Chat & support: my new Discord server

Want to contribute? TheBloke's Patreon page

Vigogne Instruct 13B - A French instruction-following LLaMa model GPTQ

These files are GPTQ 4bit model files for Vigogne Instruct 13B - A French instruction-following LLaMa model .

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

Other repositories available

• 4-bit GPTQ models for GPU inference
• 4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference
• Unquantised fp16 model in HF format

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

Open the text-generation-webui UI as normal.

Provided files

Compatible file - Vigogne-Instruct-13B-GPTQ-4bit-128g.no-act-order.safetensors

In the main branch you will find Vigogne-Instruct-13B-GPTQ-4bit-128g.no-act-order.safetensors

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

It was created with groupsize 128 to ensure higher quality inference, without --act-order parameter to maximise compatibility.

• Vigogne-Instruct-13B-GPTQ-4bit-128g.no-act-order.safetensors
  • Works with all versions of GPTQ-for-LLaMa code, both Triton and CUDA branches
  • Works with AutoGPTQ
  • Works with text-generation-webui one-click-installers
  • Parameters: Groupsize = 128. No act-order.
  • Command used to create the GPTQ:

    python llama.py /workspace/process/TheBloke_Vigogne-Instruct-13B-GGML/HF  wikitext2 --wbits 4 --true-sequential --groupsize 128 --save_safetensors /workspace/process/TheBloke_Vigogne-Instruct-13B-GGML/gptq/Vigogne-Instruct-13B-GPTQ-4bit-128g.no-act-order.safetensors
    

Discord

For further support, and discussions on these models and AI in general, join us at:

TheBloke AI's Discord server

Thanks, and how to contribute.

Thanks to the chirper.ai team!

I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.

If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.

Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.

• Patreon: https://patreon.com/TheBlokeAI
• Ko-Fi: https://ko-fi.com/TheBlokeAI

Patreon special mentions : Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.

Thank you to all my generous patrons and donaters!

Original model card

Vigogne-instruct-13b: A French Instruction-following LLaMA Model

Vigogne-instruct-13b is a LLaMA-13B model fine-tuned to follow the ?? French instructions.

For more information, please visit the Github repo: https://github.com/bofenghuang/vigogne

Usage and License Notices : Same as Stanford Alpaca , Vigogne is intended and licensed for research use only. The dataset is CC BY NC 4.0 (allowing only non-commercial use) and models trained using the dataset should not be used outside of research purposes.

Usage

This repo only contains the low-rank adapter. In order to access the complete model, you also need to load the base LLM model and tokenizer.

from peft import PeftModel
from transformers import LlamaForCausalLM, LlamaTokenizer

base_model_name_or_path = "name/or/path/to/hf/llama/13b/model"
lora_model_name_or_path = "bofenghuang/vigogne-instruct-13b"

tokenizer = LlamaTokenizer.from_pretrained(base_model_name_or_path, padding_side="right", use_fast=False)
model = LlamaForCausalLM.from_pretrained(
    base_model_name_or_path,
    load_in_8bit=True,
    torch_dtype=torch.float16,
    device_map="auto",
)
model = PeftModel.from_pretrained(model, lora_model_name_or_path)

You can infer this model by using the following Google Colab Notebook.

Limitations

Vigogne is still under development, and there are many limitations that have to be addressed. Please note that it is possible that the model generates harmful or biased content, incorrect information or generally unhelpful answers.