README.md

metadata

license: other
language:
  - en
pipeline_tag: text2text-generation
tags:
  - alpaca
  - llama
  - chat
  - gpt4
inference: false

This is a 4bit 128g GPTQ of chansung's gpt4-alpaca-lora-13b.

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-alpaca-lora-13B-GPTQ-4bit-128g.
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-alpaca-lora-13B-GPTQ-4bit-128g.
7. If you see an error in the bottom right, ignore it - it's temporary.
8. Check that the GPTQ parameters are correct 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!

Command to create was:

CUDA_VISIBLE_DEVICES=0 python3 llama.py /content/gpt4-alpaca-lora-13B-HF c4 --wbits 4 --true-sequential --act-order --groupsize 128 --save_safetensors /content/gpt4-alpaca-lora-13B-GPTQ-4bit-128g.safetensors 

Command to clone the latest Triton GPTQ-for-LLaMa repo for inference using llama_inference.py, or in text-generation-webui:

# Clone text-generation-webui, if you don't already have it
git clone https://github.com/oobabooga/text-generation-webui
# Make a repositories directory
mkdir -p text-generation-webui/repositories
cd text-generation-webui/repositories
# Clone the latest GPTQ-for-LLaMa code inside text-generation-webui
git clone https://github.com/qwopqwop200/GPTQ-for-LLaMa

There is also a no-act-order.safetensors file which will work with oobabooga's fork of GPTQ-for-LLaMa; it does not require the latest GPTQ code.

Original model card is below

This repository comes with LoRA checkpoint to make LLaMA into a chatbot like language model. The checkpoint is the output of instruction following fine-tuning process with the following settings on 8xA100(40G) DGX system.

• Training script: borrowed from the official Alpaca-LoRA implementation
• Training script:

python finetune.py \
    --base_model='decapoda-research/llama-30b-hf' \
    --data_path='alpaca_data_gpt4.json' \
    --num_epochs=10 \
    --cutoff_len=512 \
    --group_by_length \
    --output_dir='./gpt4-alpaca-lora-30b' \
    --lora_target_modules='[q_proj,k_proj,v_proj,o_proj]' \
    --lora_r=16 \
    --batch_size=... \
    --micro_batch_size=...

You can find how the training went from W&B report here.