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 Instruct by PhilSad

 »  All LLMs  »  PhilSad  »  Claire 7B 0.1 Instruct   URL Share it on

  450   
  8-bit   Autotrain compatible Base model:openllm-france/clai... Base model:quantized:openllm-f...   Bitsandbytes Dataset:philsad/alpaca french ...   Endpoints compatible   Falcon   Finetuned   Fr   Instruct   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/PhilSad/Claire-7b-0.1-instruct 

Claire 7B 0.1 Instruct Benchmarks

LLME Score: 0.18883
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 Instruct (PhilSad/Claire-7b-0.1-instruct)

Claire 7B 0.1 Instruct Parameters and Internals

Model Type 
4 bits PEFT QLORA fine-tuned, Causal Language Model
Use Cases 
Areas:
Research, Development
Applications:
Instruction-based text generation, Sentiment classification
Primary Use Cases:
Generating recipes and instructions, Sentiment analysis from text inputs
Additional Notes 
Model finetuned on 150 steps using a French dataset adapted from Alpaca instruction data.
Supported Languages 
French (NLP Tasks)
Training Details 
Data Sources:
tbboukhari/Alpaca_french_instruct
Methodology:
Fine-tuning with 4 bits PEFT QLORA
Training Time:
150 steps
Model Architecture:
Modified from OpenLLM-France/Claire-7B-0.1, fine-tuned with 4 bits PEFT QLORA
Input Output 
Input Format:
Prompt-based (instruction and input text structure)
Accepted Modalities:
text
Output Format:
Generated text output
LLM NameClaire 7B 0.1 Instruct
Repository 🤗https://huggingface.co/PhilSad/Claire-7b-0.1-instruct 
Base Model(s)  OpenLLM-France/Claire-7B-0.1   OpenLLM-France/Claire-7B-0.1
Model Size7b
Required VRAM7.2 GB
Updated2024-12-21
MaintainerPhilSad
Model Typefalcon
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.2 GB: 2-of-2
Supported Languagesfr
Model ArchitectureFalconForCausalLM
Licensecc-by-nc-sa-4.0
Context Length2048
Model Max Length2048
Transformers Version4.37.2
Is Biased0
Vocabulary Size65024
Torch Data Typefloat16

Best Alternatives to Claire 7B 0.1 Instruct

Best Alternatives
Context / RAM
Downloads
Likes
... Openassistant Toxicity Reduce2K / 30.4 GB100
New Falcon2K / 4.3 GB191
New Falcon2K / 4.3 GB00
Falcon 7B Instruct0K / 14.4 GB189085932
Falcon 7B Instruct Quant0K / 4 GB3690
Falcon 7B Instruct Ft0K / 13.9 GB200
Falcon 7B IT Technical Support0K / 13.8 GB101
Falcon 7B Instruct Sharded0K / 27.7 GB739726
Falcon Tiny Random0K / 0 GB280
... 7B Instruct Sharded Finetuned0K / 13.8 GB111
Note: green Score (e.g. "73.2") means that the model is better than PhilSad/Claire-7b-0.1-instruct.

Rank the Claire 7B 0.1 Instruct 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? 40013 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 v20241217
  Support LLM Explorer