Hugging Face's logo

TheBloke
/
Vigogne-2-7B-Chat-GPTQ

Text Generation
Transformers
Safetensors
French
llama
LLM
llama-2
text-generation-inference
4-bit precision
gptq
Model card Files Community
Vigogne-2-7B-Chat-GPTQ / README.md
TheBloke's picture
TheBloke
Upload README.md
f0a60c5
preview code
|
raw
history blame
20.3 kB
metadata
inference: false
language:
  - fr
library_name: transformers
license: llama2
model_creator: bofenghuang
model_link: https://huggingface.co/bofenghuang/vigogne-2-7b-chat
model_name: Vigogne 2 7B Chat
model_type: llama
pipeline_tag: text-generation
quantized_by: TheBloke
tags:
  - LLM
  - llama
  - llama-2
TheBlokeAI

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)

Vigogne 2 7B Chat - GPTQ

Description

This repo contains GPTQ model files for bofenghuang's Vigogne 2 7B Chat.

Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.

Repositories available

Prompt template: Vigogne-Chat 

Below is a conversation between a user and an AI assistant named Vigogne.
Vigogne is polite, emotionally aware, humble-but-knowledgeable, always providing helpful and detailed answers.
Vigogne is skilled in responding proficiently in the languages its users use and can perform a wide range of tasks such as text editing, translation, question answering, logical reasoning, coding, and many others.
Vigogne cannot receive or generate audio or visual content and cannot access the internet.
Vigogne strictly avoids discussing sensitive, offensive, illegal, ethical, or political topics and caveats when unsure of the answer.

<|UTILISATEUR|>: {prompt}
<|ASSISTANT|>:

Provided files and GPTQ parameters

Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.

Each separate quant is in a different branch. See below for instructions on fetching from different branches.

All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches are made with AutoGPTQ. Files in the main branch which were uploaded before August 2023 were made with GPTQ-for-LLaMa.

Explanation of GPTQ parameters
  • Bits: The bit size of the quantised model.
  • GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
  • Act Order: True or False. Also known as desc_act. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
  • Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
  • GPTQ dataset: The dataset used for quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
  • Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
  • ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
Branch Bits GS Act Order Damp % GPTQ Dataset Seq Len Size ExLlama Desc
main 4 128 No 0.1 French news 4096 3.90 GB Yes Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options.
gptq-4bit-32g-actorder_True 4 32 Yes 0.1 French news 4096 4.28 GB Yes 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed.
gptq-4bit-64g-actorder_True 4 64 Yes 0.1 French news 4096 4.02 GB Yes 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed.
gptq-4bit-128g-actorder_True 4 128 Yes 0.1 French news 4096 3.90 GB Yes 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed.
gptq-8bit--1g-actorder_True 8 None Yes 0.1 French news 4096 7.01 GB No 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed.
gptq-8bit-128g-actorder_False 8 128 No 0.1 French news 4096 7.16 GB No 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed.
gptq-8bit-128g-actorder_True 8 128 Yes 0.1 French news 4096 7.16 GB No 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed.
gptq-8bit-64g-actorder_True 8 64 Yes 0.1 French news 4096 7.31 GB No 8-bit, with group size 64g and Act Order for even higher inference quality. Poor AutoGPTQ CUDA speed.

How to download from branches

  • In text-generation-webui, you can add :branch to the end of the download name, eg TheBloke/Vigogne-2-7B-Chat-GPTQ:gptq-4bit-32g-actorder_True
  • With Git, you can clone a branch with:
git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ
  • In Python Transformers code, the branch is the revision parameter; see below.

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

Please make sure you're using the latest version of text-generation-webui.

It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.

  1. Click the Model tab.
  2. Under Download custom model or LoRA, enter TheBloke/Vigogne-2-7B-Chat-GPTQ.
  • To download from a specific branch, enter for example TheBloke/Vigogne-2-7B-Chat-GPTQ:gptq-4bit-32g-actorder_True
  • see Provided Files above for the list of branches for each option.
  1. Click Download.
  2. The model will start downloading. Once it's finished it will say "Done".
  3. In the top left, click the refresh icon next to Model.
  4. In the Model dropdown, choose the model you just downloaded: Vigogne-2-7B-Chat-GPTQ
  5. The model will automatically load, and is now ready for use!
  6. If you want any custom settings, set them and then click Save settings for this model followed by Reload the Model in the top right.
  • Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file quantize_config.json.
  1. Once you're ready, click the Text Generation tab and enter a prompt to get started!

How to use this GPTQ model from Python code

Install the necessary packages

Requires: Transformers 4.32.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.

pip3 install transformers>=4.32.0 optimum>=1.12.0
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/  # Use cu117 if on CUDA 11.7

If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:

pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
pip3 install .

For CodeLlama models only: you must use Transformers 4.33.0 or later.

If 4.33.0 is not yet released when you read this, you will need to install Transformers from source:

pip3 uninstall -y transformers
pip3 install git+https://github.com/huggingface/transformers.git

You can then use the following code 

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

model_name_or_path = "TheBloke/Vigogne-2-7B-Chat-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-32g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             torch_dtype=torch.float16,
                                             device_map="auto",
                                             revision="main")

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)

prompt = "Tell me about AI"
prompt_template=f'''Below is a conversation between a user and an AI assistant named Vigogne.
Vigogne is polite, emotionally aware, humble-but-knowledgeable, always providing helpful and detailed answers.
Vigogne is skilled in responding proficiently in the languages its users use and can perform a wide range of tasks such as text editing, translation, question answering, logical reasoning, coding, and many others.
Vigogne cannot receive or generate audio or visual content and cannot access the internet.
Vigogne strictly avoids discussing sensitive, offensive, illegal, ethical, or political topics and caveats when unsure of the answer.

<|UTILISATEUR|>: {prompt}
<|ASSISTANT|>: 

'''

print("\n\n*** Generate:")

input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))

# Inference can also be done using transformers' pipeline

print("*** Pipeline:")
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    max_new_tokens=512,
    temperature=0.7,
    top_p=0.95,
    repetition_penalty=1.15
)

print(pipe(prompt_template)[0]['generated_text'])

Compatibility

The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with Occ4m's GPTQ-for-LLaMa fork.

ExLlama is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.

Huggingface Text Generation Inference (TGI) is compatible with all GPTQ models.

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.

Special thanks to: Aemon Algiz.

Patreon special mentions: Russ Johnson, J, alfie_i, Alex, NimbleBox.ai, Chadd, Mandus, Nikolai Manek, Ken Nordquist, ya boyyy, Illia Dulskyi, Viktor Bowallius, vamX, Iucharbius, zynix, Magnesian, Clay Pascal, Pierre Kircher, Enrico Ros, Tony Hughes, Elle, Andrey, knownsqashed, Deep Realms, Jerry Meng, Lone Striker, Derek Yates, Pyrater, Mesiah Bishop, James Bentley, Femi Adebogun, Brandon Frisco, SuperWojo, Alps Aficionado, Michael Dempsey, Vitor Caleffi, Will Dee, Edmond Seymore, usrbinkat, LangChain4j, Kacper Wikieł, Luke Pendergrass, John Detwiler, theTransient, Nathan LeClaire, Tiffany J. Kim, biorpg, Eugene Pentland, Stanislav Ovsiannikov, Fred von Graf, terasurfer, Kalila, Dan Guido, Nitin Borwankar, 阿明, Ai Maven, John Villwock, Gabriel Puliatti, Stephen Murray, Asp the Wyvern, danny, Chris Smitley, ReadyPlayerEmma, S_X, Daniel P. Andersen, Olakabola, Jeffrey Morgan, Imad Khwaja, Caitlyn Gatomon, webtim, Alicia Loh, Trenton Dambrowitz, Swaroop Kallakuri, Erik Bjäreholt, Leonard Tan, Spiking Neurons AB, Luke @flexchar, Ajan Kanaga, Thomas Belote, Deo Leter, RoA, Willem Michiel, transmissions 11, subjectnull, Matthew Berman, Joseph William Delisle, David Ziegler, Michael Davis, Johann-Peter Hartmann, Talal Aujan, senxiiz, Artur Olbinski, Rainer Wilmers, Spencer Kim, Fen Risland, Cap'n Zoog, Rishabh Srivastava, Michael Levine, Geoffrey Montalvo, Sean Connelly, Alexandros Triantafyllidis, Pieter, Gabriel Tamborski, Sam, Subspace Studios, Junyu Yang, Pedro Madruga, Vadim, Cory Kujawski, K, Raven Klaugh, Randy H, Mano Prime, Sebastain Graf, Space Cruiser

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: bofenghuang's Vigogne 2 7B Chat

Vigogne

Vigogne-2-7B-Chat-V2.0: A Llama-2 based French chat LLM

Vigogne-2-7B-Chat-V2.0 is a French chat LLM, based on LLaMA-2-7B, optimized to generate helpful and coherent responses in user conversations.

Check out our blog and GitHub repository for more information.

Usage and License Notices: Vigogne-2-7B-Chat-V2.0 follows Llama-2's usage policy. A significant portion of the training data is distilled from GPT-3.5-Turbo and GPT-4, kindly use it cautiously to avoid any violations of OpenAI's terms of use.

Changelog

All previous versions are accessible through branches.

  • V1.0: Trained on 420K chat data.
  • V2.0: Trained on 520K data. Check out our blog for more details.

Usage 

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig, TextStreamer
from vigogne.preprocess import generate_inference_chat_prompt

model_name_or_path = "bofenghuang/vigogne-2-7b-chat"
revision = "v2.0"

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, revision=revision, padding_side="right", use_fast=False)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, revision=revision, torch_dtype=torch.float16, device_map="auto")

streamer = TextStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)


def infer(
    utterances,
    system_message=None,
    temperature=0.1,
    top_p=1.0,
    top_k=0,
    repetition_penalty=1.1,
    max_new_tokens=1024,
    **kwargs,
):
    prompt = generate_inference_chat_prompt(utterances, tokenizer, system_message=system_message)
    input_ids = tokenizer(prompt, return_tensors="pt")["input_ids"].to(model.device)
    input_length = input_ids.shape[1]

    generated_outputs = model.generate(
        input_ids=input_ids,
        generation_config=GenerationConfig(
            temperature=temperature,
            do_sample=temperature > 0.0,
            top_p=top_p,
            top_k=top_k,
            repetition_penalty=repetition_penalty,
            max_new_tokens=max_new_tokens,
            eos_token_id=tokenizer.eos_token_id,
            pad_token_id=tokenizer.pad_token_id,
            **kwargs,
        ),
        streamer=streamer,
        return_dict_in_generate=True,
    )
    generated_tokens = generated_outputs.sequences[0, input_length:]
    generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)
    return generated_text


user_query = "Expliquez la différence entre DoS et phishing."
infer([[user_query, ""]])

You can utilize the Google Colab Notebook below for inferring with the Vigogne chat models.

Open In Colab

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.