LLM Explorer: A Curated Large Language Model Directory and Analytics  // 

Claire 7B 0.1 GPTQ by TheBloke

What open-source LLMs or SLMs are you in search of? 18732 in total.

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

  4-bit   Autotrain compatible Base model:openllm-france/clai...   Conversational   Custom code   Endpoints compatible   Falcon   Fr   Gptq   License:cc-by-nc-sa-4.0   Pretrained   Quantized   Region:us   Safetensors

Rank the Claire 7B 0.1 GPTQ Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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  
Claire 7B 0.1 GPTQ (TheBloke/Claire-7B-0.1-GPTQ)

Best Alternatives to Claire 7B 0.1 GPTQ

Best Alternatives
HF Rank
Tiny Random Falcon 7B2K /  GB60
Tiny Testing Falcon Alibi2K / 0 GB87971
Really Tiny Falcon Testing2K / 0 GB509950
Quantized Falcon 7B2K / 4.2 GB250
Claire 7B 0.1 AWQ2K / 4.8 GB400
Claire 7B 0.1 Instruct2K / 7.2 GB181
Test Falcon St2K / 13.8 GB50
...Tyellow 90pct 2048 Cutoff 70002K / 13.8 GB50
...Resp Tag Packing 100samp 1epch2K / 13.8 GB50
...n 7B Tyellow 90pct 2048 Cutoff2K / 13.8 GB50

Claire 7B 0.1 GPTQ Parameters and Internals

LLM NameClaire 7B 0.1 GPTQ
RepositoryOpen on ๐Ÿค— 
Model NameClaire 7B 0.1
Model CreatorOpenLLM France
Base Model(s)  Claire 7B 0.1   OpenLLM-France/Claire-7B-0.1
Model Size7b
Required VRAM4 GB
Model Typefalcon
Model Files  4 GB
Supported Languagesfr
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureFalconForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.35.0
Is Biased0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size65024
Initializer Range0.02
Torch Data Typebfloat16
Layer Norm Epsilon1.0E-5
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003