Hugging Face's logo

TheBloke
/
gpt4-x-vicuna-13B-GPTQ

Text Generation
Transformers
Safetensors
llama
text-generation-inference
4-bit precision
gptq
Model card Files Community
2
gpt4-x-vicuna-13B-GPTQ / README.md
TheBloke's picture
TheBloke
Update README.md
023a3de
preview code
|
raw
history blame
3.41 kB
metadata
license: gpl
inference: false

gpt4-x-vicuna-13B-GPTQ

This repo contains 4bit GPTQ format quantised models of NousResearch's gpt4-x-vicuna-13b.

It is the result of quantising to 4bit using GPTQ-for-LLaMa.

Repositories available

How to easily download and use this model in text-generation-webui

Open the text-generation-webui UI as normal.

  1. Click the Model tab.
  2. Under Download custom model or LoRA, enter TheBloke/gpt4-x-vicuna-13B-GPTQ.
  3. Click Download.
  4. Wait until it says it's finished downloading.
  5. Click the Refresh icon next to Model in the top left.
  6. In the Model drop-down: choose the model you just downloaded, gpt4-x-vicuna-13B-GPTQ.
  7. If you see an error in the bottom right, ignore it - it's temporary.
  8. Fill out the GPTQ parameters on the right: Bits = 4, Groupsize = 128, model_type = Llama
  9. Click Save settings for this model in the top right.
  10. Click Reload the Model in the top right.
  11. Once it says it's loaded, click the Text Generation tab and enter a prompt!

Provided files

Compatible file - GPT4-x-Vicuna-13B-GPTQ-4bit-128g.compat.act-order.safetensors

In the main branch - the default one - you will find GPT4-x-Vicuna-13B-GPTQ-4bit-128g.compat.act-order.safetensors

This will work with all versions of GPTQ-for-LLaMa. It has maximum compatibility

It was created without the --act-order parameter. It may have slightly lower inference quality compared to the other file, but is guaranteed to work on all versions of GPTQ-for-LLaMa and text-generation-webui.

  • GPT4-x-Vicuna-13B-GPTQ-4bit-128g.compat.act-order.safetensors
    • Works with all versions of GPTQ-for-LLaMa code, both Triton and CUDA branches
    • Works with text-generation-webui one-click-installers
    • Parameters: Groupsize = 128g. No act-order.
    • Command used to create the GPTQ:
      CUDA_VISIBLE_DEVICES=0 python3 llama.py GPT4All-13B-snoozy c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors GPT4-x-Vicuna-13B-GPTQ-4bit-128g.compat.act-order.safetensors

Original model card

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, 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.

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/