|
--- |
|
license: gpl |
|
inference: false |
|
--- |
|
|
|
# gpt4-x-vicuna-13B-GPTQ |
|
|
|
This repo contains 4bit GPTQ format quantised models of [NousResearch's gpt4-x-vicuna-13b](https://huggingface.co/NousResearch/gpt4-x-vicuna-13b). |
|
|
|
It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa). |
|
|
|
## Repositories available |
|
|
|
* [4bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/gpt4-x-vicuna-13B-GPTQ). |
|
* [4bit and 5bit GGML models for CPU inference](https://huggingface.co/TheBloke/gpt4-x-vicuna-13B-GGML). |
|
* [float16 model in HF format for GPU inference](https://huggingface.co/TheBloke/gpt4-x-vicuna-13B-HF). |
|
|
|
## 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/ |
