Text Generation Webui Colab

🐣 Please follow me for new updates https://twitter.com/camenduru <br /> 🔥 Please join our discord server https://discord.gg/k5BwmmvJJU <br /> 🥳 Please join my patreon community https://patreon.com/camenduru <br />

🚦 WIP 🚦

🦒 Colab

| colab | Info - Model Page | --- | --- | | vicuna-13b-GPTQ-4bit-128g <br /> https://vicuna.lmsys.org | vicuna-13B-1.1-GPTQ-4bit-128g <br /> https://vicuna.lmsys.org | stable-vicuna-13B-GPTQ-4bit-128g <br /> https://huggingface.co/CarperAI/stable-vicuna-13b-delta | gpt4-x-alpaca-13b-native-4bit-128g <br /> https://huggingface.co/chavinlo/gpt4-x-alpaca | pyg-7b-GPTQ-4bit-128g <br /> https://huggingface.co/Neko-Institute-of-Science/pygmalion-7b | koala-13B-GPTQ-4bit-128g <br /> https://bair.berkeley.edu/blog/2023/04/03/koala | oasst-llama13b-GPTQ-4bit-128g <br /> https://open-assistant.io | wizard-lm-uncensored-7b-GPTQ-4bit-128g <br /> https://github.com/nlpxucan/WizardLM | mpt-storywriter-7b-GPTQ-4bit-128g <br /> https://www.mosaicml.com | wizard-lm-uncensored-13b-GPTQ-4bit-128g <br /> https://github.com/nlpxucan/WizardLM | pyg-13b-GPTQ-4bit-128g <br /> https://huggingface.co/PygmalionAI/pygmalion-13b | falcon-7b-instruct-GPTQ-4bit <br /> https://falconllm.tii.ae/ | wizard-lm-13b-1.1-GPTQ-4bit-128g <br /> https://github.com/nlpxucan/WizardLM | llama-2-7b-chat-GPTQ-4bit (4bit) <br /> https://ai.meta.com/llama/ | llama-2-13b-chat-GPTQ-4bit (4bit) <br /> https://ai.meta.com/llama/ <br /> 🚦 WIP 🚦 please try llama-2-13b-chat or llama-2-7b-chat or llama-2-7b-chat-GPTQ-4bit | llama-2-7b-chat (16bit) <br /> https://ai.meta.com/llama/ | llama-2-13b-chat (8bit) <br /> https://ai.meta.com/llama/ | redmond-puffin-13b-GPTQ-4bit (4bit) <br /> https://huggingface.co/NousResearch/Redmond-Puffin-13B | stable-beluga-7b (16bit) <br /> https://huggingface.co/stabilityai/StableBeluga-7B | doctor-gpt-7b (16bit) <br /> https://ai.meta.com/llama/ (https://github.com/llSourcell/DoctorGPT) | code-llama-7b (16bit) <br /> https://github.com/facebookresearch/codellama | code-llama-instruct-7b (16bit) <br /> https://github.com/facebookresearch/codellama | code-llama-python-7b (16bit) <br /> https://github.com/facebookresearch/codellama | mistral-7b-Instruct-v0.1-8bit (8bit) <br /> https://mistral.ai/ | mytho-max-l2-13b-GPTQ (4bit) <br /> https://huggingface.co/Gryphe/MythoMax-L2-13b

🦒 Colab Pro

According to the Facebook Research LLaMA license (Non-commercial bespoke license), maybe we cannot use this model with a Colab Pro account. But Yann LeCun said "GPL v3" (https://twitter.com/ylecun/status/1629189925089296386) I am a little confused. Is it possible to use this with a non-free Colab Pro account?

Tutorial

https://www.youtube.com/watch?v=kgA7eKU1XuA

⚠ If you encounter an IndexError: list index out of range error, please set the models instruction template.

Text Generation Web UI

https://github.com/oobabooga/text-generation-webui (Thanks to @oobabooga ❤)

Models License

| Model | License | --- | --- | vicuna-13b-GPTQ-4bit-128g | From https://vicuna.lmsys.org: The online demo is a research preview intended for non-commercial use only, subject to the model License of LLaMA, Terms of Use of the data generated by OpenAI, and Privacy Practices of ShareGPT. Please contact us If you find any potential violation. The code is released under the Apache License 2.0. gpt4-x-alpaca-13b-native-4bit-128g | https://huggingface.co/chavinlo/alpaca-native -> https://huggingface.co/chavinlo/alpaca-13b -> https://huggingface.co/chavinlo/gpt4-x-alpaca llama-2 | https://ai.meta.com/llama/ Llama 2 is available for free for research and commercial use. 🥳

Special Thanks

Thanks to facebookresearch ❤ for https://github.com/facebookresearch/llama <br /> Thanks to lmsys ❤ for https://huggingface.co/lmsys/vicuna-13b-delta-v0 <br /> Thanks to anon8231489123 ❤ for https://huggingface.co/anon8231489123/vicuna-13b-GPTQ-4bit-128g (GPTQ 4bit quantization of: https://huggingface.co/lmsys/vicuna-13b-delta-v0) <br /> Thanks to tatsu-lab ❤ for https://github.com/tatsu-lab/stanford_alpaca <br /> Thanks to chavinlo ❤ for https://huggingface.co/chavinlo/gpt4-x-alpaca <br /> Thanks to qwopqwop200 ❤ for https://github.com/qwopqwop200/GPTQ-for-LLaMa <br /> Thanks to tsumeone ❤ for https://huggingface.co/tsumeone/gpt4-x-alpaca-13b-native-4bit-128g-cuda (GPTQ 4bit quantization of: https://huggingface.co/chavinlo/gpt4-x-alpaca) <br /> Thanks to transformers ❤ for https://github.com/huggingface/transformers <br /> Thanks to gradio-app ❤ for https://github.com/gradio-app/gradio <br /> Thanks to TheBloke ❤ for https://huggingface.co/TheBloke/stable-vicuna-13B-GPTQ <br /> Thanks to Neko-Institute-of-Science ❤ for https://huggingface.co/Neko-Institute-of-Science/pygmalion-7b <br