LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Claire 7B 0.1 GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Claire 7B 0.1 GPTQ   URL Share it on

  48   
  4-bit   Autotrain compatible Base model:openllm-france/clai... Base model:quantized:openllm-f...   Conversational   Custom code   Endpoints compatible   Falcon   Fr   Gptq   Pretrained   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Claire-7B-0.1-GPTQ 

Claire 7B 0.1 GPTQ Benchmarks

LLME Score: 0.14188
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Claire 7B 0.1 GPTQ (TheBloke/Claire-7B-0.1-GPTQ)

Claire 7B 0.1 GPTQ Parameters and Internals

Model Type 
falcon, text-generation, conversational
Use Cases 
Primary Use Cases:
dialogue generation and understanding
Limitations:
disfluencies due to training on spoken language
Considerations:
Trained on French conversational data, mainly intended for dialogue.
Additional Notes 
The model is attuned to the dynamics of linguistic interactions in dialogues. Suitable for generating continuations of dialogues.
Supported Languages 
French (high)
Training Details 
Data Sources:
assemblee-nationale.fr, theatre-classique.fr, theatregratuit.com, TCOF, CFPP, CFPB, ACSYNT, PFC, Valibel (ORFEO), ESLO, CRFP, OFROM, CID, Rhapsodie, ParisStories, CLAPI, C-ORAL-ROM (ORFEO), LinTO, ESLO, SUMM-RE, LinTO, Réunions de travail (ORFEO), FreD, ESLO, Fleuron (ORFEO), Accueil UBS, OTG, ESLO, Valibel (ORFEO), LinTO, ESLO
Methodology:
Continual pre-training
Context Length:
2048
Training Time:
50 GPU hours on 1 A100 80GB GPU
Hardware Used:
1 A100 80GB GPU
Model Architecture:
Causal decoder-only
Input Output 
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Refer to Hugging Face documentation for inference tips.
LLM NameClaire 7B 0.1 GPTQ
Repository 🤗https://huggingface.co/TheBloke/Claire-7B-0.1-GPTQ 
Model NameClaire 7B 0.1
Model CreatorOpenLLM France
Base Model(s)  OpenLLM-France/Claire-7B-0.1   OpenLLM-France/Claire-7B-0.1
Model Size7b
Required VRAM4 GB
Updated2025-03-14
MaintainerTheBloke
Model Typefalcon
Model Files  4.0 GB
Supported Languagesfr
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureFalconForCausalLM
Licensecc-by-nc-sa-4.0
Context Length2048
Model Max Length2048
Transformers Version4.35.0
Is Biased0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size65024
Torch Data Typebfloat16

Best Alternatives to Claire 7B 0.1 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Falcon 7B Instruct Bnb 8bit2K / 7.2 GB151
Falcon 7B Instruct Bnb 4bit2K / 4 GB221
...n 7B Instruct Bnb 8bit Smashed0K / 7.2 GB160
F1H10M 00002K / 13.9 GB25290
Really Tiny Falcon Testing2K / 0 GB3257670
Saqr 7B Merged2K / 13.9 GB551
Tiny Testing Falcon Alibi2K / 0 GB247041
F1H10M 00002K / 13.9 GB830
... Openassistant Toxicity Reduce2K / 30.4 GB110
Falcon Chatbot2K / 5.5 GB191
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Claire-7B-0.1-GPTQ.

Rank the Claire 7B 0.1 GPTQ Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 45019 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer