| license: gpl | |
| language: | |
| - en | |
| This is the GPTQ 4Bit Groupsize 128 Pre-Quantized Model, for the full model in fp32, visit https://huggingface.co/NousResearch/gpt4-x-vicuna-13b | |
| As a base model used https://huggingface.co/eachadea/vicuna-13b-1.1 | |
| Finetuned on Teknium's GPTeacher dataset, Teknium's unreleased Roleplay v2 dataset, WizardLM Uncensored, GPT-4-LLM Uncensored, and Nous Research Instruct Dataset | |
| Approx 180k instructions, all from GPT-4, all cleaned of any OpenAI censorship/"As an AI Language Model" etc. | |
| Base model still has OpenAI censorship. Soon, a new version will be released with cleaned vicuna from https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltere | |
| Trained on 8 A100-80GB GPUs for 5 epochs following Alpaca deepspeed training code. | |
| Prompt format is Alpaca: | |
| ``` | |
| ### Instruction: | |
| ### Response: | |
| ``` | |
| or | |
| ``` | |
| ### Instruction: | |
| ### Input: | |
| ### Response: | |
| ``` | |
| Nous Research Instruct Dataset will be released soon. | |
| GPTeacher, Roleplay v2 by https://huggingface.co/teknium | |
| Wizard LM by https://github.com/nlpxucan | |
| Nous Research Instruct Dataset by https://huggingface.co/karan4d and https://huggingface.co/huemin | |
| Compute provided by our project sponsor https://redmond.ai/ |