TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)
Claire 7B 0.1 - GGUF
- Model creator: OpenLLM France
- Original model: Claire 7B 0.1
Description
This repo contains GGUF format model files for OpenLLM France's Claire 7B 0.1.
These files were quantised using hardware kindly provided by Massed Compute.
About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
- llama.cpp. The source project for GGUF. Offers a CLI and a server option.
- text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
- KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
- LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
- LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
- Faraday.dev, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
- ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
- llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
- candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.
Repositories available
- AWQ model(s) for GPU inference.
- GPTQ models for GPU inference, with multiple quantisation parameter options.
- 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
- OpenLLM France's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions
Prompt template: OpenLLM-France
- Bonjour BotName, {prompt}
- Bonjour UserName,
Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
Explanation of quantisation methods
Click to see details
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
Refer to the Provided Files table below to see what files use which methods, and how.
Provided files
Name | Quant method | Bits | Size | Max RAM required | Use case |
---|---|---|---|---|---|
claire-7b-0.1.Q2_K.gguf | Q2_K | 2 | 4.02 GB | 6.52 GB | smallest, significant quality loss - not recommended for most purposes |
claire-7b-0.1.Q3_K_S.gguf | Q3_K_S | 3 | 4.13 GB | 6.63 GB | very small, high quality loss |
claire-7b-0.1.Q4_0.gguf | Q4_0 | 4 | 4.21 GB | 6.71 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
claire-7b-0.1.Q3_K_M.gguf | Q3_K_M | 3 | 4.37 GB | 6.87 GB | very small, high quality loss |
claire-7b-0.1.Q3_K_L.gguf | Q3_K_L | 3 | 4.56 GB | 7.06 GB | small, substantial quality loss |
claire-7b-0.1.Q4_K_S.gguf | Q4_K_S | 4 | 4.75 GB | 7.25 GB | small, greater quality loss |
claire-7b-0.1.Q4_K_M.gguf | Q4_K_M | 4 | 4.98 GB | 7.48 GB | medium, balanced quality - recommended |
claire-7b-0.1.Q5_0.gguf | Q5_0 | 5 | 5.08 GB | 7.58 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
claire-7b-0.1.Q5_K_S.gguf | Q5_K_S | 5 | 5.34 GB | 7.84 GB | large, low quality loss - recommended |
claire-7b-0.1.Q5_K_M.gguf | Q5_K_M | 5 | 5.73 GB | 8.23 GB | large, very low quality loss - recommended |
claire-7b-0.1.Q6_K.gguf | Q6_K | 6 | 7.03 GB | 9.53 GB | very large, extremely low quality loss |
claire-7b-0.1.Q8_0.gguf | Q8_0 | 8 | 7.67 GB | 10.17 GB | very large, extremely low quality loss - not recommended |
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 download GGUF files
Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
In text-generation-webui
Under Download Model, you can enter the model repo: TheBloke/Claire-7B-0.1-GGUF and below it, a specific filename to download, such as: claire-7b-0.1.Q4_K_M.gguf.
Then click Download.
On the command line, including multiple files at once
I recommend using the huggingface-hub
Python library:
pip3 install huggingface-hub
Then you can download any individual model file to the current directory, at high speed, with a command like this:
huggingface-cli download TheBloke/Claire-7B-0.1-GGUF claire-7b-0.1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
More advanced huggingface-cli download usage
You can also download multiple files at once with a pattern:
huggingface-cli download TheBloke/Claire-7B-0.1-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
For more documentation on downloading with huggingface-cli
, please see: HF -> Hub Python Library -> Download files -> Download from the CLI.
To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer
:
pip3 install hf_transfer
And set environment variable HF_HUB_ENABLE_HF_TRANSFER
to 1
:
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Claire-7B-0.1-GGUF claire-7b-0.1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
Windows Command Line users: You can set the environment variable by running set HF_HUB_ENABLE_HF_TRANSFER=1
before the download command.
Example llama.cpp
command
Make sure you are using llama.cpp
from commit d0cee0d or later.
./main -ngl 32 -m claire-7b-0.1.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "- Bonjour BotName, {prompt}\n- Bonjour UserName,"
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 extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
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
How to run in text-generation-webui
Further instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model Tab.md.
How to run from Python code
You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries.
How to load this model in Python code, using ctransformers
First install the package
Run one of the following commands, according to your system:
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
Simple ctransformers example code
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/Claire-7B-0.1-GGUF", model_file="claire-7b-0.1.Q4_K_M.gguf", model_type="falcon", gpu_layers=50)
print(llm("AI is going to"))
How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
Discord
For further support, and discussions on these models and AI in general, join us at:
Thanks, and how to contribute
Thanks to the chirper.ai team!
Thanks to Clay from gpus.llm-utils.org!
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: Aemon Algiz.
Patreon special mentions: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
Original model card: OpenLLM France's Claire 7B 0.1
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
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
Claire-7B-0.1 was tuned from Falcon-7b on the following data distribution:
Data type | Words | Training Sampling Weight | Sources |
---|---|---|---|
Parliamentary Proceedings | 135M | 35% | assemblee-nationale.fr |
Theatre | 16M | 18% | theatre-classique.fr, theatregratuit.com |
Interviews | 6.4M | 29% | TCOF, CFPP, CFPB, ACSYNT, PFC, Valibel (ORFEO), ESLO |
Free Conversations | 2.2M | 10% | CRFP, OFROM, CID, Rhapsodie, ParisStories, PFC, CLAPI, C-ORAL-ROM (ORFEO), LinTO, ESLO |
Meetings | 1.2M | 5% | SUMM-RE, LinTO, Réunions de travail (ORFEO) |
Debates | 402k | <2% | FreD, ESLO |
Assistance | 159k | <1% | Fleuron (ORFEO), Accueil UBS, OTG, ESLO |
Presentation, Formal Address | 86k | <0.5% | Valibel (ORFEO), LinTO, ESLO |
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
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:
Hyperparameter | Value |
---|---|
Precision | bfloat16 |
Optimizer | AdamW |
Learning rate | 1e-4 |
Weight decay | 1e-2 |
Batch size | 132 |
LoRA rank | 16 |
LoRA alpha | 32 |
Dropout | 0.05 |
gradient clipping | 1 |
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:
... over Claire-Falcon |
... over Claire-Mistral |
... over Falcon |
... over Mistral |
|
---|---|---|---|---|
prefer Claire-Falcon ... |
62.2% | 63.9% | 83.8% | |
prefer Claire-Mistral ... |
34.8% | 56.2% | 75.3% | |
prefer Falcon ... |
36.1% | 43.8% | 81.4% | |
prefer Mistral ... |
16.2% | 24.7% | 18.6% |
(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
- Downloads last month
- 298