---
inference: false
language:
- fr
library_name: transformers
license: other
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
---

<!-- header start -->
<div style="width: 100%;">
    <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
    <div style="display: flex; flex-direction: column; align-items: flex-start;">
        <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
    </div>
    <div style="display: flex; flex-direction: column; align-items: flex-end;">
        <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
    </div>
</div>
<!-- header end -->

# Vigogne 2 7B Chat - GGML
- Model creator: [bofenghuang](https://huggingface.co/bofenghuang)
- Original model: [Vigogne 2 7B Chat](https://huggingface.co/bofenghuang/vigogne-2-7b-chat)

## Description

This repo contains GGML format model files for [bofenghuang's Vigogne 2 7B Chat](https://huggingface.co/bofenghuang/vigogne-2-7b-chat).

GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most popular web UI. Supports NVidia CUDA GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a powerful GGML web UI with GPU acceleration on all platforms (CUDA and OpenCL). Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), a fully featured local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with CUDA GPU acceleration via the c_transformers backend.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.

## Repositories available

* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGML)
* [bofenghuang's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/bofenghuang/vigogne-2-7b-chat)

## 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|>:
```

<!-- compatibility_ggml start -->
## Compatibility

These quantised GGML files are compatible with llama.cpp as of June 6th, commit `2d43387`.

They should also be compatible with all UIs, libraries and utilities which use GGML.

## Explanation of the new k-quant methods
<details>
  <summary>Click to see details</summary>

The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.

Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_ggml end -->

## Provided files

| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [vigogne-2-7b-chat.ggmlv3.q2_K.bin](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGML/blob/main/vigogne-2-7b-chat.ggmlv3.q2_K.bin) | q2_K | 2 | 2.87 GB| 5.37 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| [vigogne-2-7b-chat.ggmlv3.q3_K_L.bin](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGML/blob/main/vigogne-2-7b-chat.ggmlv3.q3_K_L.bin) | q3_K_L | 3 | 3.60 GB| 6.10 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| [vigogne-2-7b-chat.ggmlv3.q3_K_M.bin](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGML/blob/main/vigogne-2-7b-chat.ggmlv3.q3_K_M.bin) | q3_K_M | 3 | 3.28 GB| 5.78 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| [vigogne-2-7b-chat.ggmlv3.q3_K_S.bin](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGML/blob/main/vigogne-2-7b-chat.ggmlv3.q3_K_S.bin) | q3_K_S | 3 | 2.95 GB| 5.45 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| [vigogne-2-7b-chat.ggmlv3.q4_0.bin](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGML/blob/main/vigogne-2-7b-chat.ggmlv3.q4_0.bin) | q4_0 | 4 | 3.83 GB| 6.33 GB | Original quant method, 4-bit. |
| [vigogne-2-7b-chat.ggmlv3.q4_1.bin](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGML/blob/main/vigogne-2-7b-chat.ggmlv3.q4_1.bin) | q4_1 | 4 | 4.24 GB| 6.74 GB | Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| [vigogne-2-7b-chat.ggmlv3.q4_K_M.bin](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGML/blob/main/vigogne-2-7b-chat.ggmlv3.q4_K_M.bin) | q4_K_M | 4 | 4.08 GB| 6.58 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
| [vigogne-2-7b-chat.ggmlv3.q4_K_S.bin](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGML/blob/main/vigogne-2-7b-chat.ggmlv3.q4_K_S.bin) | q4_K_S | 4 | 3.83 GB| 6.33 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| [vigogne-2-7b-chat.ggmlv3.q5_0.bin](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGML/blob/main/vigogne-2-7b-chat.ggmlv3.q5_0.bin) | q5_0 | 5 | 4.65 GB| 7.15 GB | Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| [vigogne-2-7b-chat.ggmlv3.q5_1.bin](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGML/blob/main/vigogne-2-7b-chat.ggmlv3.q5_1.bin) | q5_1 | 5 | 5.06 GB| 7.56 GB | Original quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| [vigogne-2-7b-chat.ggmlv3.q5_K_M.bin](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGML/blob/main/vigogne-2-7b-chat.ggmlv3.q5_K_M.bin) | q5_K_M | 5 | 4.78 GB| 7.28 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
| [vigogne-2-7b-chat.ggmlv3.q5_K_S.bin](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGML/blob/main/vigogne-2-7b-chat.ggmlv3.q5_K_S.bin) | q5_K_S | 5 | 4.65 GB| 7.15 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| [vigogne-2-7b-chat.ggmlv3.q6_K.bin](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGML/blob/main/vigogne-2-7b-chat.ggmlv3.q6_K.bin) | q6_K | 6 | 5.53 GB| 8.03 GB | New k-quant method. Uses GGML_TYPE_Q8_K for all tensors - 6-bit quantization |
| [vigogne-2-7b-chat.ggmlv3.q8_0.bin](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGML/blob/main/vigogne-2-7b-chat.ggmlv3.q8_0.bin) | q8_0 | 8 | 7.13 GB| 9.63 GB | Original quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |

**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.

## How to run in `llama.cpp`

I use the following command line; adjust for your tastes and needs:

```
./main -t 10 -ngl 32 -m vigogne-2-7b-chat.ggmlv3.q4_K_M.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:"
```
Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`.

Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

Change `-c 2048` to the desired sequence length for this model. For example, `-c 4096` for a Llama 2 model.  For models that use RoPE, add `--rope-freq-base 10000 --rope-freq-scale 0.5` for doubled context, or `--rope-freq-base 10000 --rope-freq-scale 0.25` for 4x context.

If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`

For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)

## How to run in `text-generation-webui`

Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).

<!-- footer start -->
## Discord

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

[TheBloke AI's Discord server](https://discord.gg/theblokeai)

## Thanks, and how to contribute.

Thanks to the [chirper.ai](https://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

**Special thanks to**: Luke from CarbonQuill, Aemon Algiz.

**Patreon special mentions**: Willem Michiel, Ajan Kanaga, Cory Kujawski, Alps Aficionado, Nikolai Manek, Jonathan Leane, Stanislav Ovsiannikov, Michael Levine, Luke Pendergrass, Sid, K, Gabriel Tamborski, Clay Pascal, Kalila, William Sang, Will Dee, Pieter, Nathan LeClaire, ya boyyy, David Flickinger, vamX, Derek Yates, Fen Risland, Jeffrey Morgan, webtim, Daniel P. Andersen, Chadd, Edmond Seymore, Pyrater, Olusegun Samson, Lone Striker, biorpg, alfie_i, Mano Prime, Chris Smitley, Dave, zynix, Trenton Dambrowitz, Johann-Peter Hartmann, Magnesian, Spencer Kim, John Detwiler, Iucharbius, Gabriel Puliatti, LangChain4j, Luke @flexchar, Vadim, Rishabh Srivastava, Preetika Verma, Ai Maven, Femi Adebogun, WelcomeToTheClub, Leonard Tan, Imad Khwaja, Steven Wood, Stefan Sabev, Sebastain Graf, usrbinkat, Dan Guido, Sam, Eugene Pentland, Mandus, transmissions 11, Slarti, Karl Bernard, Spiking Neurons AB, Artur Olbinski, Joseph William Delisle, ReadyPlayerEmma, Olakabola, Asp the Wyvern, Space Cruiser, Matthew Berman, Randy H, subjectnull, danny, John Villwock, Illia Dulskyi, Rainer Wilmers, theTransient, Pierre Kircher, Alexandros Triantafyllidis, Viktor Bowallius, terasurfer, Deep Realms, SuperWojo, senxiiz, Oscar Rangel, Alex, Stephen Murray, Talal Aujan, Raven Klaugh, Sean Connelly, Raymond Fosdick, Fred von Graf, chris gileta, Junyu Yang, Elle


Thank you to all my generous patrons and donaters!

<!-- footer end -->

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


<p align="center" width="100%">
<img src="https://huggingface.co/bofenghuang/vigogne-2-7b-chat/resolve/main/vigogne_logo.png" alt="Vigogne" style="width: 40%; min-width: 300px; display: block; margin: auto;">
</p>

# Vigogne-2-7B-Chat: A Llama-2 based French chat model

Vigogne-2-7B-Chat is a model based on [LLaMA-2-7B](https://ai.meta.com/llama) that has been fine-tuned to conduct multi-turn dialogues in French between human user and AI assistant.

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

**Usage and License Notices**: Vigogne-2-7B-Chat follows the same usage policy as Llama-2, which can be found [here](https://ai.meta.com/llama/use-policy).

## Usage

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

model_name_or_path = "bofenghuang/vigogne-2-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, padding_side="right", use_fast=False)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, torch_dtype=torch.float16, device_map="auto")

user_query = "Expliquez la différence entre DoS et phishing."
prompt = generate_inference_chat_prompt([[user_query, ""]], tokenizer=tokenizer)
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=0.1,
        do_sample=True,
        repetition_penalty=1.0,
        max_new_tokens=512,
    ),
    return_dict_in_generate=True,
)
generated_tokens = generated_outputs.sequences[0, input_length:]
generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)
print(generated_text)
```

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

<a href="https://colab.research.google.com/github/bofenghuang/vigogne/blob/main/notebooks/infer_chat.ipynb" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>

## 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.