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/