NousResearch/GPT4-x-Vicuna-13b-fp16
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
main
GPT4-x-Vicuna-13b-fp16/README.md
ModelHub XC 3832a9de68 初始化项目，由ModelHub XC社区提供模型 
Model: NousResearch/GPT4-x-Vicuna-13b-fp16
Source: Original Platform
2026-06-07 21:46:12 +08:00

1.0 KiB
Raw Permalink Blame History

license
license
gpl

As a base model used https://huggingface.co/eachadea/vicuna-13b-1.1

Finetuned on Teknium's GPTeacher dataset, unreleased Roleplay v2 dataset, GPT-4-LLM dataset Uncensored, WizardLM 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.

Nous Research Instruct Dataset will be released soon.

Prompt format is Alpaca:

### Instruction:

### Response:

or

### Instruction:

### Input:

### Response:

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/