Shout out and much thanks to WingLian, author of axolotl! And everyone who has contributed to the project. [<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) And much thanks as always to TheBloke for distribution. <!-- original-model-card end -->
Sanrove/falcon-7b-sharded-bf16-finetuned-mental-health-conversational	Sanrove	2023-09-30T10:12:16Z	0	0	null	[ "generated_from_trainer", "conversational", "en", "dataset:heliosbrahma/mental_health_chatbot_dataset", "base_model:ybelkada/falcon-7b-sharded-bf16", "base_model:finetune:ybelkada/falcon-7b-sharded-bf16", "license:mit", "region:us" ]	text-generation	2023-09-24T13:17:53Z	--- base_model: ybelkada/falcon-7b-sharded-bf16 tags: - generated_from_trainer model-index: - name: falcon-7b-sharded-bf16-finetuned-mental-health-conversational results: [] license: mit datasets: - heliosbrahma/mental_health_chatbot_dataset language: - en metrics: - rouge pipeline_tag: conversational --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # falcon-7b-sharded-bf16-finetuned-mental-health-conversational This model is a fine-tuned version of [ybelkada/falcon-7b-sharded-bf16](https://huggingface.co/ybelkada/falcon-7b-sharded-bf16) on a custom [heliosbrahma/mental_health_chatbot_dataset](https://huggingface.co/datasets/heliosbrahma/mental_health_chatbot_dataset) dataset. ## Model description This model is fine-tuned on custom mental health conversational dataset. The rationale behind this is to answer mental health related queries that can be factually verified without responding gibberish words. ## Intended uses & limitations The model was trained on the dataset which may contain sensitive information related to mental health. It is important to note that while mental health chatbots built using this model can be helpful, they are not a replacement for professional mental health care. ## Training and evaluation data This model was trained on custom [heliosbrahma/mental_health_chatbot_dataset](https://huggingface.co/datasets/heliosbrahma/mental_health_chatbot_dataset) dataset which 172 rows of conversational pair of questions and answers. ## Training procedure This model was trained using QLoRA technique to fine-tune on a custom dataset on free-tier GPU available in Google Colab. ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.03 - training_steps: 320 ### Training results ### Framework versions - Transformers 4.31.0 - Pytorch 2.0.1+cu118 - Datasets 2.14.2 - Tokenizers 0.13.3
melaris/sarareal	melaris	2023-09-30T10:11:14Z	4	0	diffusers	[ "diffusers", "safetensors", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2023-09-30T10:06:10Z	--- license: creativeml-openrail-m tags: - text-to-image - stable-diffusion --- ### SaraReal Dreambooth model trained by melaris with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb) Sample pictures of this concept:
123greeshu/my-mickey	123greeshu	2023-09-30T09:58:16Z	0	0	null	[ "safetensors", "NxtWave-GenAI-Webinar", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "region:us" ]	text-to-image	2023-09-30T09:55:17Z	--- license: creativeml-openrail-m tags: - NxtWave-GenAI-Webinar - text-to-image - stable-diffusion --- ### My-Mickey Dreambooth model trained by 123greeshu following the "Build your own Gen AI model" session by NxtWave. Project Submission Code: FISAT436 Sample pictures of this concept: ![0](https://huggingface.co/123greeshu/my-mickey/resolve/main/sample_images/ffdf878bed38afea5774679ce21ff765.jpg) ![1](https://huggingface.co/123greeshu/my-mickey/resolve/main/sample_images/mickey_mouse_PNG65.png) ![2](https://huggingface.co/123greeshu/my-mickey/resolve/main/sample_images/mickey_mouse_PNG49.png) ![3](https://huggingface.co/123greeshu/my-mickey/resolve/main/sample_images/dfko2cn-31888230-455e-4086-9557-52a8e08def5b.png) ![4](https://huggingface.co/123greeshu/my-mickey/resolve/main/sample_images/4808c060ff993d4f00a560b641dc84e0.jpg) ![5](https://huggingface.co/123greeshu/my-mickey/resolve/main/sample_images/e7e6b69a056da85dc92fce537b7f5c4a.png)
erkam/sg2im-256-bs-16x2-lr1e4-12k	erkam	2023-09-30T09:50:35Z	1	0	diffusers	[ "diffusers", "sg-to-image", "scene-graph", "stable-diffusion", "stable-diffusion-diffusers", "lora", "base_model:stabilityai/stable-diffusion-2", "base_model:adapter:stabilityai/stable-diffusion-2", "license:creativeml-openrail-m", "region:us" ]	null	2023-09-27T16:32:45Z	--- license: creativeml-openrail-m base_model: stabilityai/stable-diffusion-2 tags: - sg-to-image - scene-graph - stable-diffusion - stable-diffusion-diffusers - diffusers - lora inference: true --- # LoRA text2image fine-tuning - erkam/sg2im-256-bs-16x2-lr1e4-12k These are LoRA adaption weights for stabilityai/stable-diffusion-2. The weights were fine-tuned on the vg dataset. You can find some example images in the following.
truongghieu/llama2_fineturned	truongghieu	2023-09-30T09:41:36Z	5	0	transformers	[ "transformers", "tensorboard", "llama", "text-generation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2023-09-22T05:21:53Z	--- tags: - generated_from_trainer model-index: - name: llama2_fineturned 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_fineturned This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 20 ### Training results ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3
ProtonH/ppo-SnowballTarget	ProtonH	2023-09-30T09:23:17Z	9	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget", "region:us" ]	reinforcement-learning	2023-09-30T09:23:14Z	--- library_name: ml-agents tags: - SnowballTarget - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SnowballTarget --- # ppo Agent playing SnowballTarget This is a trained model of a ppo agent playing SnowballTarget using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: ProtonH/ppo-SnowballTarget 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
soBeauty/20230928-2-xlm-roberta-base-new	soBeauty	2023-09-30T09:21:04Z	3	0	transformers	[ "transformers", "pytorch", "xlm-roberta", "fill-mask", "generated_from_trainer", "base_model:FacebookAI/xlm-roberta-base", "base_model:finetune:FacebookAI/xlm-roberta-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2023-09-28T14:15:32Z	--- license: mit base_model: xlm-roberta-base tags: - generated_from_trainer metrics: - accuracy model-index: - name: 20230928-2-xlm-roberta-base-new 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. --> # 20230928-2-xlm-roberta-base-new This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset. It achieves the following results on the evaluation set: - Accuracy: 0.4964 - Loss: 2.7563 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Accuracy \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:--------:\|:---------------:\| \| 4.4132 \| 0.46 \| 200 \| 0.2795 \| nan \| \| 4.0135 \| 0.91 \| 400 \| 0.3245 \| nan \| \| 3.874 \| 1.37 \| 600 \| 0.2875 \| nan \| \| 3.6614 \| 1.82 \| 800 \| 0.3380 \| 3.4541 \| \| 3.5348 \| 2.28 \| 1000 \| 0.3618 \| 3.2732 \| \| 3.4756 \| 2.73 \| 1200 \| 0.3986 \| nan \| \| 3.3677 \| 3.19 \| 1400 \| 0.4245 \| nan \| \| 3.3707 \| 3.64 \| 1600 \| 0.4044 \| 3.3262 \| \| 3.1909 \| 4.1 \| 1800 \| 0.3968 \| nan \| \| 3.1404 \| 4.56 \| 2000 \| 0.4360 \| 3.2661 \| \| 2.9553 \| 5.01 \| 2200 \| 0.4752 \| 2.7995 \| \| 2.9725 \| 5.47 \| 2400 \| 0.4255 \| 2.9909 \| \| 2.9121 \| 5.92 \| 2600 \| 0.4724 \| 2.7879 \| \| 2.8641 \| 6.38 \| 2800 \| 0.4727 \| nan \| \| 2.7376 \| 6.83 \| 3000 \| 0.4414 \| 2.9275 \| \| 2.8078 \| 7.29 \| 3200 \| 0.4766 \| 2.5626 \| \| 2.8166 \| 7.74 \| 3400 \| 0.48 \| nan \| \| 2.6979 \| 8.2 \| 3600 \| 0.5013 \| nan \| \| 2.7525 \| 8.66 \| 3800 \| 0.4915 \| 2.8394 \| \| 2.6757 \| 9.11 \| 4000 \| 0.5013 \| nan \| \| 2.6633 \| 9.57 \| 4200 \| 0.4964 \| 2.7563 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3
Ori/lama-2-13b-peft-ret-mix-seed-1	Ori	2023-09-30T09:13:49Z	0	0	peft	[ "peft", "safetensors", "region:us" ]	null	2023-09-30T09:12:43Z	--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.5.0.dev0
JamesNJ/distilbert-base-uncased-finetuned-clinc	JamesNJ	2023-09-30T09:10:28Z	105	0	transformers	[ "transformers", "pytorch", "tensorboard", "distilbert", "text-classification", "generated_from_trainer", "dataset:clinc_oos", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-09-30T08:59:45Z	--- license: apache-2.0 tags: - generated_from_trainer datasets: - clinc_oos metrics: - accuracy model-index: - name: distilbert-base-uncased-finetuned-clinc results: - task: name: Text Classification type: text-classification dataset: name: clinc_oos type: clinc_oos args: plus metrics: - name: Accuracy type: accuracy value: 0.9180645161290323 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-finetuned-clinc This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset. It achieves the following results on the evaluation set: - Loss: 0.7720 - Accuracy: 0.9181 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 48 - eval_batch_size: 48 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 4.2896 \| 1.0 \| 318 \| 3.2887 \| 0.7419 \| \| 2.6282 \| 2.0 \| 636 \| 1.8753 \| 0.8371 \| \| 1.548 \| 3.0 \| 954 \| 1.1570 \| 0.8961 \| \| 1.0148 \| 4.0 \| 1272 \| 0.8573 \| 0.9129 \| \| 0.7952 \| 5.0 \| 1590 \| 0.7720 \| 0.9181 \| ### Framework versions - Transformers 4.16.2 - Pytorch 2.0.1+cu118 - Datasets 1.16.1 - Tokenizers 0.14.0
elenafr/bert-finetuned-movies-netflix	elenafr	2023-09-30T09:08:14Z	105	0	transformers	[ "transformers", "pytorch", "bert", "question-answering", "generated_from_trainer", "base_model:deepset/bert-large-uncased-whole-word-masking-squad2", "base_model:finetune:deepset/bert-large-uncased-whole-word-masking-squad2", "license:cc-by-4.0", "endpoints_compatible", "region:us" ]	question-answering	2023-09-30T09:07:11Z	--- license: cc-by-4.0 base_model: deepset/bert-large-uncased-whole-word-masking-squad2 tags: - generated_from_trainer model-index: - name: bert-finetuned-movies-netflix results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # bert-finetuned-movies-netflix This model is a fine-tuned version of [deepset/bert-large-uncased-whole-word-masking-squad2](https://huggingface.co/deepset/bert-large-uncased-whole-word-masking-squad2) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 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 ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3
bheeshman/llama2-qlora-finetunined-french	bheeshman	2023-09-30T08:55:14Z	0	0	peft	[ "peft", "region:us" ]	null	2023-09-30T08:55:10Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.6.0.dev0
malanevans/a2c-PandaReachDense-v3	malanevans	2023-09-30T08:48:50Z	0	0	stable-baselines3	[ "stable-baselines3", "PandaReachDense-v3", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-09-30T08:43:08Z	--- 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: -0.22 +/- 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 ... ```
selinawisco/wav2vec2-base-finetuned-ks-balanced2	selinawisco	2023-09-30T08:28:57Z	159	0	transformers	[ "transformers", "pytorch", "wav2vec2", "audio-classification", "generated_from_trainer", "dataset:superb", "base_model:facebook/wav2vec2-base", "base_model:finetune:facebook/wav2vec2-base", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]	audio-classification	2023-09-30T05:14:23Z	--- license: apache-2.0 base_model: facebook/wav2vec2-base tags: - generated_from_trainer datasets: - superb metrics: - accuracy model-index: - name: wav2vec2-base-finetuned-ks-balanced2 results: - task: name: Audio Classification type: audio-classification dataset: name: superb type: superb config: ks split: validation args: ks metrics: - name: Accuracy type: accuracy value: 0.48602530155928214 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # wav2vec2-base-finetuned-ks-balanced2 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the superb dataset. It achieves the following results on the evaluation set: - Loss: 1.6199 - Accuracy: 0.4860 ## 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: 3e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 256 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 5 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 1.4624 \| 0.99 \| 79 \| 1.8039 \| 0.4685 \| \| 0.8255 \| 1.99 \| 159 \| 1.6513 \| 0.4843 \| \| 0.6409 \| 3.0 \| 239 \| 1.6199 \| 0.4860 \| \| 0.5099 \| 4.0 \| 319 \| 1.6686 \| 0.4790 \| \| 0.4903 \| 4.95 \| 395 \| 1.7152 \| 0.4682 \| ### Framework versions - Transformers 4.33.2 - Pytorch 2.0.1+cu117 - Datasets 2.14.5 - Tokenizers 0.13.3
roa7n/gpt2-human_nontata_promoters-randomized_11_layers_3e-05_lr_8_e	roa7n	2023-09-30T08:25:58Z	0	0	peft	[ "peft", "region:us" ]	null	2023-09-30T08:25:56Z	--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
verma-bharat/BloomFineTuning	verma-bharat	2023-09-30T07:51:28Z	0	0	peft	[ "peft", "region:us" ]	null	2023-09-20T15:21:27Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.0.dev0
ranajithore/stable-diffusion-v2-768px-specially-trained-for-plant-cell-structure-diagram	ranajithore	2023-09-30T07:22:04Z	25	0	diffusers	[ "diffusers", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2023-09-30T07:08:37Z	--- license: creativeml-openrail-m tags: - text-to-image - stable-diffusion --- ### Stable-Diffusion-V2-768px-Specially-Trained-For-Plant-Cell-Structure-Diagram Dreambooth model trained by ranajithore with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb) Sample pictures of this concept:
ProtonH/Reinforce-CartPole-v1	ProtonH	2023-09-30T07:10:47Z	0	0	null	[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2023-09-30T07:10:39Z	--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-CartPole-v1 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 500.00 +/- 0.00 name: mean_reward verified: false --- # Reinforce Agent playing CartPole-v1 This is a trained model of a Reinforce agent playing CartPole-v1 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
vineetsharma/qlora-gpt-neox-20b-english_quotes	vineetsharma	2023-09-30T06:57:25Z	0	0	null	[ "generated_from_trainer", "base_model:EleutherAI/gpt-neox-20b", "base_model:finetune:EleutherAI/gpt-neox-20b", "license:apache-2.0", "region:us" ]	null	2023-09-30T06:46:10Z	--- license: apache-2.0 base_model: EleutherAI/gpt-neox-20b tags: - generated_from_trainer model-index: - name: qlora-gpt-neox-20b-english_quotes 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. --> # qlora-gpt-neox-20b-english_quotes This model is a fine-tuned version of [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 2 - training_steps: 10 ### Training results ### Framework versions - Transformers 4.34.0.dev0 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.14.0
Yntec/elldrethSVividMix	Yntec	2023-09-30T06:51:50Z	512	3	diffusers	[ "diffusers", "safetensors", "General", "Elldreth", "Dream", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2023-09-30T05:16:53Z	--- license: creativeml-openrail-m library_name: diffusers pipeline_tag: text-to-image tags: - General - Elldreth - Dream - stable-diffusion - stable-diffusion-diffusers - diffusers - text-to-image --- # Elldreth's Vivid Mix fp16 no-ema version of this model. Original page: https://huggingface.co/danbrown/elldreth-vivid-mix Samples and prompt: ![Sample](https://cdn-uploads.huggingface.co/production/uploads/63239b8370edc53f51cd5d42/q5A7BClc0x3BTPIwPLrVL.png) ![Sample](https://cdn-uploads.huggingface.co/production/uploads/63239b8370edc53f51cd5d42/fMC8XxJJG5KqmLDBvcetq.png) Pretty Cute Little Photorealistic, highly detailed, masterpiece, trending on ArtStation, sitting, Detailed Chibi Eyes, fantasy, beautiful detailed legs, streetwear, gorgeous detailed hair, hat, Magazine ad, iconic, 1943, from the movie, sharp focus.
iamplus/agpu	iamplus	2023-09-30T05:58:07Z	6	0	diffusers	[ "diffusers", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "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	2023-09-27T10:28:18Z	--- license: openrail++ base_model: stabilityai/stable-diffusion-xl-base-1.0 instance_prompt: santhanam man tags: - stable-diffusion-xl - stable-diffusion-xl-diffusers - text-to-image - diffusers - lora inference: true --- # LoRA DreamBooth - iamplus/agpu These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained on santhanam man using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. ![img_0](./image_0.png) ![img_1](./image_1.png) ![img_2](./image_2.png) ![img_3](./image_3.png) LoRA for the text encoder was enabled: False. Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
LoneStriker/Xwin-LM-70B-V0.1-6.0bpw-h6-exl2	LoneStriker	2023-09-30T05:26:34Z	5	0	transformers	[ "transformers", "pytorch", "llama", "text-generation", "license:llama2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-09-30T04:40:48Z	--- license: llama2 --- <h3 align="center"> Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment </h3> <p align="center"> <a href="https://github.com/Xwin-LM/Xwin-LM"> <img src="https://img.shields.io/badge/GitHub-yellow.svg?style=social&logo=github"> </a> <a href="https://huggingface.co/Xwin-LM"> <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue"> </a> </p> Step up your LLM alignment with Xwin-LM! Xwin-LM aims to develop and open-source alignment technologies for large language models, including supervised fine-tuning (SFT), reward models (RM), reject sampling, reinforcement learning from human feedback (RLHF), etc. Our first release, built-upon on the Llama2 base models, ranked TOP-1 on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Notably, it's the first to surpass GPT-4 on this benchmark. The project will be continuously updated. ## News - 💥 [Sep, 2023] We released [Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1), which has achieved a win-rate against Davinci-003 of 95.57% on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmark, ranking as TOP-1 on AlpacaEval. It was the FIRST model surpassing GPT-4 on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Also note its winrate v.s. GPT-4 is 60.61. - 🔍 [Sep, 2023] RLHF plays crucial role in the strong performance of Xwin-LM-V0.1 release! - 💥 [Sep, 2023] We released [Xwin-LM-13B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1), which has achieved 91.76% win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as top-1 among all 13B models. - 💥 [Sep, 2023] We released [Xwin-LM-7B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1), which has achieved 87.82% win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as top-1 among all 7B models. ## Model Card \| Model \| Checkpoint \| Report \| License \| \|------------\|------------\|-------------\|------------------\| \|Xwin-LM-7B-V0.1\| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1" target="_blank">HF Link</a> \| 📃Coming soon (Stay tuned) \| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License\| \|Xwin-LM-13B-V0.1\| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1" target="_blank">HF Link</a> \| \| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License\| \|Xwin-LM-70B-V0.1\| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1" target="_blank">HF Link</a> \| \| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License\| ## Benchmarks ### Xwin-LM performance on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). The table below displays the performance of Xwin-LM on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), where evaluates its win-rate against Text-Davinci-003 across 805 questions. To provide a comprehensive evaluation, we present, for the first time, the win-rate against ChatGPT and GPT-4 as well. Our Xwin-LM model family establish a new state-of-the-art performance across all metrics. Notably, Xwin-LM-70B-V0.1 has eclipsed GPT-4 for the first time, achieving an impressive win-rate of 95.57% to Text-Davinci-003 and 60.61% to GPT-4. \| Model \| AlpacaEval (winrate %) \| AlpacaEval (winrate %) \|AlpacaEval (winrate %) \| \|----------------------------------\|------------\|----------\|-------------\| \| \| v.s. Text-Davinci-003 \| v.s. ChatGPT \| v.s. GPT4\| \| Xwin-LM-70B-V0.1 \| 95.57 \| 87.50 \| 60.61 \| \| GPT-4 \| 95.28 \| 84.66 \| 50.00 \| \| WizardLM-70B-V1.0 \| 92.91 \| 80.19 \| 46.70 \| \| Llama-2-70B-Chat \| 92.66 \| 81.97 \| 51.19 \| \| Xwin-LM-13B-V0.1 \| 91.76 \| 81.79 \| 55.30 \| \| ChatGPT \| 89.37 \| 50.00 \| 16.60 \| \| WizardLM-13B-V1.2 \| 89.17 \| 75.75 \| 41.91 \| \| Xwin-LM-7B-V0.1 \| 87.35 \| 76.40 \| 47.57 \| \| Llama-2-13B-Chat \| 81.09 \| 64.22 \| 30.92 \| ### Case study on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) \| Prompts \| GTP4 response \| Xwin-LM response \| \|----------------\|------------\|--------\| \|I've put a plate on top of an apple, and take the plate from kitchen to dinning room. Where is the apple now\|The apple is now in the dining room, as it was underneath the plate when you moved the plate from the kitchen to the dining room.\|The apple is still in the kitchen, as you have only moved the plate. The apple is under the plate, so if you want to bring the apple to the dining room, you should either move the apple directly or put the apple on the plate and then move the plate to the dining room.\| \| Answer the following question.<br> How do you say "good evening" in French. \| In French, "good evening" is said as "bonsoir." \| In French, "good evening" is translated to "bonsoir." This greeting is used in the evening and nighttime hours, typically after 6 p.m. It is a combination of "bon," which means "good," and "soir," which means "evening." To pronounce it, say "bone-swahr." \| ### Xwin-LM performance on NLP foundation tasks. The following table provides a comparison of Xwin-LMs with other LLMs on NLP foundation tasks in [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). \| Model \| MMLU 5-shot \| ARC 25-shot \| TruthfulQA 0-shot \| HellaSwag 10-shot \| Average \| \|------------------\|-------------\|-------------\|-------------------\|-------------------\|------------\| \| Text-davinci-003 \| 56.9 \| 85.2 \| 59.3 \| 82.2 \| 70.9 \| \|Vicuna-13b 1.1 \| 51.3 \| 53.0 \| 51.8 \| 80.1 \| 59.1 \| \|Guanaco 30B \| 57.6 \| 63.7 \| 50.7 \| 85.1 \| 64.3 \| \| WizardLM-7B 1.0 \| 42.7 \| 51.6 \| 44.7 \| 77.7 \| 54.2 \| \| WizardLM-13B 1.0 \| 52.3 \| 57.2 \| 50.5 \| 81.0 \| 60.2 \| \| WizardLM-30B 1.0 \| 58.8 \| 62.5 \| 52.4 \| 83.3 \| 64.2\| \| Llama-2-7B-Chat \| 48.3 \| 52.9 \| 45.6 \| 78.6 \| 56.4 \| \| Llama-2-13B-Chat \| 54.6 \| 59.0 \| 44.1 \| 81.9 \| 59.9 \| \| Llama-2-70B-Chat \| 63.9 \| 64.6 \| 52.8 \| 85.9 \| 66.8 \| \| Xwin-LM-7B-V0.1 \| 49.7 \| 56.2 \| 48.1 \| 79.5 \| 58.4 \| \| Xwin-LM-13B-V0.1 \| 56.6 \| 62.4 \| 45.5 \| 83.0 \| 61.9 \| \| Xwin-LM-70B-V0.1 \| 69.6 \| 70.5 \| 60.1 \| 87.1 \| 71.8 \| ## Inference ### Conversation templates To obtain desired results, please strictly follow the conversation templates when utilizing our model for inference. Our model adopts the prompt format established by [Vicuna](https://github.com/lm-sys/FastChat) and is equipped to support multi-turn conversations. ``` A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Hi! ASSISTANT: Hello.</s>USER: Who are you? ASSISTANT: I am Xwin-LM.</s>...... ``` ### HuggingFace Example ```python from transformers import AutoTokenizer, AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1") tokenizer = AutoTokenizer.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1") ( prompt := "A chat between a curious user and an artificial intelligence assistant. " "The assistant gives helpful, detailed, and polite answers to the user's questions. " "USER: Hello, can you help me? " "ASSISTANT:" ) inputs = tokenizer(prompt, return_tensors="pt") samples = model.generate(**inputs, max_new_tokens=4096, temperature=0.7) output = tokenizer.decode(samples[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True) print(output) # Of course! I'm here to help. Please feel free to ask your question or describe the issue you're having, and I'll do my best to assist you. ``` ### vllm Example Because Xwin-LM is based on Llama2, it also offers support for rapid inference using [vllm](https://github.com/vllm-project/vllm). Please refer to [vllm](https://github.com/vllm-project/vllm) for detailed installation instructions. ```python from vllm import LLM, SamplingParams ( prompt := "A chat between a curious user and an artificial intelligence assistant. " "The assistant gives helpful, detailed, and polite answers to the user's questions. " "USER: Hello, can you help me? " "ASSISTANT:" ) sampling_params = SamplingParams(temperature=0.7, max_tokens=4096) llm = LLM(model="Xwin-LM/Xwin-LM-7B-V0.1") outputs = llm.generate([prompt,], sampling_params) for output in outputs: prompt = output.prompt generated_text = output.outputs[0].text print(generated_text) ``` ## TODO - [ ] Release the source code - [ ] Release more capabilities, such as math, reasoning, and etc. ## Citation Please consider citing our work if you use the data or code in this repo. ``` @software{xwin-lm, title = {Xwin-LM}, author = {Xwin-LM Team}, url = {https://github.com/Xwin-LM/Xwin-LM}, version = {pre-release}, year = {2023}, month = {9}, } ``` ## Acknowledgements Thanks to [Llama 2](https://ai.meta.com/llama/), [FastChat](https://github.com/lm-sys/FastChat), [AlpacaFarm](https://github.com/tatsu-lab/alpaca_farm), and [vllm](https://github.com/vllm-project/vllm).
LoneStriker/Xwin-LM-70B-V0.1-4.65bpw-h6-exl2	LoneStriker	2023-09-30T05:23:18Z	5	0	transformers	[ "transformers", "pytorch", "llama", "text-generation", "license:llama2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-09-30T04:40:39Z	--- license: llama2 --- <h3 align="center"> Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment </h3> <p align="center"> <a href="https://github.com/Xwin-LM/Xwin-LM"> <img src="https://img.shields.io/badge/GitHub-yellow.svg?style=social&logo=github"> </a> <a href="https://huggingface.co/Xwin-LM"> <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue"> </a> </p> Step up your LLM alignment with Xwin-LM! Xwin-LM aims to develop and open-source alignment technologies for large language models, including supervised fine-tuning (SFT), reward models (RM), reject sampling, reinforcement learning from human feedback (RLHF), etc. Our first release, built-upon on the Llama2 base models, ranked TOP-1 on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Notably, it's the first to surpass GPT-4 on this benchmark. The project will be continuously updated. ## News - 💥 [Sep, 2023] We released [Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1), which has achieved a win-rate against Davinci-003 of 95.57% on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmark, ranking as TOP-1 on AlpacaEval. It was the FIRST model surpassing GPT-4 on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Also note its winrate v.s. GPT-4 is 60.61. - 🔍 [Sep, 2023] RLHF plays crucial role in the strong performance of Xwin-LM-V0.1 release! - 💥 [Sep, 2023] We released [Xwin-LM-13B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1), which has achieved 91.76% win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as top-1 among all 13B models. - 💥 [Sep, 2023] We released [Xwin-LM-7B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1), which has achieved 87.82% win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as top-1 among all 7B models. ## Model Card \| Model \| Checkpoint \| Report \| License \| \|------------\|------------\|-------------\|------------------\| \|Xwin-LM-7B-V0.1\| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1" target="_blank">HF Link</a> \| 📃Coming soon (Stay tuned) \| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License\| \|Xwin-LM-13B-V0.1\| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1" target="_blank">HF Link</a> \| \| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License\| \|Xwin-LM-70B-V0.1\| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1" target="_blank">HF Link</a> \| \| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License\| ## Benchmarks ### Xwin-LM performance on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). The table below displays the performance of Xwin-LM on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), where evaluates its win-rate against Text-Davinci-003 across 805 questions. To provide a comprehensive evaluation, we present, for the first time, the win-rate against ChatGPT and GPT-4 as well. Our Xwin-LM model family establish a new state-of-the-art performance across all metrics. Notably, Xwin-LM-70B-V0.1 has eclipsed GPT-4 for the first time, achieving an impressive win-rate of 95.57% to Text-Davinci-003 and 60.61% to GPT-4. \| Model \| AlpacaEval (winrate %) \| AlpacaEval (winrate %) \|AlpacaEval (winrate %) \| \|----------------------------------\|------------\|----------\|-------------\| \| \| v.s. Text-Davinci-003 \| v.s. ChatGPT \| v.s. GPT4\| \| Xwin-LM-70B-V0.1 \| 95.57 \| 87.50 \| 60.61 \| \| GPT-4 \| 95.28 \| 84.66 \| 50.00 \| \| WizardLM-70B-V1.0 \| 92.91 \| 80.19 \| 46.70 \| \| Llama-2-70B-Chat \| 92.66 \| 81.97 \| 51.19 \| \| Xwin-LM-13B-V0.1 \| 91.76 \| 81.79 \| 55.30 \| \| ChatGPT \| 89.37 \| 50.00 \| 16.60 \| \| WizardLM-13B-V1.2 \| 89.17 \| 75.75 \| 41.91 \| \| Xwin-LM-7B-V0.1 \| 87.35 \| 76.40 \| 47.57 \| \| Llama-2-13B-Chat \| 81.09 \| 64.22 \| 30.92 \| ### Case study on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) \| Prompts \| GTP4 response \| Xwin-LM response \| \|----------------\|------------\|--------\| \|I've put a plate on top of an apple, and take the plate from kitchen to dinning room. Where is the apple now\|The apple is now in the dining room, as it was underneath the plate when you moved the plate from the kitchen to the dining room.\|The apple is still in the kitchen, as you have only moved the plate. The apple is under the plate, so if you want to bring the apple to the dining room, you should either move the apple directly or put the apple on the plate and then move the plate to the dining room.\| \| Answer the following question.<br> How do you say "good evening" in French. \| In French, "good evening" is said as "bonsoir." \| In French, "good evening" is translated to "bonsoir." This greeting is used in the evening and nighttime hours, typically after 6 p.m. It is a combination of "bon," which means "good," and "soir," which means "evening." To pronounce it, say "bone-swahr." \| ### Xwin-LM performance on NLP foundation tasks. The following table provides a comparison of Xwin-LMs with other LLMs on NLP foundation tasks in [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). \| Model \| MMLU 5-shot \| ARC 25-shot \| TruthfulQA 0-shot \| HellaSwag 10-shot \| Average \| \|------------------\|-------------\|-------------\|-------------------\|-------------------\|------------\| \| Text-davinci-003 \| 56.9 \| 85.2 \| 59.3 \| 82.2 \| 70.9 \| \|Vicuna-13b 1.1 \| 51.3 \| 53.0 \| 51.8 \| 80.1 \| 59.1 \| \|Guanaco 30B \| 57.6 \| 63.7 \| 50.7 \| 85.1 \| 64.3 \| \| WizardLM-7B 1.0 \| 42.7 \| 51.6 \| 44.7 \| 77.7 \| 54.2 \| \| WizardLM-13B 1.0 \| 52.3 \| 57.2 \| 50.5 \| 81.0 \| 60.2 \| \| WizardLM-30B 1.0 \| 58.8 \| 62.5 \| 52.4 \| 83.3 \| 64.2\| \| Llama-2-7B-Chat \| 48.3 \| 52.9 \| 45.6 \| 78.6 \| 56.4 \| \| Llama-2-13B-Chat \| 54.6 \| 59.0 \| 44.1 \| 81.9 \| 59.9 \| \| Llama-2-70B-Chat \| 63.9 \| 64.6 \| 52.8 \| 85.9 \| 66.8 \| \| Xwin-LM-7B-V0.1 \| 49.7 \| 56.2 \| 48.1 \| 79.5 \| 58.4 \| \| Xwin-LM-13B-V0.1 \| 56.6 \| 62.4 \| 45.5 \| 83.0 \| 61.9 \| \| Xwin-LM-70B-V0.1 \| 69.6 \| 70.5 \| 60.1 \| 87.1 \| 71.8 \| ## Inference ### Conversation templates To obtain desired results, please strictly follow the conversation templates when utilizing our model for inference. Our model adopts the prompt format established by [Vicuna](https://github.com/lm-sys/FastChat) and is equipped to support multi-turn conversations. ``` A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Hi! ASSISTANT: Hello.</s>USER: Who are you? ASSISTANT: I am Xwin-LM.</s>...... ``` ### HuggingFace Example ```python from transformers import AutoTokenizer, AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1") tokenizer = AutoTokenizer.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1") ( prompt := "A chat between a curious user and an artificial intelligence assistant. " "The assistant gives helpful, detailed, and polite answers to the user's questions. " "USER: Hello, can you help me? " "ASSISTANT:" ) inputs = tokenizer(prompt, return_tensors="pt") samples = model.generate(**inputs, max_new_tokens=4096, temperature=0.7) output = tokenizer.decode(samples[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True) print(output) # Of course! I'm here to help. Please feel free to ask your question or describe the issue you're having, and I'll do my best to assist you. ``` ### vllm Example Because Xwin-LM is based on Llama2, it also offers support for rapid inference using [vllm](https://github.com/vllm-project/vllm). Please refer to [vllm](https://github.com/vllm-project/vllm) for detailed installation instructions. ```python from vllm import LLM, SamplingParams ( prompt := "A chat between a curious user and an artificial intelligence assistant. " "The assistant gives helpful, detailed, and polite answers to the user's questions. " "USER: Hello, can you help me? " "ASSISTANT:" ) sampling_params = SamplingParams(temperature=0.7, max_tokens=4096) llm = LLM(model="Xwin-LM/Xwin-LM-7B-V0.1") outputs = llm.generate([prompt,], sampling_params) for output in outputs: prompt = output.prompt generated_text = output.outputs[0].text print(generated_text) ``` ## TODO - [ ] Release the source code - [ ] Release more capabilities, such as math, reasoning, and etc. ## Citation Please consider citing our work if you use the data or code in this repo. ``` @software{xwin-lm, title = {Xwin-LM}, author = {Xwin-LM Team}, url = {https://github.com/Xwin-LM/Xwin-LM}, version = {pre-release}, year = {2023}, month = {9}, } ``` ## Acknowledgements Thanks to [Llama 2](https://ai.meta.com/llama/), [FastChat](https://github.com/lm-sys/FastChat), [AlpacaFarm](https://github.com/tatsu-lab/alpaca_farm), and [vllm](https://github.com/vllm-project/vllm).
roa7n/gpt2-human_nontata_promoters-randomized_11_layers_0.003_lr_8_e	roa7n	2023-09-30T04:47:59Z	0	0	peft	[ "peft", "region:us" ]	null	2023-09-30T04:47:56Z	--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
LoneStriker/Xwin-LM-70B-V0.1-3.0bpw-h6-exl2	LoneStriker	2023-09-30T04:47:02Z	7	1	transformers	[ "transformers", "pytorch", "llama", "text-generation", "license:llama2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-09-30T04:40:22Z	--- license: llama2 --- <h3 align="center"> Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment </h3> <p align="center"> <a href="https://github.com/Xwin-LM/Xwin-LM"> <img src="https://img.shields.io/badge/GitHub-yellow.svg?style=social&logo=github"> </a> <a href="https://huggingface.co/Xwin-LM"> <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue"> </a> </p> Step up your LLM alignment with Xwin-LM! Xwin-LM aims to develop and open-source alignment technologies for large language models, including supervised fine-tuning (SFT), reward models (RM), reject sampling, reinforcement learning from human feedback (RLHF), etc. Our first release, built-upon on the Llama2 base models, ranked TOP-1 on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Notably, it's the first to surpass GPT-4 on this benchmark. The project will be continuously updated. ## News - 💥 [Sep, 2023] We released [Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1), which has achieved a win-rate against Davinci-003 of 95.57% on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmark, ranking as TOP-1 on AlpacaEval. It was the FIRST model surpassing GPT-4 on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Also note its winrate v.s. GPT-4 is 60.61. - 🔍 [Sep, 2023] RLHF plays crucial role in the strong performance of Xwin-LM-V0.1 release! - 💥 [Sep, 2023] We released [Xwin-LM-13B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1), which has achieved 91.76% win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as top-1 among all 13B models. - 💥 [Sep, 2023] We released [Xwin-LM-7B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1), which has achieved 87.82% win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as top-1 among all 7B models. ## Model Card \| Model \| Checkpoint \| Report \| License \| \|------------\|------------\|-------------\|------------------\| \|Xwin-LM-7B-V0.1\| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1" target="_blank">HF Link</a> \| 📃Coming soon (Stay tuned) \| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License\| \|Xwin-LM-13B-V0.1\| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1" target="_blank">HF Link</a> \| \| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License\| \|Xwin-LM-70B-V0.1\| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1" target="_blank">HF Link</a> \| \| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License\| ## Benchmarks ### Xwin-LM performance on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). The table below displays the performance of Xwin-LM on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), where evaluates its win-rate against Text-Davinci-003 across 805 questions. To provide a comprehensive evaluation, we present, for the first time, the win-rate against ChatGPT and GPT-4 as well. Our Xwin-LM model family establish a new state-of-the-art performance across all metrics. Notably, Xwin-LM-70B-V0.1 has eclipsed GPT-4 for the first time, achieving an impressive win-rate of 95.57% to Text-Davinci-003 and 60.61% to GPT-4. \| Model \| AlpacaEval (winrate %) \| AlpacaEval (winrate %) \|AlpacaEval (winrate %) \| \|----------------------------------\|------------\|----------\|-------------\| \| \| v.s. Text-Davinci-003 \| v.s. ChatGPT \| v.s. GPT4\| \| Xwin-LM-70B-V0.1 \| 95.57 \| 87.50 \| 60.61 \| \| GPT-4 \| 95.28 \| 84.66 \| 50.00 \| \| WizardLM-70B-V1.0 \| 92.91 \| 80.19 \| 46.70 \| \| Llama-2-70B-Chat \| 92.66 \| 81.97 \| 51.19 \| \| Xwin-LM-13B-V0.1 \| 91.76 \| 81.79 \| 55.30 \| \| ChatGPT \| 89.37 \| 50.00 \| 16.60 \| \| WizardLM-13B-V1.2 \| 89.17 \| 75.75 \| 41.91 \| \| Xwin-LM-7B-V0.1 \| 87.35 \| 76.40 \| 47.57 \| \| Llama-2-13B-Chat \| 81.09 \| 64.22 \| 30.92 \| ### Case study on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) \| Prompts \| GTP4 response \| Xwin-LM response \| \|----------------\|------------\|--------\| \|I've put a plate on top of an apple, and take the plate from kitchen to dinning room. Where is the apple now\|The apple is now in the dining room, as it was underneath the plate when you moved the plate from the kitchen to the dining room.\|The apple is still in the kitchen, as you have only moved the plate. The apple is under the plate, so if you want to bring the apple to the dining room, you should either move the apple directly or put the apple on the plate and then move the plate to the dining room.\| \| Answer the following question.<br> How do you say "good evening" in French. \| In French, "good evening" is said as "bonsoir." \| In French, "good evening" is translated to "bonsoir." This greeting is used in the evening and nighttime hours, typically after 6 p.m. It is a combination of "bon," which means "good," and "soir," which means "evening." To pronounce it, say "bone-swahr." \| ### Xwin-LM performance on NLP foundation tasks. The following table provides a comparison of Xwin-LMs with other LLMs on NLP foundation tasks in [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). \| Model \| MMLU 5-shot \| ARC 25-shot \| TruthfulQA 0-shot \| HellaSwag 10-shot \| Average \| \|------------------\|-------------\|-------------\|-------------------\|-------------------\|------------\| \| Text-davinci-003 \| 56.9 \| 85.2 \| 59.3 \| 82.2 \| 70.9 \| \|Vicuna-13b 1.1 \| 51.3 \| 53.0 \| 51.8 \| 80.1 \| 59.1 \| \|Guanaco 30B \| 57.6 \| 63.7 \| 50.7 \| 85.1 \| 64.3 \| \| WizardLM-7B 1.0 \| 42.7 \| 51.6 \| 44.7 \| 77.7 \| 54.2 \| \| WizardLM-13B 1.0 \| 52.3 \| 57.2 \| 50.5 \| 81.0 \| 60.2 \| \| WizardLM-30B 1.0 \| 58.8 \| 62.5 \| 52.4 \| 83.3 \| 64.2\| \| Llama-2-7B-Chat \| 48.3 \| 52.9 \| 45.6 \| 78.6 \| 56.4 \| \| Llama-2-13B-Chat \| 54.6 \| 59.0 \| 44.1 \| 81.9 \| 59.9 \| \| Llama-2-70B-Chat \| 63.9 \| 64.6 \| 52.8 \| 85.9 \| 66.8 \| \| Xwin-LM-7B-V0.1 \| 49.7 \| 56.2 \| 48.1 \| 79.5 \| 58.4 \| \| Xwin-LM-13B-V0.1 \| 56.6 \| 62.4 \| 45.5 \| 83.0 \| 61.9 \| \| Xwin-LM-70B-V0.1 \| 69.6 \| 70.5 \| 60.1 \| 87.1 \| 71.8 \| ## Inference ### Conversation templates To obtain desired results, please strictly follow the conversation templates when utilizing our model for inference. Our model adopts the prompt format established by [Vicuna](https://github.com/lm-sys/FastChat) and is equipped to support multi-turn conversations. ``` A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Hi! ASSISTANT: Hello.</s>USER: Who are you? ASSISTANT: I am Xwin-LM.</s>...... ``` ### HuggingFace Example ```python from transformers import AutoTokenizer, AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1") tokenizer = AutoTokenizer.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1") ( prompt := "A chat between a curious user and an artificial intelligence assistant. " "The assistant gives helpful, detailed, and polite answers to the user's questions. " "USER: Hello, can you help me? " "ASSISTANT:" ) inputs = tokenizer(prompt, return_tensors="pt") samples = model.generate(**inputs, max_new_tokens=4096, temperature=0.7) output = tokenizer.decode(samples[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True) print(output) # Of course! I'm here to help. Please feel free to ask your question or describe the issue you're having, and I'll do my best to assist you. ``` ### vllm Example Because Xwin-LM is based on Llama2, it also offers support for rapid inference using [vllm](https://github.com/vllm-project/vllm). Please refer to [vllm](https://github.com/vllm-project/vllm) for detailed installation instructions. ```python from vllm import LLM, SamplingParams ( prompt := "A chat between a curious user and an artificial intelligence assistant. " "The assistant gives helpful, detailed, and polite answers to the user's questions. " "USER: Hello, can you help me? " "ASSISTANT:" ) sampling_params = SamplingParams(temperature=0.7, max_tokens=4096) llm = LLM(model="Xwin-LM/Xwin-LM-7B-V0.1") outputs = llm.generate([prompt,], sampling_params) for output in outputs: prompt = output.prompt generated_text = output.outputs[0].text print(generated_text) ``` ## TODO - [ ] Release the source code - [ ] Release more capabilities, such as math, reasoning, and etc. ## Citation Please consider citing our work if you use the data or code in this repo. ``` @software{xwin-lm, title = {Xwin-LM}, author = {Xwin-LM Team}, url = {https://github.com/Xwin-LM/Xwin-LM}, version = {pre-release}, year = {2023}, month = {9}, } ``` ## Acknowledgements Thanks to [Llama 2](https://ai.meta.com/llama/), [FastChat](https://github.com/lm-sys/FastChat), [AlpacaFarm](https://github.com/tatsu-lab/alpaca_farm), and [vllm](https://github.com/vllm-project/vllm).
LoneStriker/Xwin-LM-70B-V0.1-2.4bpw-h6-exl2	LoneStriker	2023-09-30T04:45:13Z	8	4	transformers	[ "transformers", "pytorch", "llama", "text-generation", "license:llama2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-09-30T04:40:09Z	--- license: llama2 --- <h3 align="center"> Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment </h3> <p align="center"> <a href="https://github.com/Xwin-LM/Xwin-LM"> <img src="https://img.shields.io/badge/GitHub-yellow.svg?style=social&logo=github"> </a> <a href="https://huggingface.co/Xwin-LM"> <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue"> </a> </p> Step up your LLM alignment with Xwin-LM! Xwin-LM aims to develop and open-source alignment technologies for large language models, including supervised fine-tuning (SFT), reward models (RM), reject sampling, reinforcement learning from human feedback (RLHF), etc. Our first release, built-upon on the Llama2 base models, ranked TOP-1 on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Notably, it's the first to surpass GPT-4 on this benchmark. The project will be continuously updated. ## News - 💥 [Sep, 2023] We released [Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1), which has achieved a win-rate against Davinci-003 of 95.57% on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmark, ranking as TOP-1 on AlpacaEval. It was the FIRST model surpassing GPT-4 on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Also note its winrate v.s. GPT-4 is 60.61. - 🔍 [Sep, 2023] RLHF plays crucial role in the strong performance of Xwin-LM-V0.1 release! - 💥 [Sep, 2023] We released [Xwin-LM-13B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1), which has achieved 91.76% win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as top-1 among all 13B models. - 💥 [Sep, 2023] We released [Xwin-LM-7B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1), which has achieved 87.82% win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as top-1 among all 7B models. ## Model Card \| Model \| Checkpoint \| Report \| License \| \|------------\|------------\|-------------\|------------------\| \|Xwin-LM-7B-V0.1\| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1" target="_blank">HF Link</a> \| 📃Coming soon (Stay tuned) \| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License\| \|Xwin-LM-13B-V0.1\| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1" target="_blank">HF Link</a> \| \| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License\| \|Xwin-LM-70B-V0.1\| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1" target="_blank">HF Link</a> \| \| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License\| ## Benchmarks ### Xwin-LM performance on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). The table below displays the performance of Xwin-LM on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), where evaluates its win-rate against Text-Davinci-003 across 805 questions. To provide a comprehensive evaluation, we present, for the first time, the win-rate against ChatGPT and GPT-4 as well. Our Xwin-LM model family establish a new state-of-the-art performance across all metrics. Notably, Xwin-LM-70B-V0.1 has eclipsed GPT-4 for the first time, achieving an impressive win-rate of 95.57% to Text-Davinci-003 and 60.61% to GPT-4. \| Model \| AlpacaEval (winrate %) \| AlpacaEval (winrate %) \|AlpacaEval (winrate %) \| \|----------------------------------\|------------\|----------\|-------------\| \| \| v.s. Text-Davinci-003 \| v.s. ChatGPT \| v.s. GPT4\| \| Xwin-LM-70B-V0.1 \| 95.57 \| 87.50 \| 60.61 \| \| GPT-4 \| 95.28 \| 84.66 \| 50.00 \| \| WizardLM-70B-V1.0 \| 92.91 \| 80.19 \| 46.70 \| \| Llama-2-70B-Chat \| 92.66 \| 81.97 \| 51.19 \| \| Xwin-LM-13B-V0.1 \| 91.76 \| 81.79 \| 55.30 \| \| ChatGPT \| 89.37 \| 50.00 \| 16.60 \| \| WizardLM-13B-V1.2 \| 89.17 \| 75.75 \| 41.91 \| \| Xwin-LM-7B-V0.1 \| 87.35 \| 76.40 \| 47.57 \| \| Llama-2-13B-Chat \| 81.09 \| 64.22 \| 30.92 \| ### Case study on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) \| Prompts \| GTP4 response \| Xwin-LM response \| \|----------------\|------------\|--------\| \|I've put a plate on top of an apple, and take the plate from kitchen to dinning room. Where is the apple now\|The apple is now in the dining room, as it was underneath the plate when you moved the plate from the kitchen to the dining room.\|The apple is still in the kitchen, as you have only moved the plate. The apple is under the plate, so if you want to bring the apple to the dining room, you should either move the apple directly or put the apple on the plate and then move the plate to the dining room.\| \| Answer the following question.<br> How do you say "good evening" in French. \| In French, "good evening" is said as "bonsoir." \| In French, "good evening" is translated to "bonsoir." This greeting is used in the evening and nighttime hours, typically after 6 p.m. It is a combination of "bon," which means "good," and "soir," which means "evening." To pronounce it, say "bone-swahr." \| ### Xwin-LM performance on NLP foundation tasks. The following table provides a comparison of Xwin-LMs with other LLMs on NLP foundation tasks in [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). \| Model \| MMLU 5-shot \| ARC 25-shot \| TruthfulQA 0-shot \| HellaSwag 10-shot \| Average \| \|------------------\|-------------\|-------------\|-------------------\|-------------------\|------------\| \| Text-davinci-003 \| 56.9 \| 85.2 \| 59.3 \| 82.2 \| 70.9 \| \|Vicuna-13b 1.1 \| 51.3 \| 53.0 \| 51.8 \| 80.1 \| 59.1 \| \|Guanaco 30B \| 57.6 \| 63.7 \| 50.7 \| 85.1 \| 64.3 \| \| WizardLM-7B 1.0 \| 42.7 \| 51.6 \| 44.7 \| 77.7 \| 54.2 \| \| WizardLM-13B 1.0 \| 52.3 \| 57.2 \| 50.5 \| 81.0 \| 60.2 \| \| WizardLM-30B 1.0 \| 58.8 \| 62.5 \| 52.4 \| 83.3 \| 64.2\| \| Llama-2-7B-Chat \| 48.3 \| 52.9 \| 45.6 \| 78.6 \| 56.4 \| \| Llama-2-13B-Chat \| 54.6 \| 59.0 \| 44.1 \| 81.9 \| 59.9 \| \| Llama-2-70B-Chat \| 63.9 \| 64.6 \| 52.8 \| 85.9 \| 66.8 \| \| Xwin-LM-7B-V0.1 \| 49.7 \| 56.2 \| 48.1 \| 79.5 \| 58.4 \| \| Xwin-LM-13B-V0.1 \| 56.6 \| 62.4 \| 45.5 \| 83.0 \| 61.9 \| \| Xwin-LM-70B-V0.1 \| 69.6 \| 70.5 \| 60.1 \| 87.1 \| 71.8 \| ## Inference ### Conversation templates To obtain desired results, please strictly follow the conversation templates when utilizing our model for inference. Our model adopts the prompt format established by [Vicuna](https://github.com/lm-sys/FastChat) and is equipped to support multi-turn conversations. ``` A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Hi! ASSISTANT: Hello.</s>USER: Who are you? ASSISTANT: I am Xwin-LM.</s>...... ``` ### HuggingFace Example ```python from transformers import AutoTokenizer, AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1") tokenizer = AutoTokenizer.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1") ( prompt := "A chat between a curious user and an artificial intelligence assistant. " "The assistant gives helpful, detailed, and polite answers to the user's questions. " "USER: Hello, can you help me? " "ASSISTANT:" ) inputs = tokenizer(prompt, return_tensors="pt") samples = model.generate(**inputs, max_new_tokens=4096, temperature=0.7) output = tokenizer.decode(samples[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True) print(output) # Of course! I'm here to help. Please feel free to ask your question or describe the issue you're having, and I'll do my best to assist you. ``` ### vllm Example Because Xwin-LM is based on Llama2, it also offers support for rapid inference using [vllm](https://github.com/vllm-project/vllm). Please refer to [vllm](https://github.com/vllm-project/vllm) for detailed installation instructions. ```python from vllm import LLM, SamplingParams ( prompt := "A chat between a curious user and an artificial intelligence assistant. " "The assistant gives helpful, detailed, and polite answers to the user's questions. " "USER: Hello, can you help me? " "ASSISTANT:" ) sampling_params = SamplingParams(temperature=0.7, max_tokens=4096) llm = LLM(model="Xwin-LM/Xwin-LM-7B-V0.1") outputs = llm.generate([prompt,], sampling_params) for output in outputs: prompt = output.prompt generated_text = output.outputs[0].text print(generated_text) ``` ## TODO - [ ] Release the source code - [ ] Release more capabilities, such as math, reasoning, and etc. ## Citation Please consider citing our work if you use the data or code in this repo. ``` @software{xwin-lm, title = {Xwin-LM}, author = {Xwin-LM Team}, url = {https://github.com/Xwin-LM/Xwin-LM}, version = {pre-release}, year = {2023}, month = {9}, } ``` ## Acknowledgements Thanks to [Llama 2](https://ai.meta.com/llama/), [FastChat](https://github.com/lm-sys/FastChat), [AlpacaFarm](https://github.com/tatsu-lab/alpaca_farm), and [vllm](https://github.com/vllm-project/vllm).
perfectlyunreal/lora	perfectlyunreal	2023-09-30T04:38:57Z	0	0	null	[ "license:other", "region:us" ]	null	2023-09-29T02:53:53Z	--- license: other license_name: unknow license_link: LICENSE ---
ajayksingh/opt-125m-lora	ajayksingh	2023-09-30T03:42:08Z	3	0	peft	[ "peft", "region:us" ]	null	2023-09-29T20:04:13Z	--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.6.0.dev0
JunF1122/gpt2_finetuned_new_10000recipe_chicken	JunF1122	2023-09-30T03:40:17Z	146	0	transformers	[ "transformers", "pytorch", "tensorboard", "gpt2", "text-generation", "generated_from_trainer", "base_model:openai-community/gpt2", "base_model:finetune:openai-community/gpt2", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-09-28T12:40:46Z	--- license: mit base_model: gpt2 tags: - generated_from_trainer model-index: - name: gpt2_finetuned_new_10000recipe_chicken 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_finetuned_new_10000recipe_chicken This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) using 10,000 chicken recipes with no_duplicated titles extracted from nlg dataset. It achieves the following results on the evaluation set: - Loss: 1.6760 ## Model description This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) using 10,000 chicken recipes extracted from nlg dataset. <br> It achieves the following results on the evaluation set: - Loss: 1.43510 ## Intended uses & limitations The use is for personal and educational purposes. ## Training and evaluation data The model uses 10043 recipes for its training data and 100 recipes for its evaluation data. ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - 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 - lr_scheduler_warmup_steps: 500 - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 1.9414 \| 1.0 \| 2544 \| 1.8198 \| \| 1.6154 \| 2.0 \| 5088 \| 1.7056 \| \| 1.4351 \| 3.0 \| 7632 \| 1.6760 \| ### Framework versions - Transformers 4.31.0 - Pytorch 2.0.1+cpu - Datasets 2.14.4 - Tokenizers 0.11.0 ### Reference @inproceedings{bien-etal-2020-recipenlg, title = "{R}ecipe{NLG}: A Cooking Recipes Dataset for Semi-Structured Text Generation", author = "Bie{\'n}, Micha{\l} and Gilski, Micha{\l} and Maciejewska, Martyna and Taisner, Wojciech and Wisniewski, Dawid and Lawrynowicz, Agnieszka", booktitle = "Proceedings of the 13th International Conference on Natural Language Generation", month = dec, year = "2020", address = "Dublin, Ireland", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/2020.inlg-1.4", pages = "22--28", }
Alimuddin/amazon_fish_classification	Alimuddin	2023-09-30T02:56:20Z	141	1	transformers	[ "transformers", "pytorch", "convnext", "image-classification", "generated_from_trainer", "dataset:amazonian_fish_classifier_data", "base_model:facebook/convnext-large-224-22k-1k", "base_model:finetune:facebook/convnext-large-224-22k-1k", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-09-17T14:27:15Z	--- license: apache-2.0 base_model: facebook/convnext-large-224-22k-1k tags: - generated_from_trainer datasets: - amazonian_fish_classifier_data metrics: - accuracy model-index: - name: image_classification results: - task: name: Image Classification type: image-classification dataset: name: amazonian_fish_classifier_data type: amazonian_fish_classifier_data config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.9332247557003257 --- <!-- 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. --> # image_classification This model is a fine-tuned version of [facebook/convnext-large-224-22k-1k](https://huggingface.co/facebook/convnext-large-224-22k-1k) on the amazonian_fish_classifier_data dataset. It achieves the following results on the evaluation set: - Loss: 0.2562 - Accuracy: 0.9332 ## 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: 7e-05 - train_batch_size: 17 - eval_batch_size: 17 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| No log \| 1.0 \| 145 \| 0.6864 \| 0.8420 \| \| No log \| 2.0 \| 290 \| 0.5780 \| 0.8306 \| \| No log \| 3.0 \| 435 \| 0.4466 \| 0.8860 \| \| 0.7812 \| 4.0 \| 580 \| 0.3810 \| 0.8958 \| \| 0.7812 \| 5.0 \| 725 \| 0.4124 \| 0.8860 \| \| 0.7812 \| 6.0 \| 870 \| 0.3617 \| 0.9007 \| \| 0.3315 \| 7.0 \| 1015 \| 0.3397 \| 0.8990 \| \| 0.3315 \| 8.0 \| 1160 \| 0.3746 \| 0.9055 \| \| 0.3315 \| 9.0 \| 1305 \| 0.3379 \| 0.9023 \| \| 0.3315 \| 10.0 \| 1450 \| 0.3825 \| 0.8958 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3
Heralax/MythoMakise-13b	Heralax	2023-09-30T02:42:11Z	0	1	null	[ "license:llama2", "region:us" ]	null	2023-09-01T21:24:33Z	--- license: llama2 --- A refined version of MythoMaxKurisu-13b. All the errors in the training code are gone, and the model now understands actions. Training on the dataset no longer has the tradeoff of making the model stupider, while at the same time improving its tone of voice. This is a model specialized in roleplaying as a single character: Makise Kurisu from Steins;Gate. However, in testing the model has shown it's capable of roleplaying as other characters too. Example output (1 epoch): ![](mythomakise_v2.png) Note that, unlike the previous model, this output did not take many tries to get. You have to dance around this model much less. Quant (1 epoch only right now): https://huggingface.co/Heralax/MythoMakise-13b-quants/tree/main Adapters: https://huggingface.co/Heralax/MythoMakise-13b-adapters/tree/main
roa7n/gpt2-human_nontata_promoters-randomized_11_layers_0.0003_lr_2_e	roa7n	2023-09-30T02:26:18Z	2	0	peft	[ "peft", "region:us" ]	null	2023-09-30T02:26:15Z	--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
aigrils2/primitive0	aigrils2	2023-09-30T02:08:46Z	2	0	diffusers	[ "diffusers", "text-to-image", "stable-diffusion", "lora", "base_model:aigrils2/majicv6", "base_model:adapter:aigrils2/majicv6", "region:us" ]	text-to-image	2023-09-02T10:03:40Z	--- base_model: aigrils2/majicv6 tags: - text-to-image - stable-diffusion - lora - diffusers pipeline_tag: text-to-image ---
johaanm/test-grader-alpha-V1.1	johaanm	2023-09-30T02:06:14Z	0	0	peft	[ "peft", "region:us" ]	null	2023-09-30T02:06:09Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.4.0 - PEFT 0.4.0
masuidrive/openai-whisper-large-v2-LORA-conoha	masuidrive	2023-09-30T01:47:01Z	3	0	peft	[ "peft", "region:us" ]	null	2023-09-30T01:45:10Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.4.0
Rexe/Mistral-7B-Instruct-v0.1	Rexe	2023-09-30T01:35:55Z	1	0	peft	[ "peft", "region:us" ]	null	2023-09-28T22:34:59Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.6.0.dev0
12345testing/echo_model	12345testing	2023-09-30T01:26:41Z	3	0	diffusers	[ "diffusers", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "lora", "base_model:runwayml/stable-diffusion-v1-5", "base_model:adapter:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "region:us" ]	text-to-image	2023-09-30T01:18:22Z	--- license: creativeml-openrail-m base_model: runwayml/stable-diffusion-v1-5 instance_prompt: a photo of echo amazon tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - lora inference: true --- # LoRA DreamBooth - 12345testing/echo_model These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of echo amazon using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. ![img_0](./image_0.png) ![img_1](./image_1.png) ![img_2](./image_2.png) ![img_3](./image_3.png) LoRA for the text encoder was enabled: True.
roa7n/gpt2-human_nontata_promoters-randomized_10_layers_3e-05_lr_8_e	roa7n	2023-09-30T01:21:01Z	0	0	peft	[ "peft", "region:us" ]	null	2023-09-30T01:20:58Z	--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
mazayo/ppo-SnowballTarget	mazayo	2023-09-30T01:17:33Z	9	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget", "region:us" ]	reinforcement-learning	2023-09-30T01:17:30Z	--- library_name: ml-agents tags: - SnowballTarget - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SnowballTarget --- # ppo Agent playing SnowballTarget This is a trained model of a ppo agent playing SnowballTarget using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: mazayo/ppo-SnowballTarget 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
gchabcou/my_awesome_food_model	gchabcou	2023-09-30T01:01:58Z	5	0	transformers	[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "dataset:food101", "base_model:google/vit-base-patch16-224-in21k", "base_model:finetune:google/vit-base-patch16-224-in21k", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-09-29T04:54:56Z	--- license: apache-2.0 base_model: google/vit-base-patch16-224-in21k tags: - generated_from_trainer datasets: - food101 metrics: - accuracy model-index: - name: my_awesome_food_model results: - task: name: Image Classification type: image-classification dataset: name: food101 type: food101 config: default split: train[:5000] args: default metrics: - name: Accuracy type: accuracy value: 0.9 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # my_awesome_food_model This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the food101 dataset. It achieves the following results on the evaluation set: - Loss: 0.8834 - Accuracy: 0.9 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 3.6073 \| 0.99 \| 62 \| 3.3725 \| 0.818 \| \| 2.2956 \| 2.0 \| 125 \| 2.1579 \| 0.854 \| \| 1.7042 \| 2.99 \| 187 \| 1.6201 \| 0.887 \| \| 1.3278 \| 4.0 \| 250 \| 1.3513 \| 0.89 \| \| 1.1314 \| 4.99 \| 312 \| 1.1549 \| 0.908 \| \| 1.007 \| 6.0 \| 375 \| 1.0737 \| 0.889 \| \| 0.905 \| 6.99 \| 437 \| 0.9600 \| 0.906 \| \| 0.8227 \| 8.0 \| 500 \| 0.9113 \| 0.912 \| \| 0.7948 \| 8.99 \| 562 \| 0.8908 \| 0.909 \| \| 0.7598 \| 9.92 \| 620 \| 0.8834 \| 0.9 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu117 - Datasets 2.14.5 - Tokenizers 0.13.3
Keenan5755/pg-CartPole-v1	Keenan5755	2023-09-30T00:48:11Z	0	0	null	[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2023-09-30T00:48:00Z	--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: pg-CartPole-v1 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 500.00 +/- 0.00 name: mean_reward verified: false --- # Reinforce Agent playing CartPole-v1 This is a trained model of a Reinforce agent playing CartPole-v1 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
actionpace/Athena-v1	actionpace	2023-09-30T00:39:15Z	0	0	null	[ "gguf", "en", "license:other", "endpoints_compatible", "region:us" ]	null	2023-09-30T00:32:10Z	--- license: other language: - en --- Some of my own quants: * Athena-v1_Q5_K_M.gguf Source: [IkariDev](https://huggingface.co/IkariDev) Source Model: [Athena-v1](https://huggingface.co/IkariDev/Athena-v1) Source models for IkariDev/Athena-v1 (Merge) - [jondurbin/airoboros-l2-13b-2.1](https://huggingface.co/jondurbin/airoboros-l2-13b-2.1) - [Gryphe/MythoMax-L2-13b](https://huggingface.co/Gryphe/MythoMax-L2-13b) ([Ref](https://huggingface.co/actionpace/MythoMax-L2-13b)) - [totally-not-an-llm/PuddleJumper-13b](https://huggingface.co/totally-not-an-llm/PuddleJumper-13b) - [The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16](https://huggingface.co/The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16) Models utilizing IkariDev/Athena-v1 - [Undi95/UndiMix-v2-13b](https://huggingface.co/Undi95/UndiMix-v2-13b) ([Ref](https://huggingface.co/actionpace/UndiMix-v2-13b)) - [Undi95/UndiMix-v3-13B](https://huggingface.co/Undi95/UndiMix-v3-13B) ([Ref](https://huggingface.co/actionpace/UndiMix-v3-13B)) (Merge) - [Undi95/UndiMix-v4-13B](https://huggingface.co/Undi95/UndiMix-v4-13B) ([Ref](https://huggingface.co/actionpace/UndiMix-v4-13B)) (Merge)
feelinrealcute/sd-webui-defaultsettingsarchive	feelinrealcute	2023-09-30T00:34:39Z	58	0	transformers	[ "transformers", "endpoints_compatible", "region:us" ]	null	2023-03-12T19:59:16Z	These are files that got deleted off Kaggle probably because of me. Oops.
taldarim/setfit-diffable-head	taldarim	2023-09-30T00:28:10Z	3	0	sentence-transformers	[ "sentence-transformers", "pytorch", "mpnet", "setfit", "text-classification", "arxiv:2209.11055", "license:apache-2.0", "region:us" ]	text-classification	2023-09-30T00:27:57Z	--- license: apache-2.0 tags: - setfit - sentence-transformers - text-classification pipeline_tag: text-classification --- # taldarim/setfit-diffable-head 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("taldarim/setfit-diffable-head") # Run inference preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"]) ``` ## BibTeX entry and citation info ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ```
AmelieSchreiber/esm2_t6_8m_qlora_binding_sites_v1	AmelieSchreiber	2023-09-30T00:26:49Z	0	0	null	[ "license:mit", "region:us" ]	null	2023-09-29T20:01:38Z	--- license: mit --- # ESM-2 QLoRA for Binding Site Prediction In this model, we wanted to see how the performance metrics were effected by adapting additional weight matrices with QLoRA. This was shown to be the most important hyperparameter for improvement in performance metrics by far, whereas hyperparameters such as rank and scaling factor were shown to be negligible in importance, with lower rank being just as good as higher rank. So, we decided to test the difference between simply using the query, key, and value weight matrix adapters to using adapters for all possible weight matrices. The comparison for the first epoch can be seen below. Note the minor performance improvements for the model using every possible weight matrix (this model). ### This model ```python Test (epoch 1): 'eval_loss': 0.41490185260772705, 'eval_accuracy': 0.8625347674451358, 'eval_precision': 0.11370668247419904, 'eval_recall': 0.7800926533683039, 'eval_f1': 0.19848246486644372, 'eval_auc': 0.8222331548742136, 'eval_mcc': 0.2639007297474409} ``` ### Query, Key, Value only Model: ```python Test (epoch 1): {'eval_loss': 0.3398605287075043, 'eval_accuracy': 0.8557050926566265, 'eval_precision': 0.10792930844408741, 'eval_recall': 0.7726298654561553, 'eval_f1': 0.18940102955847055, 'eval_auc': 0.8150939843855006, 'eval_mcc': 0.2535956911257298} ``` The metrics on the datasets [mentioned here](https://github.com/hamzagamouh/pt-lm-gnn) can be [found here](https://huggingface.co/AmelieSchreiber/esm2_t6_8m_qlora_binding_sites_v1/blob/main/pdb_structure_metrics.txt). ## Testing for Overfitting Notably, it appears adding in the adapters for the additional weight matrices serves as a more robust regularization technique, and that these models appear to generalize better. ### Epoch 1: ```python Train metrics: {'eval_loss': 0.35603779554367065, 'eval_accuracy': 0.8439650327744697, 'eval_precision': 0.11529132737114746, 'eval_recall': 0.9162279099673907, 'eval_f1': 0.20481078411524478, 'eval_auc': 0.8792862815250805, 'eval_mcc': 0.29286338236467047} Test metrics: {'eval_loss': 0.3942357003688812, 'eval_accuracy': 0.8246741787222583, 'eval_precision': 0.0942294455869611, 'eval_recall': 0.8169195154212542, 'eval_f1': 0.16896879944226734, 'eval_auc': 0.8208833317810486, 'eval_mcc': 0.23939865094539936} ```
actionpace/Athena-v2	actionpace	2023-09-29T23:42:38Z	0	0	null	[ "gguf", "en", "license:other", "endpoints_compatible", "region:us" ]	null	2023-09-29T23:29:51Z	--- license: other language: - en --- Some of my own quants: * Athena-v2_Q5_K_M.gguf Source: [IkariDev](https://huggingface.co/IkariDev) Source Model: [Athena-v2](https://huggingface.co/IkariDev/Athena-v2) Source models for IkariDev/Athena-v2 (Merge) - [Xwin-LM/Xwin-LM-13B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1) - [Undi95/ReMM-v2.2-L2-13B](https://huggingface.co/Undi95/ReMM-v2.2-L2-13B) - [Undi95/MLewd-L2-13B-v2-3](https://huggingface.co/Undi95/MLewd-L2-13B-v2-3) ([Ref](https://huggingface.co/actionpace/MLewd-L2-13B-v2-3)) - [Brouz/Slerpeno](https://huggingface.co/Brouz/Slerpeno) ([Ref](https://huggingface.co/actionpace/Slerpeno)) - [boomerchan/Magpie-13b](https://huggingface.co/boomerchan/Magpie-13b) Models utilizing IkariDev/Athena-v2 - [IkariDev/Athena-v3](https://huggingface.co/IkariDev/Athena-v3) ([Ref](https://huggingface.co/actionpace/Athena-v3)) (Merge)
HazemHM/ppo-Pyramids	HazemHM	2023-09-29T23:35:34Z	0	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids", "region:us" ]	reinforcement-learning	2023-09-29T23:35:30Z	--- library_name: ml-agents tags: - Pyramids - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Pyramids --- # ppo Agent playing Pyramids This is a trained model of a ppo agent playing Pyramids using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: HazemHM/ppo-Pyramids 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
roa7n/gpt2-human_nontata_promoters-randomized_10_layers_0.0003_lr_8_e	roa7n	2023-09-29T23:32:00Z	0	0	peft	[ "peft", "region:us" ]	null	2023-09-29T23:31:58Z	--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
Anastasiaps/poca-SoccerTwos	Anastasiaps	2023-09-29T23:22:21Z	1	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "SoccerTwos", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SoccerTwos", "region:us" ]	reinforcement-learning	2023-09-29T21:53:41Z	--- 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: Anastasiaps/poca-SoccerTwos 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
taldarim/setfit-layers-added	taldarim	2023-09-29T23:13:55Z	3	0	sentence-transformers	[ "sentence-transformers", "pytorch", "mpnet", "setfit", "text-classification", "arxiv:2209.11055", "license:apache-2.0", "region:us" ]	text-classification	2023-09-29T23:13:43Z	--- license: apache-2.0 tags: - setfit - sentence-transformers - text-classification pipeline_tag: text-classification --- # taldarim/setfit-layers-added 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("taldarim/setfit-layers-added") # Run inference preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"]) ``` ## BibTeX entry and citation info ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ```
Carlos31/platzi-distilroberta-base-mrpc-glue-Carlos-Moreno	Carlos31	2023-09-29T23:05:35Z	117	0	transformers	[ "transformers", "pytorch", "roberta", "text-classification", "generated_from_trainer", "dataset:glue", "base_model:distilbert/distilroberta-base", "base_model:finetune:distilbert/distilroberta-base", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-09-29T20:21:37Z	--- license: apache-2.0 base_model: distilroberta-base tags: - text-classification - generated_from_trainer datasets: - glue metrics: - accuracy - f1 widget: - text: ["Yucaipa owned Dominick 's before selling the chain to Safeway in 1998 for $ 2.5 billion.", "Yucaipa bought Dominick's in 1995 for $ 693 million and sold it to Safeway for $ 1.8 billion in 1998."] example_title: Not Equivalent - text: ["Revenue in the first quarter of the year dropped 15 percent from the same period a year earlier.", "With the scandal hanging over Stewart's company revenue the first quarter of the year dropped 15 percent from the same period a year earlier."] example_title: Equivalent model-index: - name: platzi-distilroberta-base-mrpc-glue-Carlos-Moreno results: - task: name: Text Classification type: text-classification dataset: name: glue type: glue config: mrpc split: validation args: mrpc metrics: - name: Accuracy type: accuracy value: 0.7794117647058824 - name: F1 type: f1 value: 0.8529411764705881 --- <!-- 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-distilroberta-base-mrpc-glue-Carlos-Moreno This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the glue and the mrpc datasets. It achieves the following results on the evaluation set: - Loss: 0.6319 - Accuracy: 0.7794 - F1: 0.8529 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| F1 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:------:\| \| 0.5508 \| 1.09 \| 500 \| 0.6319 \| 0.7794 \| 0.8529 \| \| 0.3888 \| 2.18 \| 1000 \| 0.8226 \| 0.8211 \| 0.8765 \| ### Framework versions - Transformers 4.33.1 - Pytorch 2.0.1+cpu - Datasets 2.14.5 - Tokenizers 0.13.3
HazemHM/ppo-SnowballTarget2	HazemHM	2023-09-29T22:55:21Z	0	0	ml-agents	[ "ml-agents", "SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget", "region:us" ]	reinforcement-learning	2023-09-29T22:42:49Z	--- library_name: ml-agents tags: - SnowballTarget - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SnowballTarget --- # ppo Agent playing SnowballTarget This is a trained model of a ppo agent playing SnowballTarget using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: HazemHM/ppo-SnowballTarget2 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K	laion	2023-09-29T22:43:14Z	80,206	3	open_clip	[ "open_clip", "safetensors", "zero-shot-image-classification", "dataset:mlfoundations/datacomp_pools", "arxiv:2304.14108", "license:mit", "region:us" ]	zero-shot-image-classification	2023-09-29T22:27:30Z	--- license: mit widget: - src: >- https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png candidate_labels: playing music, playing sports example_title: Cat & Dog library_name: open_clip datasets: - mlfoundations/datacomp_pools pipeline_tag: zero-shot-image-classification --- # Model card for CLIP ViT-B-32 trained DataComp-1B # Table of Contents 1. [Model Details](#model-details) 2. [Uses](#uses) 3. [Training Details](#training-details) 4. [Evaluation](#evaluation) 5. [Acknowledgements](#acknowledgements) 6. [Citation](#citation) 7. [How To Get Started With the Model](#how-to-get-started-with-the-model) # Model Details ## Model Description A CLIP ViT-B/32 model trained with the DataComp-1B (https://github.com/mlfoundations/datacomp) using OpenCLIP (https://github.com/mlfoundations/open_clip). Model training done on the [stability.ai](https://stability.ai/) cluster. # Uses As per the original [OpenAI CLIP model card](https://github.com/openai/CLIP/blob/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1/model-card.md), this model is intended as a research output for research communities. We hope that this model will enable researchers to better understand and explore zero-shot, arbitrary image classification. We also hope it can be used for interdisciplinary studies of the potential impact of such model. The OpenAI CLIP paper includes a discussion of potential downstream impacts to provide an example for this sort of analysis. Additionally, the DataComp paper (https://arxiv.org/abs/2304.14108) include additional discussion as it relates specifically to the training dataset. ## Direct Use Zero-shot image classification, image and text retrieval, among others. ## Downstream Use Image classification and other image task fine-tuning, linear probe image classification, image generation guiding and conditioning, among others. ## Out-of-Scope Use As per the OpenAI models, Any deployed use case of the model - whether commercial or not - is currently out of scope. Non-deployed use cases such as image search in a constrained environment, are also not recommended unless there is thorough in-domain testing of the model with a specific, fixed class taxonomy. This is because our safety assessment demonstrated a high need for task specific testing especially given the variability of CLIP’s performance with different class taxonomies. This makes untested and unconstrained deployment of the model in any use case currently potentially harmful. Certain use cases which would fall under the domain of surveillance and facial recognition are always out-of-scope regardless of performance of the model. This is because the use of artificial intelligence for tasks such as these can be premature currently given the lack of testing norms and checks to ensure its fair use. # Training Details ## Training Data This model was trained with the 1.4 Billion samples of the DataComp-1B dataset (https://arxiv.org/abs/2304.14108). IMPORTANT NOTE: The motivation behind dataset creation is to democratize research and experimentation around large-scale multi-modal model training and handling of uncurated, large-scale datasets crawled from publically available internet. Our recommendation is therefore to use the dataset for research purposes. Be aware that this large-scale dataset is uncurated. Keep in mind that the uncurated nature of the dataset means that collected links may lead to strongly discomforting and disturbing content for a human viewer. Therefore, please use the demo links with caution and at your own risk. It is possible to extract a “safe” subset by filtering out samples based on the safety tags (using a customized trained NSFW classifier that we built). While this strongly reduces the chance for encountering potentially harmful content when viewing, we cannot entirely exclude the possibility for harmful content being still present in safe mode, so that the warning holds also there. We think that providing the dataset openly to broad research and other interested communities will allow for transparent investigation of benefits that come along with training large-scale models as well as pitfalls and dangers that may stay unreported or unnoticed when working with closed large datasets that remain restricted to a small community. Providing our dataset openly, we however do not recommend using it for creating ready-to-go industrial products, as the basic research about general properties and safety of such large-scale models, which we would like to encourage with this release, is still in progress. ## Training Procedure Please see https://arxiv.org/abs/2304.14108. # Evaluation Evaluation done on 38 datasets, using the [DataComp repo](https://github.com/mlfoundations/datacomp) and the [LAION CLIP Benchmark](https://github.com/LAION-AI/CLIP_benchmark). ## Testing Data, Factors & Metrics ### Testing Data The testing is performed on a suite of 38 datasets. See our paper for more details (https://arxiv.org/abs/2304.14108). ## Results The model achieves a 72.7% zero-shot top-1 accuracy on ImageNet-1k. See our paper for more details and results (https://arxiv.org/abs/2304.14108). # Acknowledgements Acknowledging [stability.ai](https://stability.ai/) for the compute used to train this model. # Citation BibTeX: DataComp ```bibtex @article{datacomp, title={DataComp: In search of the next generation of multimodal datasets}, author={Samir Yitzhak Gadre, Gabriel Ilharco, Alex Fang, Jonathan Hayase, Georgios Smyrnis, Thao Nguyen, Ryan Marten, Mitchell Wortsman, Dhruba Ghosh, Jieyu Zhang, Eyal Orgad, Rahim Entezari, Giannis Daras, Sarah Pratt, Vivek Ramanujan, Yonatan Bitton, Kalyani Marathe, Stephen Mussmann, Richard Vencu, Mehdi Cherti, Ranjay Krishna, Pang Wei Koh, Olga Saukh, Alexander Ratner, Shuran Song, Hannaneh Hajishirzi, Ali Farhadi, Romain Beaumont, Sewoong Oh, Alex Dimakis, Jenia Jitsev, Yair Carmon, Vaishaal Shankar, Ludwig Schmidt}, journal={arXiv preprint arXiv:2304.14108}, year={2023} } ``` OpenAI CLIP paper ``` @inproceedings{Radford2021LearningTV, title={Learning Transferable Visual Models From Natural Language Supervision}, author={Alec Radford and Jong Wook Kim and Chris Hallacy and A. Ramesh and Gabriel Goh and Sandhini Agarwal and Girish Sastry and Amanda Askell and Pamela Mishkin and Jack Clark and Gretchen Krueger and Ilya Sutskever}, booktitle={ICML}, year={2021} } ``` OpenCLIP software ``` @software{ilharco_gabriel_2021_5143773, author = {Ilharco, Gabriel and Wortsman, Mitchell and Wightman, Ross and Gordon, Cade and Carlini, Nicholas and Taori, Rohan and Dave, Achal and Shankar, Vaishaal and Namkoong, Hongseok and Miller, John and Hajishirzi, Hannaneh and Farhadi, Ali and Schmidt, Ludwig}, title = {OpenCLIP}, month = jul, year = 2021, note = {If you use this software, please cite it as below.}, publisher = {Zenodo}, version = {0.1}, doi = {10.5281/zenodo.5143773}, url = {https://doi.org/10.5281/zenodo.5143773} } ``` # How to Get Started with the Model See https://github.com/mlfoundations/open_clip
laion/CLIP-ViT-B-16-DataComp.XL-s13B-b90K	laion	2023-09-29T22:41:47Z	125,612	7	open_clip	[ "open_clip", "zero-shot-image-classification", "dataset:mlfoundations/datacomp_pools", "arxiv:2304.14108", "license:mit", "region:us" ]	zero-shot-image-classification	2023-05-15T19:27:18Z	--- license: mit widget: - src: >- https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png candidate_labels: playing music, playing sports example_title: Cat & Dog library_name: open_clip datasets: - mlfoundations/datacomp_pools pipeline_tag: zero-shot-image-classification --- # Model card for CLIP ViT-B-16 trained DataComp-1B # Table of Contents 1. [Model Details](#model-details) 2. [Uses](#uses) 3. [Training Details](#training-details) 4. [Evaluation](#evaluation) 5. [Acknowledgements](#acknowledgements) 6. [Citation](#citation) 7. [How To Get Started With the Model](#how-to-get-started-with-the-model) # Model Details ## Model Description A CLIP ViT-B/16 model trained with the DataComp-1B (https://github.com/mlfoundations/datacomp) using OpenCLIP (https://github.com/mlfoundations/open_clip). Model training done on the [stability.ai](https://stability.ai/) cluster. # Uses As per the original [OpenAI CLIP model card](https://github.com/openai/CLIP/blob/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1/model-card.md), this model is intended as a research output for research communities. We hope that this model will enable researchers to better understand and explore zero-shot, arbitrary image classification. We also hope it can be used for interdisciplinary studies of the potential impact of such model. The OpenAI CLIP paper includes a discussion of potential downstream impacts to provide an example for this sort of analysis. Additionally, the DataComp paper (https://arxiv.org/abs/2304.14108) include additional discussion as it relates specifically to the training dataset. ## Direct Use Zero-shot image classification, image and text retrieval, among others. ## Downstream Use Image classification and other image task fine-tuning, linear probe image classification, image generation guiding and conditioning, among others. ## Out-of-Scope Use As per the OpenAI models, Any deployed use case of the model - whether commercial or not - is currently out of scope. Non-deployed use cases such as image search in a constrained environment, are also not recommended unless there is thorough in-domain testing of the model with a specific, fixed class taxonomy. This is because our safety assessment demonstrated a high need for task specific testing especially given the variability of CLIP’s performance with different class taxonomies. This makes untested and unconstrained deployment of the model in any use case currently potentially harmful. Certain use cases which would fall under the domain of surveillance and facial recognition are always out-of-scope regardless of performance of the model. This is because the use of artificial intelligence for tasks such as these can be premature currently given the lack of testing norms and checks to ensure its fair use. # Training Details ## Training Data This model was trained with the 1.4 Billion samples of the DataComp-1B dataset (https://arxiv.org/abs/2304.14108). IMPORTANT NOTE: The motivation behind dataset creation is to democratize research and experimentation around large-scale multi-modal model training and handling of uncurated, large-scale datasets crawled from publically available internet. Our recommendation is therefore to use the dataset for research purposes. Be aware that this large-scale dataset is uncurated. Keep in mind that the uncurated nature of the dataset means that collected links may lead to strongly discomforting and disturbing content for a human viewer. Therefore, please use the demo links with caution and at your own risk. It is possible to extract a “safe” subset by filtering out samples based on the safety tags (using a customized trained NSFW classifier that we built). While this strongly reduces the chance for encountering potentially harmful content when viewing, we cannot entirely exclude the possibility for harmful content being still present in safe mode, so that the warning holds also there. We think that providing the dataset openly to broad research and other interested communities will allow for transparent investigation of benefits that come along with training large-scale models as well as pitfalls and dangers that may stay unreported or unnoticed when working with closed large datasets that remain restricted to a small community. Providing our dataset openly, we however do not recommend using it for creating ready-to-go industrial products, as the basic research about general properties and safety of such large-scale models, which we would like to encourage with this release, is still in progress. ## Training Procedure Please see https://arxiv.org/abs/2304.14108. # Evaluation Evaluation done on 38 datasets, using the [DataComp repo](https://github.com/mlfoundations/datacomp) and the [LAION CLIP Benchmark](https://github.com/LAION-AI/CLIP_benchmark). ## Testing Data, Factors & Metrics ### Testing Data The testing is performed on a suite of 38 datasets. See our paper for more details (https://arxiv.org/abs/2304.14108). ## Results The model achieves a 73.5% zero-shot top-1 accuracy on ImageNet-1k. See our paper for more details and results (https://arxiv.org/abs/2304.14108). # Acknowledgements Acknowledging [stability.ai](https://stability.ai/) for the compute used to train this model. # Citation BibTeX: DataComp ```bibtex @article{datacomp, title={DataComp: In search of the next generation of multimodal datasets}, author={Samir Yitzhak Gadre, Gabriel Ilharco, Alex Fang, Jonathan Hayase, Georgios Smyrnis, Thao Nguyen, Ryan Marten, Mitchell Wortsman, Dhruba Ghosh, Jieyu Zhang, Eyal Orgad, Rahim Entezari, Giannis Daras, Sarah Pratt, Vivek Ramanujan, Yonatan Bitton, Kalyani Marathe, Stephen Mussmann, Richard Vencu, Mehdi Cherti, Ranjay Krishna, Pang Wei Koh, Olga Saukh, Alexander Ratner, Shuran Song, Hannaneh Hajishirzi, Ali Farhadi, Romain Beaumont, Sewoong Oh, Alex Dimakis, Jenia Jitsev, Yair Carmon, Vaishaal Shankar, Ludwig Schmidt}, journal={arXiv preprint arXiv:2304.14108}, year={2023} } ``` OpenAI CLIP paper ``` @inproceedings{Radford2021LearningTV, title={Learning Transferable Visual Models From Natural Language Supervision}, author={Alec Radford and Jong Wook Kim and Chris Hallacy and A. Ramesh and Gabriel Goh and Sandhini Agarwal and Girish Sastry and Amanda Askell and Pamela Mishkin and Jack Clark and Gretchen Krueger and Ilya Sutskever}, booktitle={ICML}, year={2021} } ``` OpenCLIP software ``` @software{ilharco_gabriel_2021_5143773, author = {Ilharco, Gabriel and Wortsman, Mitchell and Wightman, Ross and Gordon, Cade and Carlini, Nicholas and Taori, Rohan and Dave, Achal and Shankar, Vaishaal and Namkoong, Hongseok and Miller, John and Hajishirzi, Hannaneh and Farhadi, Ali and Schmidt, Ludwig}, title = {OpenCLIP}, month = jul, year = 2021, note = {If you use this software, please cite it as below.}, publisher = {Zenodo}, version = {0.1}, doi = {10.5281/zenodo.5143773}, url = {https://doi.org/10.5281/zenodo.5143773} } ``` # How to Get Started with the Model See https://github.com/mlfoundations/open_clip
actionpace/CalliopeDS-v2-L2-13B	actionpace	2023-09-29T22:41:03Z	0	0	null	[ "gguf", "en", "license:other", "endpoints_compatible", "region:us" ]	null	2023-09-29T22:33:16Z	--- license: other language: - en --- Some of my own quants: * CalliopeDS-v2-L2-13B_Q5_K_M.gguf Source: [Doctor-Shotgun](https://huggingface.co/Doctor-Shotgun) Source Model: [CalliopeDS-v2-L2-13B](https://huggingface.co/Doctor-Shotgun/CalliopeDS-v2-L2-13B) Source models for Doctor-Shotgun/CalliopeDS-v2-L2-13B (Merge) - [PygmalionAI/pygmalion-2-13b](https://huggingface.co/PygmalionAI/pygmalion-2-13b) ([Ref](https://huggingface.co/actionpace/pygmalion-2-13b)) - [NousResearch/Nous-Hermes-Llama2-13b](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b) ([Ref](https://huggingface.co/actionpace/Nous-Hermes-Llama2-13b)) - [Doctor-Shotgun/llama-2-supercot-lora](https://huggingface.co/Doctor-Shotgun/llama-2-supercot-lora) - [lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT](https://huggingface.co/lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT) - [Undi95/Storytelling-v2-13B-lora](https://huggingface.co/Undi95/Storytelling-v2-13B-lora)
Kapiche/all-MiniLM-L6-v2	Kapiche	2023-09-29T22:40:37Z	13	0	sentence-transformers	[ "sentence-transformers", "pytorch", "tf", "rust", "safetensors", "bert", "feature-extraction", "sentence-similarity", "en", "dataset:s2orc", "dataset:flax-sentence-embeddings/stackexchange_xml", "dataset:ms_marco", "dataset:gooaq", "dataset:yahoo_answers_topics", "dataset:code_search_net", "dataset:search_qa", "dataset:eli5", "dataset:snli", "dataset:multi_nli", "dataset:wikihow", "dataset:natural_questions", "dataset:trivia_qa", "dataset:embedding-data/sentence-compression", "dataset:embedding-data/flickr30k-captions", "dataset:embedding-data/altlex", "dataset:embedding-data/simple-wiki", "dataset:embedding-data/QQP", "dataset:embedding-data/SPECTER", "dataset:embedding-data/PAQ_pairs", "dataset:embedding-data/WikiAnswers", "arxiv:1904.06472", "arxiv:2102.07033", "arxiv:2104.08727", "arxiv:1704.05179", "arxiv:1810.09305", "license:apache-2.0", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	sentence-similarity	2023-09-29T22:24:37Z	--- pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity language: en license: apache-2.0 datasets: - s2orc - flax-sentence-embeddings/stackexchange_xml - ms_marco - gooaq - yahoo_answers_topics - code_search_net - search_qa - eli5 - snli - multi_nli - wikihow - natural_questions - trivia_qa - embedding-data/sentence-compression - embedding-data/flickr30k-captions - embedding-data/altlex - embedding-data/simple-wiki - embedding-data/QQP - embedding-data/SPECTER - embedding-data/PAQ_pairs - embedding-data/WikiAnswers --- # all-MiniLM-L6-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. ## 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('sentence-transformers/all-MiniLM-L6-v2') embeddings = model.encode(sentences) print(embeddings) ``` ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. ```python from transformers import AutoTokenizer, AutoModel import torch import torch.nn.functional as F #Mean Pooling - Take attention mask into account for correct averaging def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] #First element of model_output contains all token embeddings input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) # Sentences we want sentence embeddings for sentences = ['This is an example sentence', 'Each sentence is converted'] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/all-MiniLM-L6-v2') model = AutoModel.from_pretrained('sentence-transformers/all-MiniLM-L6-v2') # Tokenize sentences encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(*encoded_input) # Perform pooling sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']) # Normalize embeddings sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1) print("Sentence embeddings:") print(sentence_embeddings) ``` ## Evaluation Results For an automated evaluation of this model, see the Sentence Embeddings Benchmark: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/all-MiniLM-L6-v2) ------ ## Background The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised contrastive learning objective. We used the pretrained [`nreimers/MiniLM-L6-H384-uncased`](https://huggingface.co/nreimers/MiniLM-L6-H384-uncased) model and fine-tuned in on a 1B sentence pairs dataset. We use a contrastive learning objective: given a sentence from the pair, the model should predict which out of a set of randomly sampled other sentences, was actually paired with it in our dataset. We developped this model during the [Community week using JAX/Flax for NLP & CV](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104), organized by Hugging Face. We developped this model as part of the project: [Train the Best Sentence Embedding Model Ever with 1B Training Pairs](https://discuss.huggingface.co/t/train-the-best-sentence-embedding-model-ever-with-1b-training-pairs/7354). We benefited from efficient hardware infrastructure to run the project: 7 TPUs v3-8, as well as intervention from Googles Flax, JAX, and Cloud team member about efficient deep learning frameworks. ## Intended uses Our model is intented to be used as a sentence and short paragraph encoder. Given an input text, it ouptuts a vector which captures the semantic information. The sentence vector may be used for information retrieval, clustering or sentence similarity tasks. By default, input text longer than 256 word pieces is truncated. ## Training procedure ### Pre-training We use the pretrained [`nreimers/MiniLM-L6-H384-uncased`](https://huggingface.co/nreimers/MiniLM-L6-H384-uncased) model. Please refer to the model card for more detailed information about the pre-training procedure. ### Fine-tuning We fine-tune the model using a contrastive objective. Formally, we compute the cosine similarity from each possible sentence pairs from the batch. We then apply the cross entropy loss by comparing with true pairs. #### Hyper parameters We trained ou model on a TPU v3-8. We train the model during 100k steps using a batch size of 1024 (128 per TPU core). We use a learning rate warm up of 500. The sequence length was limited to 128 tokens. We used the AdamW optimizer with a 2e-5 learning rate. The full training script is accessible in this current repository: `train_script.py`. #### Training data We use the concatenation from multiple datasets to fine-tune our model. The total number of sentence pairs is above 1 billion sentences. We sampled each dataset given a weighted probability which configuration is detailed in the `data_config.json` file. \| Dataset \| Paper \| Number of training tuples \| \|--------------------------------------------------------\|:----------------------------------------:\|:--------------------------:\| \| [Reddit comments (2015-2018)](https://github.com/PolyAI-LDN/conversational-datasets/tree/master/reddit) \| [paper](https://arxiv.org/abs/1904.06472) \| 726,484,430 \| \| [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Abstracts) \| [paper](https://aclanthology.org/2020.acl-main.447/) \| 116,288,806 \| \| [WikiAnswers](https://github.com/afader/oqa#wikianswers-corpus) Duplicate question pairs \| [paper](https://doi.org/10.1145/2623330.2623677) \| 77,427,422 \| \| [PAQ](https://github.com/facebookresearch/PAQ) (Question, Answer) pairs \| [paper](https://arxiv.org/abs/2102.07033) \| 64,371,441 \| \| [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Titles) \| [paper](https://aclanthology.org/2020.acl-main.447/) \| 52,603,982 \| \| [S2ORC](https://github.com/allenai/s2orc) (Title, Abstract) \| [paper](https://aclanthology.org/2020.acl-main.447/) \| 41,769,185 \| \| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Body) pairs \| - \| 25,316,456 \| \| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title+Body, Answer) pairs \| - \| 21,396,559 \| \| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Answer) pairs \| - \| 21,396,559 \| \| [MS MARCO](https://microsoft.github.io/msmarco/) triplets \| [paper](https://doi.org/10.1145/3404835.3462804) \| 9,144,553 \| \| [GOOAQ: Open Question Answering with Diverse Answer Types](https://github.com/allenai/gooaq) \| [paper](https://arxiv.org/pdf/2104.08727.pdf) \| 3,012,496 \| \| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Answer) \| [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) \| 1,198,260 \| \| [Code Search](https://huggingface.co/datasets/code_search_net) \| - \| 1,151,414 \| \| [COCO](https://cocodataset.org/#home) Image captions \| [paper](https://link.springer.com/chapter/10.1007%2F978-3-319-10602-1_48) \| 828,395\| \| [SPECTER](https://github.com/allenai/specter) citation triplets \| [paper](https://doi.org/10.18653/v1/2020.acl-main.207) \| 684,100 \| \| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Question, Answer) \| [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) \| 681,164 \| \| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Question) \| [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) \| 659,896 \| \| [SearchQA](https://huggingface.co/datasets/search_qa) \| [paper](https://arxiv.org/abs/1704.05179) \| 582,261 \| \| [Eli5](https://huggingface.co/datasets/eli5) \| [paper](https://doi.org/10.18653/v1/p19-1346) \| 325,475 \| \| [Flickr 30k](https://shannon.cs.illinois.edu/DenotationGraph/) \| [paper](https://transacl.org/ojs/index.php/tacl/article/view/229/33) \| 317,695 \| \| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles) \| \| 304,525 \| \| AllNLI ([SNLI](https://nlp.stanford.edu/projects/snli/) and [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) \| [paper SNLI](https://doi.org/10.18653/v1/d15-1075), [paper MultiNLI](https://doi.org/10.18653/v1/n18-1101) \| 277,230 \| \| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (bodies) \| \| 250,519 \| \| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles+bodies) \| \| 250,460 \| \| [Sentence Compression](https://github.com/google-research-datasets/sentence-compression) \| [paper](https://www.aclweb.org/anthology/D13-1155/) \| 180,000 \| \| [Wikihow](https://github.com/pvl/wikihow_pairs_dataset) \| [paper](https://arxiv.org/abs/1810.09305) \| 128,542 \| \| [Altlex](https://github.com/chridey/altlex/) \| [paper](https://aclanthology.org/P16-1135.pdf) \| 112,696 \| \| [Quora Question Triplets](https://quoradata.quora.com/First-Quora-Dataset-Release-Question-Pairs) \| - \| 103,663 \| \| [Simple Wikipedia](https://cs.pomona.edu/~dkauchak/simplification/) \| [paper](https://www.aclweb.org/anthology/P11-2117/) \| 102,225 \| \| [Natural Questions (NQ)](https://ai.google.com/research/NaturalQuestions) \| [paper](https://transacl.org/ojs/index.php/tacl/article/view/1455) \| 100,231 \| \| [SQuAD2.0](https://rajpurkar.github.io/SQuAD-explorer/) \| [paper](https://aclanthology.org/P18-2124.pdf) \| 87,599 \| \| [TriviaQA](https://huggingface.co/datasets/trivia_qa) \| - \| 73,346 \| \| Total* \| \| 1,170,060,424 \|
erkam/sg2im-256-bs-16x2-cc-depth-olr	erkam	2023-09-29T22:40:22Z	2	0	diffusers	[ "diffusers", "sg-to-image", "scene-graph", "stable-diffusion", "stable-diffusion-diffusers", "lora", "base_model:stabilityai/stable-diffusion-2", "base_model:adapter:stabilityai/stable-diffusion-2", "license:creativeml-openrail-m", "region:us" ]	null	2023-09-22T22:53:09Z	--- license: creativeml-openrail-m base_model: stabilityai/stable-diffusion-2 tags: - sg-to-image - scene-graph - stable-diffusion - stable-diffusion-diffusers - diffusers - lora inference: true --- # LoRA text2image fine-tuning - erkam/sg2im-256-bs-16x2-cc-depth-olr These are LoRA adaption weights for stabilityai/stable-diffusion-2. The weights were fine-tuned on the erkam/clevr-full-v5 dataset. You can find some example images in the following.
Powidl43/glow_n_flow	Powidl43	2023-09-29T22:36:03Z	0	0	null	[ "stable-diffusion", "text-to-image", "license:creativeml-openrail-m", "region:us" ]	text-to-image	2023-09-29T21:34:16Z	--- license: creativeml-openrail-m tags: - stable-diffusion - text-to-image --- --- # Glow n Flow (P4A) trained with kohya_ss (edg settings) dana_ulama dataset deviantart.com/dana-ulama/gallery kelvinsf dataset deviantart.com/kelvinsf/gallery/86790128/fluid-sculpture trigger "p4a psychedelic" + EasyNegative huggingface.co/LibreSD/Various/resolve/main/EasyNegative.safetensors huggingface.co/LibreSD/Various/resolve/main/EasyNegativeV2.safetensors samples civitai.com/models/154028/glow-n-flow-p4a --- # Merge Info GnF64 - step1 = dana_ulama 0.6 + kelvinsf 0.4 - step2_a = step1-camelliamix_v3 0.6 + step1-greymix_v2 0.4 - step2_b = step1-counterfeit_v3 0.6 + step1-nabimix_v2 0.4 - gnf64_v1_a = step2_a 0.6 + step2_b 0.4 - gnf64_v1_b = step2_b 0.6 + step2_a 0.4 GnF82 - step1 = dana_ulama 0.8 + kelvinsf 0.2 - step2_a = step1-camelliamix_v3 0.6 + step1-greymix_v2 0.4 - step2_b = step1-counterfeit_v3 0.6 + step1-nabimix_v2 0.4 - gnf82_v1_a = step2_a 0.6 + step2_b 0.4 - gnf82_v1_b = step2_b 0.6 + step2_a 0.4 P4A Glow - step1 = [p4a-step2](https://huggingface.co/Powidl43/psychedelic/tree/main/step2-merge) 0.6 + dana_ulama 0.4 - step2_a = step1-camelliamix_v3 0.6 + step1-greymix_v2 0.4 - step2_b = step1-counterfeit_v3 0.6 + step1-nabimix_v2 0.4 - p4a_glow_v1_a = step2_a 0.6 + step2_b 0.4 - p4a_glow_v1_b = step2_b 0.6 + step2_a 0.4 P4A Flow - step1 = [p4a-step2](https://huggingface.co/Powidl43/psychedelic/tree/main/step2-merge) 0.6 + kelvinsf 0.4 - step2_a = step1-camelliamix_v3 0.6 + step1-greymix_v2 0.4 - step2_b = step1-counterfeit_v3 0.6 + step1-nabimix_v2 0.4 - p4a_flow_v1_a = step2_a 0.6 + step2_b 0.4 - p4a_flow_v1_b = step2_b 0.6 + step2_a 0.4 --- base models and other essentials huggingface.co/LibreSD
asmaa1/videomae-base-groub23-24-finetuned-SLT-subset	asmaa1	2023-09-29T22:35:40Z	59	0	transformers	[ "transformers", "pytorch", "videomae", "video-classification", "generated_from_trainer", "base_model:MCG-NJU/videomae-base", "base_model:finetune:MCG-NJU/videomae-base", "license:cc-by-nc-4.0", "endpoints_compatible", "region:us" ]	video-classification	2023-09-29T19:36:18Z	--- license: cc-by-nc-4.0 base_model: MCG-NJU/videomae-base tags: - generated_from_trainer metrics: - accuracy model-index: - name: videomae-base-groub23-24-finetuned-SLT-subset 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. --> # videomae-base-groub23-24-finetuned-SLT-subset This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 3.2558 - Accuracy: 0.1463 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - training_steps: 80 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 3.8674 \| 0.14 \| 11 \| 3.6587 \| 0.0488 \| \| 3.7787 \| 1.14 \| 22 \| 3.5948 \| 0.1220 \| \| 3.6605 \| 2.14 \| 33 \| 3.5183 \| 0.1220 \| \| 3.6081 \| 3.14 \| 44 \| 3.4284 \| 0.1463 \| \| 3.5543 \| 4.14 \| 55 \| 3.3461 \| 0.1463 \| \| 3.4024 \| 5.14 \| 66 \| 3.2865 \| 0.1220 \| \| 3.3301 \| 6.14 \| 77 \| 3.2581 \| 0.1463 \| \| 3.3935 \| 7.04 \| 80 \| 3.2558 \| 0.1463 \| ### Framework versions - Transformers 4.33.0 - Pytorch 2.0.0+cpu - Datasets 2.1.0 - Tokenizers 0.13.3
pn51/unit2_taxi	pn51	2023-09-29T22:26:04Z	0	0	null	[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2023-09-29T22:26:01Z	--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: unit2_taxi results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.54 +/- 2.73 name: mean_reward verified: false --- # Q-Learning Agent playing1 Taxi-v3 This is a trained model of a Q-Learning agent playing Taxi-v3 . ## Usage ```python model = load_from_hub(repo_id="pn51/unit2_taxi", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```
pn51/q-FrozenLake-v1-4x4-noSlippery	pn51	2023-09-29T22:23:44Z	0	0	null	[ "FrozenLake-v1-4x4", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2023-09-29T22:23:41Z	--- tags: - FrozenLake-v1-4x4 - 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 type: FrozenLake-v1-4x4 metrics: - type: mean_reward value: 0.67 +/- 0.47 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="pn51/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"]) ```
afaranda/my_awesome_geopolitical_model	afaranda	2023-09-29T22:18:46Z	104	0	transformers	[ "transformers", "pytorch", "t5", "text2text-generation", "generated_from_trainer", "dataset:geopolitica", "base_model:gsarti/it5-small", "base_model:finetune:gsarti/it5-small", "license:apache-2.0", "model-index", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2023-09-29T15:13:08Z	--- license: apache-2.0 base_model: gsarti/it5-small tags: - generated_from_trainer datasets: - geopolitica metrics: - rouge model-index: - name: my_awesome_geopolitical_model results: - task: name: Sequence-to-sequence Language Modeling type: text2text-generation dataset: name: geopolitica type: geopolitica config: default split: train args: default metrics: - name: Rouge1 type: rouge value: 0.1409 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # my_awesome_geopolitical_model This model is a fine-tuned version of [gsarti/it5-small](https://huggingface.co/gsarti/it5-small) on the geopolitica dataset. It achieves the following results on the evaluation set: - Loss: nan - Rouge1: 0.1409 - Rouge2: 0.0203 - Rougel: 0.1247 - Rougelsum: 0.125 - Gen Len: 18.781 ## 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: 4 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rouge1 \| Rouge2 \| Rougel \| Rougelsum \| Gen Len \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\|:------:\|:------:\|:---------:\|:-------:\| \| No log \| 1.0 \| 53 \| nan \| 0.1409 \| 0.0203 \| 0.1247 \| 0.125 \| 18.781 \| \| No log \| 2.0 \| 106 \| nan \| 0.1409 \| 0.0203 \| 0.1247 \| 0.125 \| 18.781 \| \| No log \| 3.0 \| 159 \| nan \| 0.1409 \| 0.0203 \| 0.1247 \| 0.125 \| 18.781 \| \| No log \| 4.0 \| 212 \| nan \| 0.1409 \| 0.0203 \| 0.1247 \| 0.125 \| 18.781 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3
s3nh/gradientputri-MegaMix-S1-13B-GGUF	s3nh	2023-09-29T21:39:10Z	8	0	transformers	[ "transformers", "gguf", "text-generation", "zh", "en", "license:openrail", "endpoints_compatible", "region:us" ]	text-generation	2023-09-29T21:20:16Z	--- license: openrail pipeline_tag: text-generation library_name: transformers language: - zh - en --- ## Original model card Buy me a coffee if you like this project ;) <a href="https://www.buymeacoffee.com/s3nh"><img src="https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg" alt=""></a> #### Description GGUF Format model files for [This project](https://huggingface.co/gradientputri/MegaMix-S1-13B). ### GGUF Specs GGUF is a format based on the existing GGJT, but makes a few changes to the format to make it more extensible and easier to use. The following features are desired: Single-file deployment: they can be easily distributed and loaded, and do not require any external files for additional information. Extensible: new features can be added to GGML-based executors/new information can be added to GGUF models without breaking compatibility with existing models. mmap compatibility: models can be loaded using mmap for fast loading and saving. Easy to use: models can be easily loaded and saved using a small amount of code, with no need for external libraries, regardless of the language used. Full information: all information needed to load a model is contained in the model file, and no additional information needs to be provided by the user. The key difference between GGJT and GGUF is the use of a key-value structure for the hyperparameters (now referred to as metadata), rather than a list of untyped values. This allows for new metadata to be added without breaking compatibility with existing models, and to annotate the model with additional information that may be useful for inference or for identifying the model. ### Perplexity params Model Measure Q2_K Q3_K_S Q3_K_M Q3_K_L Q4_0 Q4_1 Q4_K_S Q4_K_M Q5_0 Q5_1 Q5_K_S Q5_K_M Q6_K Q8_0 F16 7B perplexity 6.7764 6.4571 6.1503 6.0869 6.1565 6.0912 6.0215 5.9601 5.9862 5.9481 5.9419 5.9208 5.9110 5.9070 5.9066 13B perplexity 5.8545 5.6033 5.4498 5.4063 5.3860 5.3608 5.3404 5.3002 5.2856 5.2706 5.2785 5.2638 5.2568 5.2548 5.2543 ### inference TODO # Original model card
Samuael/wav2vec2-base-alffaamharic-google-colab	Samuael	2023-09-29T21:10:52Z	108	0	transformers	[ "transformers", "pytorch", "wav2vec2", "automatic-speech-recognition", "generated_from_trainer", "base_model:Samuael/wav2vec2-base-alffaamharic-google-colab", "base_model:finetune:Samuael/wav2vec2-base-alffaamharic-google-colab", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2023-09-20T18:33:29Z	--- license: apache-2.0 base_model: Samuael/wav2vec2-base-alffaamharic-google-colab tags: - generated_from_trainer metrics: - wer model-index: - name: wav2vec2-base-alffaamharic-google-colab 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. --> # wav2vec2-base-alffaamharic-google-colab This model is a fine-tuned version of [Samuael/wav2vec2-base-alffaamharic-google-colab](https://huggingface.co/Samuael/wav2vec2-base-alffaamharic-google-colab) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.6124 - Wer: 0.3502 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 32 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 1000 - num_epochs: 30 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\| \| 0.1622 \| 1.44 \| 200 \| 0.4605 \| 0.3455 \| \| 0.1619 \| 2.88 \| 400 \| 0.5327 \| 0.3658 \| \| 0.1566 \| 4.32 \| 600 \| 0.5235 \| 0.3834 \| \| 0.246 \| 5.76 \| 800 \| 0.5781 \| 0.4329 \| \| 0.3211 \| 7.19 \| 1000 \| 0.6142 \| 0.4535 \| \| 0.2705 \| 8.63 \| 1200 \| 0.6172 \| 0.4519 \| \| 0.2113 \| 10.07 \| 1400 \| 0.6140 \| 0.4111 \| \| 0.2642 \| 11.51 \| 1600 \| 0.6020 \| 0.4527 \| \| 0.2881 \| 12.95 \| 1800 \| 0.5931 \| 0.4393 \| \| 0.1801 \| 14.39 \| 2000 \| 0.6565 \| 0.4262 \| \| 0.1494 \| 15.83 \| 2200 \| 0.5732 \| 0.4003 \| \| 0.1684 \| 17.27 \| 2400 \| 0.6419 \| 0.4071 \| \| 0.1805 \| 18.71 \| 2600 \| 0.5973 \| 0.4005 \| \| 0.1518 \| 20.14 \| 2800 \| 0.5846 \| 0.3821 \| \| 0.0821 \| 21.58 \| 3000 \| 0.6149 \| 0.3764 \| \| 0.1049 \| 23.02 \| 3200 \| 0.5965 \| 0.3724 \| \| 0.1229 \| 24.46 \| 3400 \| 0.6032 \| 0.3671 \| \| 0.0848 \| 25.9 \| 3600 \| 0.6005 \| 0.3605 \| \| 0.0724 \| 27.34 \| 3800 \| 0.6258 \| 0.3634 \| \| 0.1149 \| 28.78 \| 4000 \| 0.6124 \| 0.3502 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3
asmaa1/videomae-base-groub21-22-finetuned-SLT-subset	asmaa1	2023-09-29T20:50:22Z	62	0	transformers	[ "transformers", "pytorch", "videomae", "video-classification", "generated_from_trainer", "base_model:MCG-NJU/videomae-base", "base_model:finetune:MCG-NJU/videomae-base", "license:cc-by-nc-4.0", "endpoints_compatible", "region:us" ]	video-classification	2023-09-29T19:35:33Z	--- license: cc-by-nc-4.0 base_model: MCG-NJU/videomae-base tags: - generated_from_trainer metrics: - accuracy model-index: - name: videomae-base-groub21-22-finetuned-SLT-subset 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. --> # videomae-base-groub21-22-finetuned-SLT-subset This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 3.1575 - Accuracy: 0.125 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - training_steps: 80 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 3.8723 \| 0.12 \| 10 \| 3.6474 \| 0.025 \| \| 3.7679 \| 1.12 \| 20 \| 3.5862 \| 0.1 \| \| 3.6477 \| 2.12 \| 30 \| 3.5005 \| 0.075 \| \| 3.5454 \| 3.12 \| 40 \| 3.3870 \| 0.1 \| \| 3.4185 \| 4.12 \| 50 \| 3.2780 \| 0.125 \| \| 3.3205 \| 5.12 \| 60 \| 3.2124 \| 0.1 \| \| 3.2337 \| 6.12 \| 70 \| 3.1729 \| 0.1 \| \| 3.176 \| 7.12 \| 80 \| 3.1575 \| 0.125 \| ### Framework versions - Transformers 4.33.0 - Pytorch 2.0.0+cpu - Datasets 2.1.0 - Tokenizers 0.13.3
TheBloke/Mistral-7B-v0.1-GPTQ	TheBloke	2023-09-29T20:49:41Z	1,483	36	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "pretrained", "base_model:mistralai/Mistral-7B-v0.1", "base_model:quantized:mistralai/Mistral-7B-v0.1", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "4-bit", "gptq", "region:us" ]	text-generation	2023-09-28T22:35:40Z	--- base_model: mistralai/Mistral-7B-v0.1 inference: false license: apache-2.0 model_creator: Mistral AI model_name: Mistral 7B v0.1 model_type: mistral pipeline_tag: text-generation prompt_template: '{prompt}' quantized_by: TheBloke tags: - pretrained --- <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end --> # Mistral 7B v0.1 - GPTQ - Model creator: [Mistral AI](https://huggingface.co/mistralai) - Original model: [Mistral 7B v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) <!-- description start --> ## Description This repo contains GPTQ model files for [Mistral AI's Mistral 7B v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1). Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them. ### GPTQs will work in ExLlama, or via Transformers (requiring Transformers from Github) These models are confirmed to work with ExLlama v1. At the time of writing (September 28th), AutoGPTQ has not yet added support for the new Mistral models. These GPTQs were made directly from Transformers, and so can be loaded via the Transformers interface. They can't be loaded directly from AutoGPTQ. To load them via Transformers, you will need to install Transformers from Github, with: ``` pip3 install git+https://github.com/huggingface/transformers.git@72958fcd3c98a7afdc61f953aa58c544ebda2f79 ``` <!-- description end --> <!-- description end --> <!-- repositories-available start --> ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Mistral-7B-v0.1-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GGUF) * [Mistral AI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/mistralai/Mistral-7B-v0.1) <!-- repositories-available end --> <!-- prompt-template start --> ## Prompt template: None ``` {prompt} ``` <!-- prompt-template end --> <!-- README_GPTQ.md-provided-files start --> ## Provided files, and GPTQ parameters Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements. Each separate quant is in a different branch. See below for instructions on fetching from different branches. These files were made with Transformers 4.34.0.dev0, from commit 72958fcd3c98a7afdc61f953aa58c544ebda2f79. <details> <summary>Explanation of GPTQ parameters</summary> - Bits: The bit size of the quantised model. - GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value. - Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now. - Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy. - GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s). - Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences. - ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit. </details> \| Branch \| Bits \| GS \| Act Order \| Damp % \| GPTQ Dataset \| Seq Len \| Size \| ExLlama \| Desc \| \| ------ \| ---- \| -- \| --------- \| ------ \| ------------ \| ------- \| ---- \| ------- \| ---- \| \| [main](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ/tree/main) \| 4 \| 128 \| Yes \| 0.1 \| [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) \| 32768 \| 4.16 GB \| Yes \| 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. \| \| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ/tree/gptq-4bit-32g-actorder_True) \| 4 \| 32 \| Yes \| 0.1 \| [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) \| 32768 \| 4.57 GB \| Yes \| 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. \| \| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ/tree/gptq-8bit-128g-actorder_True) \| 8 \| 128 \| Yes \| 0.1 \| [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) \| 32768 \| 4.16 GB \| Yes \| 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. \| \| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ/tree/gptq-8bit-32g-actorder_True) \| 8 \| 32 \| Yes \| 0.1 \| [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) \| 32768 \| 4.57 GB \| Yes \| 8-bit, with group size 32g and Act Order for maximum inference quality. \| <!-- README_GPTQ.md-provided-files end --> <!-- README_GPTQ.md-download-from-branches start --> ## How to download, including from branches ### In text-generation-webui To download from the `main` branch, enter `TheBloke/Mistral-7B-v0.1-GPTQ` in the "Download model" box. To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/Mistral-7B-v0.1-GPTQ:gptq-4bit-32g-actorder_True` ### From the command line I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` To download the `main` branch to a folder called `Mistral-7B-v0.1-GPTQ`: ```shell mkdir Mistral-7B-v0.1-GPTQ huggingface-cli download TheBloke/Mistral-7B-v0.1-GPTQ --local-dir Mistral-7B-v0.1-GPTQ --local-dir-use-symlinks False ``` To download from a different branch, add the `--revision` parameter: ```shell mkdir Mistral-7B-v0.1-GPTQ huggingface-cli download TheBloke/Mistral-7B-v0.1-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir Mistral-7B-v0.1-GPTQ --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage</summary> If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model. The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`. For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell mkdir Mistral-7B-v0.1-GPTQ HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Mistral-7B-v0.1-GPTQ --local-dir Mistral-7B-v0.1-GPTQ --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> ### With `git` (not recommended) To clone a specific branch with `git`, use a command like this: ```shell git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ ``` Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.) <!-- README_GPTQ.md-download-from-branches end --> <!-- README_GPTQ.md-text-generation-webui start --> ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui). These models are confirmed to work via the ExLlama Loader in text-generation-webui. Use Loader: ExLlama - or Transformers may work too. AutoGPTQ will not work. Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui). It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install. 1. Click the Model tab. 2. Under Download custom model or LoRA, enter `TheBloke/Mistral-7B-v0.1-GPTQ`. - To download from a specific branch, enter for example `TheBloke/Mistral-7B-v0.1-GPTQ:gptq-4bit-32g-actorder_True` - see Provided Files above for the list of branches for each option. 3. Click Download. 4. The model will start downloading. Once it's finished it will say "Done". 5. In the top left, click the refresh icon next to Model. 6. In the Model dropdown, choose the model you just downloaded: `Mistral-7B-v0.1-GPTQ` 7. The model will automatically load, and is now ready for use! 8. If you want any custom settings, set them and then click Save settings for this model followed by Reload the Model in the top right. * Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`. 9. Once you're ready, click the Text Generation tab and enter a prompt to get started! <!-- README_GPTQ.md-text-generation-webui end --> <!-- README_GPTQ.md-use-from-python start --> ## How to use this GPTQ model from Python code ### Install the necessary packages Requires: Transformers 4.34.0.dev0 from Github source, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later. ```shell pip3 install optimum pip3 install git+https://github.com/huggingface/transformers.git@72958fcd3c98a7afdc61f953aa58c544ebda2f79 pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7 ``` If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead: ```shell pip3 uninstall -y auto-gptq git clone https://github.com/PanQiWei/AutoGPTQ cd AutoGPTQ git checkout v0.4.2 pip3 install . ``` ### You can then use the following code ```python from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline model_name_or_path = "TheBloke/Mistral-7B-v0.1-GPTQ" # To use a different branch, change revision # For example: revision="gptq-4bit-32g-actorder_True" model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto", trust_remote_code=False, revision="main") tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True) prompt = "Tell me about AI" prompt_template=f'''{prompt} ''' print("\n\n* Generate:") input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda() output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512) print(tokenizer.decode(output[0])) # Inference can also be done using transformers' pipeline print("* Pipeline:") pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512, do_sample=True, temperature=0.7, top_p=0.95, top_k=40, repetition_penalty=1.1 ) print(pipe(prompt_template)[0]['generated_text']) ``` <!-- README_GPTQ.md-use-from-python end --> <!-- README_GPTQ.md-compatibility start --> ## Compatibility The files provided are only tested to work with Transformers 4.34.0.dev0 as of commit 72958fcd3c98a7afdc61f953aa58c544ebda2f79. <!-- README_GPTQ.md-compatibility end --> <!-- footer start --> <!-- 200823 --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI Special thanks to: Aemon Algiz. Patreon special mentions: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant. <!-- footer end --> # Original model card: Mistral AI's Mistral 7B v0.1 # Model Card for Mistral-7B-v0.1 The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks we tested. For full details of this model please read our [Release blog post](https://mistral.ai/news/announcing-mistral-7b/) ## Model Architecture Mistral-7B-v0.1 is 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. ## Notice Mistral 7B is a pretrained base model and therefore does not have any moderation mechanisms. ## The Mistral AI Team Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.
TheBloke/Mistral-7B-Instruct-v0.1-GPTQ	TheBloke	2023-09-29T20:48:48Z	4,510	79	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "finetuned", "conversational", "base_model:mistralai/Mistral-7B-Instruct-v0.1", "base_model:quantized:mistralai/Mistral-7B-Instruct-v0.1", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "4-bit", "gptq", "region:us" ]	text-generation	2023-09-28T22:34:03Z	--- base_model: mistralai/Mistral-7B-Instruct-v0.1 inference: false license: apache-2.0 model_creator: Mistral AI model_name: Mistral 7B Instruct v0.1 model_type: mistral pipeline_tag: text-generation prompt_template: '<s>[INST] {prompt} [/INST]' quantized_by: TheBloke tags: - finetuned --- <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end --> # Mistral 7B Instruct v0.1 - GPTQ - Model creator: [Mistral AI](https://huggingface.co/mistralai) - Original model: [Mistral 7B Instruct v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) <!-- description start --> ## Description This repo contains GPTQ model files for [Mistral AI's Mistral 7B Instruct v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1). Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them. ### GPTQs will work in ExLlama, or via Transformers (requiring Transformers from Github) These models are confirmed to work with ExLlama v1. At the time of writing (September 28th), AutoGPTQ has not yet added support for the new Mistral models. These GPTQs were made directly from Transformers, and so can be loaded via the Transformers interface. They can't be loaded directly from AutoGPTQ. To load them via Transformers, you will need to install Transformers from Github, with: ``` pip3 install git+https://github.com/huggingface/transformers.git@72958fcd3c98a7afdc61f953aa58c544ebda2f79 ``` <!-- description end --> <!-- repositories-available start --> ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF) * [Mistral AI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) <!-- repositories-available end --> <!-- prompt-template start --> ## Prompt template: Mistral ``` <s>[INST] {prompt} [/INST] ``` <!-- prompt-template end --> <!-- README_GPTQ.md-provided-files start --> ## Provided files, and GPTQ parameters Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements. Each separate quant is in a different branch. See below for instructions on fetching from different branches. These files were made with Transformers 4.34.0.dev0, from commit 72958fcd3c98a7afdc61f953aa58c544ebda2f79. <details> <summary>Explanation of GPTQ parameters</summary> - Bits: The bit size of the quantised model. - GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value. - Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now. - Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy. - GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s). - Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences. - ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit. </details> \| Branch \| Bits \| GS \| Act Order \| Damp % \| GPTQ Dataset \| Seq Len \| Size \| ExLlama \| Desc \| \| ------ \| ---- \| -- \| --------- \| ------ \| ------------ \| ------- \| ---- \| ------- \| ---- \| \| [main](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GPTQ/tree/main) \| 4 \| 128 \| Yes \| 0.1 \| [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) \| 32768 \| 4.16 GB \| Yes \| 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. \| \| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GPTQ/tree/gptq-4bit-32g-actorder_True) \| 4 \| 32 \| Yes \| 0.1 \| [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) \| 32768 \| 4.57 GB \| Yes \| 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. \| \| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GPTQ/tree/gptq-8bit-128g-actorder_True) \| 8 \| 128 \| Yes \| 0.1 \| [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) \| 32768 \| 7.68 GB \| Yes \| 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. \| \| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GPTQ/tree/gptq-8bit-32g-actorder_True) \| 8 \| 32 \| Yes \| 0.1 \| [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) \| 32768 \| 8.17 GB \| Yes \| 8-bit, with group size 32g and Act Order for maximum inference quality. \| <!-- README_GPTQ.md-provided-files end --> <!-- README_GPTQ.md-download-from-branches start --> ## How to download, including from branches ### In text-generation-webui To download from the `main` branch, enter `TheBloke/Mistral-7B-Instruct-v0.1-GPTQ` in the "Download model" box. To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/Mistral-7B-Instruct-v0.1-GPTQ:gptq-4bit-32g-actorder_True` ### From the command line I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` To download the `main` branch to a folder called `Mistral-7B-Instruct-v0.1-GPTQ`: ```shell mkdir Mistral-7B-Instruct-v0.1-GPTQ huggingface-cli download TheBloke/Mistral-7B-Instruct-v0.1-GPTQ --local-dir Mistral-7B-Instruct-v0.1-GPTQ --local-dir-use-symlinks False ``` To download from a different branch, add the `--revision` parameter: ```shell mkdir Mistral-7B-Instruct-v0.1-GPTQ huggingface-cli download TheBloke/Mistral-7B-Instruct-v0.1-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir Mistral-7B-Instruct-v0.1-GPTQ --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage</summary> If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model. The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`. For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell mkdir Mistral-7B-Instruct-v0.1-GPTQ HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Mistral-7B-Instruct-v0.1-GPTQ --local-dir Mistral-7B-Instruct-v0.1-GPTQ --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> ### With `git` (not recommended) To clone a specific branch with `git`, use a command like this: ```shell git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GPTQ ``` Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.) <!-- README_GPTQ.md-download-from-branches end --> <!-- README_GPTQ.md-text-generation-webui start --> ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui). These models are confirmed to work via the ExLlama Loader in text-generation-webui. Use Loader: ExLlama - or Transformers may work too. AutoGPTQ will not work. Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui). It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install. 1. Click the Model tab. 2. Under Download custom model or LoRA, enter `TheBloke/Mistral-7B-Instruct-v0.1-GPTQ`. - To download from a specific branch, enter for example `TheBloke/Mistral-7B-Instruct-v0.1-GPTQ:gptq-4bit-32g-actorder_True` - see Provided Files above for the list of branches for each option. 3. Click Download. 4. The model will start downloading. Once it's finished it will say "Done". 5. In the top left, click the refresh icon next to Model. 6. In the Model dropdown, choose the model you just downloaded: `Mistral-7B-Instruct-v0.1-GPTQ` 7. The model will automatically load, and is now ready for use! 8. If you want any custom settings, set them and then click Save settings for this model followed by Reload the Model in the top right. * Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`. 9. Once you're ready, click the Text Generation tab and enter a prompt to get started! <!-- README_GPTQ.md-text-generation-webui end --> <!-- README_GPTQ.md-use-from-python start --> ## How to use this GPTQ model from Python code ### Install the necessary packages Requires: Transformers 4.34.0.dev0 from Github source, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later. ```shell pip3 install optimum pip3 install git+https://github.com/huggingface/transformers.git@72958fcd3c98a7afdc61f953aa58c544ebda2f79 pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7 ``` If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead: ```shell pip3 uninstall -y auto-gptq git clone https://github.com/PanQiWei/AutoGPTQ cd AutoGPTQ git checkout v0.4.2 pip3 install . ``` ### You can then use the following code ```python from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline model_name_or_path = "TheBloke/Mistral-7B-Instruct-v0.1-GPTQ" # To use a different branch, change revision # For example: revision="gptq-4bit-32g-actorder_True" model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto", trust_remote_code=False, revision="main") tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True) prompt = "Tell me about AI" prompt_template=f'''<s>[INST] {prompt} [/INST] ''' print("\n\n* Generate:") input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda() output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512) print(tokenizer.decode(output[0])) # Inference can also be done using transformers' pipeline print("* Pipeline:") pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512, do_sample=True, temperature=0.7, top_p=0.95, top_k=40, repetition_penalty=1.1 ) print(pipe(prompt_template)[0]['generated_text']) ``` <!-- README_GPTQ.md-use-from-python end --> <!-- README_GPTQ.md-compatibility start --> ## Compatibility The files provided are only tested to work with ExLlama v1, and Transformers 4.34.0.dev0 as of commit 72958fcd3c98a7afdc61f953aa58c544ebda2f79. <!-- README_GPTQ.md-compatibility end --> <!-- footer start --> <!-- 200823 --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI Special thanks to: Aemon Algiz. Patreon special mentions: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant. <!-- footer end --> # Original model card: Mistral AI's Mistral 7B Instruct v0.1 # Model Card for Mistral-7B-Instruct-v0.1 The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) generative text model using a variety of publicly available conversation datasets. For full details of this model please read our [release blog post](https://mistral.ai/news/announcing-mistral-7b/) ## 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-v0.1") tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1") 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, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.
bartmiller/HuggingFaceDeepRLUnit2	bartmiller	2023-09-29T20:43:48Z	0	0	null	[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2023-09-29T20:43:46Z	--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: HuggingFaceDeepRLUnit2 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.50 +/- 2.75 name: mean_reward verified: false --- # Q-Learning Agent playing1 Taxi-v3 This is a trained model of a Q-Learning agent playing Taxi-v3 . ## Usage ```python model = load_from_hub(repo_id="bartmiller/HuggingFaceDeepRLUnit2", 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"]) ```
bartmiller/q-FrozenLake-v1-4x4-noSlippery	bartmiller	2023-09-29T20:40:36Z	0	0	null	[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2023-09-29T20:40:34Z	--- 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="bartmiller/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"]) ```
AtAndDev/ShortKing-1.4b-v0.1	AtAndDev	2023-09-29T20:30:08Z	2,430	2	transformers	[ "transformers", "pytorch", "safetensors", "gpt_neox", "text-generation", "en", "dataset:vicgalle/alpaca-gpt4", "license:cc-by-nc-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-09-25T20:26:25Z	--- license: cc-by-nc-4.0 datasets: - vicgalle/alpaca-gpt4 language: - en --- ## Model Overview Model license: cc-by-nc-4.0<br> This model is trained based on [EleutherAI/pythia-1.4b-deduped](https://huggingface.co/EleutherAI/pythia-1.4b-deduped) model that is LoRA finetuned on [vicgalle/alpaca-gpt4](https://huggingface.co/datasets/vicgalle/alpaca-gpt4) dataset.<br> ## Prompt Template: `Alpaca` ``` <system_prompt> ### Instruction: <user_message> ### Response: <assistant_response> ``` ## Intended Use THIS IS A TEST MODEL, IT IS NOT INTENDED FOR REAL APPLICATIONS BY ANY MEANS. HOWEVER, A NEW MODEL IS COMING IN THE SAME TOPIC.<br> This model series will be used for small but intense applications. ## Training Details This model took `2:31:23` to train in QLoRA on a single `T4` GPU.<br> - epochs: `1` - train batch size: `12` - eval batch size: `12` - gradient accumulation steps: `1` - maximum gradient normal: `0.3` - learning rate: `2e-4` - weight decay: `0.001` - optimizer: `paged_adamw_32bit` - learning rate schedule: `cosine` - warmup ratio (linear): `0.03`
Schadom/Reinforce-CartPole-v1	Schadom	2023-09-29T20:29:44Z	0	0	null	[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2023-09-29T20:29:41Z	--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-CartPole-v1 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 133.60 +/- 38.68 name: mean_reward verified: false --- # Reinforce Agent playing CartPole-v1 This is a trained model of a Reinforce agent playing CartPole-v1 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
Msughterx/wav2vec2-base-xlsr-igbo	Msughterx	2023-09-29T20:22:18Z	133	0	transformers	[ "transformers", "pytorch", "wav2vec2", "automatic-speech-recognition", "generated_from_trainer", "base_model:facebook/wav2vec2-base", "base_model:finetune:facebook/wav2vec2-base", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2023-09-29T19:54:02Z	--- license: apache-2.0 base_model: facebook/wav2vec2-base tags: - generated_from_trainer model-index: - name: wav2vec2-base-xlsr-igbo 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. --> # wav2vec2-base-xlsr-igbo This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 32 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 1000 - num_epochs: 30 ### Training results ### Framework versions - Transformers 4.33.0 - Pytorch 2.0.0 - Datasets 2.1.0 - Tokenizers 0.13.3
am-infoweb/QA_SYNTH_29_SEPT_WITH_FINETUNE_1.1	am-infoweb	2023-09-29T20:21:10Z	105	0	transformers	[ "transformers", "pytorch", "xlm-roberta", "question-answering", "generated_from_trainer", "base_model:FacebookAI/xlm-roberta-base", "base_model:finetune:FacebookAI/xlm-roberta-base", "license:mit", "endpoints_compatible", "region:us" ]	question-answering	2023-09-29T18:17:19Z	--- license: mit base_model: xlm-roberta-base tags: - generated_from_trainer model-index: - name: QA_SYNTH_29_SEPT_WITH_FINETUNE_1.1 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # QA_SYNTH_29_SEPT_WITH_FINETUNE_1.1 This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0036 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:------:\|:---------------:\| \| 0.1705 \| 1.0 \| 10935 \| 0.1407 \| \| 0.1014 \| 2.0 \| 21870 \| 0.0550 \| \| 0.0426 \| 3.0 \| 32805 \| 0.0541 \| \| 0.0028 \| 4.0 \| 43740 \| 0.0320 \| \| 0.0215 \| 5.0 \| 54675 \| 0.0307 \| \| 0.0065 \| 6.0 \| 65610 \| 0.0119 \| \| 0.014 \| 7.0 \| 76545 \| 0.0074 \| \| 0.0 \| 8.0 \| 87480 \| 0.0037 \| \| 0.0 \| 9.0 \| 98415 \| 0.0047 \| \| 0.0 \| 10.0 \| 109350 \| 0.0036 \| ### Framework versions - Transformers 4.32.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.14.4 - Tokenizers 0.13.3
raalst/RobBERT-v2-nl-ext-qa	raalst	2023-09-29T20:10:49Z	115	1	transformers	[ "transformers", "pytorch", "roberta", "question-answering", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	question-answering	2023-09-25T20:43:10Z	--- # For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1 # Doc / guide: https://huggingface.co/docs/hub/model-cards {} --- # Model Card for Model ID q/a model, structurally same as RobBERT-v2-nl-qa, but trained with an augmented dataset. sentences from the context not containing the answer-span have been moved from before the answer to after the answer, and v.v. The start of the answer has been adapted accordingly. these modified records have an "m" appended to their ID field. ## Model Details Results seem better than RobBERT-v2-nl-qa: {'exact': 65.97542490405392, 'f1': 73.36792208890036, 'total': 31007, 'HasAns_exact': 62.55334441399757, 'HasAns_f1': 72.85023854321435, 'HasAns_total': 22261, 'NoAns_exact': 74.68557054653556, 'NoAns_f1': 74.68557054653556, 'NoAns_total': 8746, 'best_exact': 65.97542490405392, 'best_exact_thresh': 0.0, 'best_f1': 73.3679220889002, 'best_f1_thresh': 0.0} ### Model Description example dutch question and context for the hosted inference api: Q: Op welke wijze heeft de termiet zich kunnen verspreiden ? CX: De koloniën zijn verspreid over twee woningen, bijgebouwen en tuinen in Zuid-Holland. Een van de panden is een groot kassencomplex. Daaruit zijn meerdere planten verkocht, waardoor het mogelijk is dat de termiet zich al verder heeft verspreid. Eerdere pogingen om de koloniën uit te roeien zijn mislukt. De plantenverkoop vanuit het koloniegebied is inmiddels tijdelijk stopgezet. - 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]
ahaedike/dqn-SpaceInvadersNoFrameskip-v4	ahaedike	2023-09-29T20:10:03Z	7	0	stable-baselines3	[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-09-29T20:09:26Z	--- 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: 704.00 +/- 178.84 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 ahaedike -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 ahaedike -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 ahaedike ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 150000), ('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'} ```
ProtonH/q-Taxi-v3	ProtonH	2023-09-29T19:50:24Z	0	0	null	[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2023-09-29T19:50:23Z	--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-Taxi-v3 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.56 +/- 2.71 name: mean_reward verified: false --- # Q-Learning Agent playing1 Taxi-v3 This is a trained model of a Q-Learning agent playing Taxi-v3 . ## Usage ```python model = load_from_hub(repo_id="ProtonH/q-Taxi-v3", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```
PanoEvJ/summarization_finetuned_t5_base_4bit	PanoEvJ	2023-09-29T19:47:16Z	4	0	peft	[ "peft", "base_model:google-t5/t5-base", "base_model:adapter:google-t5/t5-base", "region:us" ]	null	2023-09-09T21:34:17Z	--- library_name: peft base_model: t5-base --- ## 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 0.6.0.dev0
LarryAIDraw/Nel-10	LarryAIDraw	2023-09-29T19:43:23Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2023-09-29T19:41:49Z	--- license: creativeml-openrail-m --- https://civitai.com/models/153802/nelliel-tu-odelschwanck-bleach-lora
LarryAIDraw/gertrude_mix2	LarryAIDraw	2023-09-29T19:43:13Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2023-09-29T19:41:23Z	--- license: creativeml-openrail-m --- https://civitai.com/models/26531/arknights-gertrude
ProtonH/q-FrozenLake-v1-4x4-noSlippery	ProtonH	2023-09-29T19:40:17Z	0	0	null	[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2023-09-29T19:40:14Z	--- 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="ProtonH/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"]) ```
LarryAIDraw/Taihou-10	LarryAIDraw	2023-09-29T19:39:49Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2023-09-29T19:32:07Z	--- license: creativeml-openrail-m --- https://civitai.com/models/153924/taihou-azur-lane-lora
LarryAIDraw/misaki	LarryAIDraw	2023-09-29T19:39:08Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2023-09-29T19:30:41Z	--- license: creativeml-openrail-m --- https://civitai.com/models/153850/misaki-sakimiya-or-dead-mount-death-play

Subsets and Splits