OpenLLM-France-Claire-7B-0.1-gguf

⚠️ ARCHIVED / LEGACY MODEL NOTICE
This repository is part of a legacy collection quantized around 2023. To manage storage quotas and maintain active community projects, some rarely used quantization formats (e.g., Q2_K, Q3_K, Q4_1, Q5_1) have been permanently removed.

Only the most popular and stable formats (Q4_0, Q4_K_M, Q5_K_M, Q6_K, and Q8_0) remain available.

💡 Looking for something modern? If you are starting a new project, we highly recommend using newer architectures (like Llama 3, Mistral, or Qwen) provided by official maintainers or active community members (e.g., Bartowski, TheBloke legacy files, or official organization handles).

⚠️ This repository is no longer actively maintained. Existing files are provided "as is" for archival and legacy hardware purposes.

I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information

Claire-7B-0.1 - GGUF

• Model creator: OpenLLM-France
• Original model: Claire-7B-0.1

K-Quants in Falcon 7b models

New releases of Llama.cpp now support K-quantization for previously incompatible models, in particular all Falcon 7B models (While Falcon 40b is and always has been fully compatible with K-Quantisation). This is achieved by employing a fallback solution for model layers that cannot be quantized with real K-quants.

For Falcon 7B models, although only a quarter of the layers can be quantized with true K-quants, this approach still benefits from utilizing different legacy quantization types Q4_0, Q4_1, Q5_0, and Q5_1. As a result, it offers better quality at the same file size or smaller file sizes with comparable performance.

So this solution ensures improved performance and efficiency over legacy Q4_0, Q4_1, Q5_0 and Q5_1 Quantizations.

---

Brief

Claire is a falcon based 7B parameter causal decoder-only model built by LINAGORA and OpenLLM-France which is finetuned on French conversational open data.

OpenLLM-France provides a .gguf-converted Verison of their Model quantized with Q4-0. Here You will find a fll set of all available quantizations.

---

About GGUF format

gguf is the current file format used by the ggml library. A growing list of Software is using it and can therefore use this model. The core project making use of the ggml library is the llama.cpp project by Georgi Gerganov

Quantization variants

There is a bunch of quantized files available to cater to your specific needs. Here's how to choose the best option for you:

Legacy quants

Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are legacy quantization types. Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.

Note:

Now there's a new option to use K-quants even for previously 'incompatible' models, although this involves some fallback solution that makes them not real K-quants. More details can be found in affected model descriptions. (This mainly refers to Falcon 7b and Starcoder models)

K-quants

K-quants are designed with the idea that different levels of quantization in specific parts of the model can optimize performance, file size, and memory load. So, if possible, use K-quants. With a Q6_K, you'll likely find it challenging to discern a quality difference from the original model - ask your model two times the same question and you may encounter bigger quality differences.

---

Original Model Card:

Claire-7B-0.1

Claire-7B-0.1 is a 7B parameter causal decoder-only model built by LINAGORA and OpenLLM-France adapted from Falcon-7b on French conversational data.

Claire-7B-0.1 is a pretrained language model designed to be attuned to the dynamics of linguistic interactions in dialogue. Without further training, its expected use is to generate continuations of dialogues. Its main purpose is to serve as a base model for fine-tuning on dialogue generation (e.g., chat) and dialogue understanding (e.g., meeting summarization) tasks. Please note that due to its training, the model is prone to generate dialogues with disfluencies and other constructions common to spoken language.

• Typical usage
  • Typical prompts
• Training Details
  • Training Data
  • Training Procedure
• Evaluation
• License
• Acknowledgements
• Contact

Typical usage

import transformers
import torch

model_name = "OpenLLM-France/Claire-7B-0.1"

tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
model = transformers.AutoModelForCausalLM.from_pretrained(model_name,
    device_map="auto",
    torch_dtype=torch.bfloat16,
    load_in_4bit=True                          # For efficient inference, if supported by the GPU card
)

pipeline = transformers.pipeline("text-generation", model=model, tokenizer=tokenizer)
generation_kwargs = dict(
    num_return_sequences=1,                    # Number of variants to generate.
    return_full_text= False,                   # Do not include the prompt in the generated text.
    max_new_tokens=200,                        # Maximum length for the output text.
    do_sample=True, top_k=10, temperature=1.0, # Sampling parameters.
    pad_token_id=tokenizer.eos_token_id,       # Just to avoid a harmless warning.
)

prompt = """\
- Bonjour Dominique, qu'allez-vous nous cuisiner aujourd'hui ?
- Bonjour Camille,\
"""
completions = pipeline(prompt, **generation_kwargs)
for completion in completions:
    print(prompt + " […]" + completion['generated_text'])

This will print something like:

- Bonjour Dominique, qu'allez-vous nous cuisiner aujourd'hui ?
- Bonjour Camille, […] je vous prépare un plat de saison, une daube provençale.
- Ah je ne connais pas cette recette.
- C'est très facile à préparer, vous n'avez qu'à mettre de l'eau dans une marmite, y mettre de l'oignon émincé, des carottes coupées en petits morceaux, et vous allez mettre votre viande de bœuf coupé en petits morceaux également.
- Je n'ai jamais cuisiné de viande de bœuf, mais c'est vrai que ça a l'air bien facile.
- Vous n'avez plus qu'à laisser mijoter, et ensuite il sera temps de servir les clients.
- Très bien.

You will need at least 6GB of VRAM to run inference using 4bit quantization (16GB of VRAM without 4bit quantization).

If you have trouble running this code, make sure you have recent versions of torch, transformers and accelerate (see requirements.txt).

Typical prompts

Claire-7B-0.1 was trained on diarized French conversations. During training, the dialogues were normalized in several formats. The possible formats for expected prompts are as follows:

A monologue can be specified as a single line prompt (though keep in mind that Claire might still return a dialogue because of its training):

prompt = "Mesdames et messieurs les députés, chers collègues, bonsoir. Vous l'aurez peut-être remarqué, je cite rarement"

A dialogue between two speakers can be specified with one line per speech turn starting with a dash:

prompt = """\
- Bonjour Dominique, qu'allez-vous nous cuisiner aujourd'hui ?
- Bonjour Camille,\
"""

A dialogue or multilogue (with two or more speakers) can be specified with lines that start with [Intervenant X:] where X is a number:

prompt = """\
[Intervenant 1:] Bonjour Dominique, qu'allez-vous nous cuisiner aujourd'hui ?
[Intervenant 2:] Bonjour Camille,\
"""

A dialogue or multilogue with named speakers can be specified with lines that start with [SpeakerName:] where SpeakerName can be a first name, a first and a last name, a nickname, a title…

prompt = """\
[Mme Camille Durand:] Bonjour Dominique, qu'allez-vous nous cuisiner aujourd'hui ?
[Mr. Dominique Petit:] Bonjour Camille,\
"""

Training Details

Training Data

The training dataset will be made available soon.

Claire-7B-0.1 was tuned from Falcon-7b on the following data distribution:

Training data was augmented with the following techniques:

• varying the format used to indicate speech turns (dashes or [XXX:])
• substituting [Intervenant X:] for [SpeakerName:] or vice versa, where [SpeakerName:] might be a real name or a randomly generated name
• removing punctuation marks and/or casing (to prepare the model for transcripts produced by some Automatic Speech Recognition systems)

Long conversations were truncated at a maximum of 2048 tokens. Where possible, they were split between speaker turns.

While the model has been trained and evaluated only on French dialogues, it may be able to generate conversations in other languages from the original Falcon-7b training data.

Training Procedure

The training code will be made available soon.

Claire-7B-0.1 is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token). See Falcon-7b for more details.

Claire-7B-0.1 was trained on 1 A100 80GB GPU for about 50 GPU hours.

Hyperparameters were the following:

Evaluation

To evaluate Claire-7B-0.1’s ability to generate natural sounding, French conversations, we compared its responses to a variety of prompts with those of three other models:

• Falcon-7b,
• Mistral-7B-v0.1
• Claire-Mistral-7B-0.1 (a version of Mistral-7B-v0.1 adapted in the same fashion as Claire-7B-0.1)

We tested an even mixture of monologue and dialogue-style prompts. Each of the four generated responses was evaluated along three dimensions: Interaction, Fluency and Relevance. Evaluators were also asked to rank the four responses by preference.

Our results confirm that continual pre-training of Falcon-7b and Mistral-7B-v0.1 leads to improvement (relative to the base models) along all three evaluation dimensions and that Claire-7B-0.1 outperforms the adapted Mistral counterpart in the Fluency and Relevance categories (and in the Interaction category if we focus on dialogue-style prompts).

Ranking results also reveal a clear subjective preference for Claire-7B-0.1, as shown in the following table:

<!--| | **Claire-Falcon** | **Claire-Mistral** | **Falcon** | **Mistral** | -->

(In this table, "Claire-Falcon" stands for Claire-7B-0.1, "Falcon", for Falcon-7b, "Mistral", for Mistral-7B-v0.1 and "Claire-Mistral", for Claire-Mistral-7B-0.1.)

Please note that the model can generate disfluencies and humorous responses as a result of its training on spoken and theatrical text.

More evaluation details will be provided in a separate publication.

License

Given that some of the corpora used for training are only available under CC-BY-NC-SA licenses, Claire-7B-0.1 is made available under the CC-BY-NC-SA 4.0 license.

You can find a variant of this model published under the Apache 2.0 license at OpenLLM-France/Claire-7B-Apache-0.1.

Acknowledgements

This work was performed using HPC resources from GENCI–IDRIS (Grant 2023-AD011014561).

Claire-7B-0.1 was created by members of LINAGORA (in alphabetical order): Ismaïl Harrando, Julie Hunter, Jean-Pierre Lorré, Jérôme Louradour, Michel-Marie Maudet, Virgile Rennard, Guokan Shang.

Special thanks to partners from the OpenLLM-France community, especially Christophe Cerisara (LORIA), Pierre-Carl Langlais and Anastasia Stasenko (OpSci), and Pierre Colombo, for valuable advice.

Contact

[email protected]

End of original Model File

Please consider to support my work

Coming Soon: I'm in the process of launching a sponsorship/crowdfunding campaign for my work. I'm evaluating Kickstarter, Patreon, or the new GitHub Sponsors platform, and I am hoping for some support and contribution to the continued availability of these kind of models. Your support will enable me to provide even more valuable resources and maintain the models you rely on. Your patience and ongoing support are greatly appreciated as I work to make this page an even more valuable resource for the community.

<center>

</center>