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

Chocolatine 3B Instruct DPO V1.0 by jpacifico

 »  All LLMs  »  jpacifico  »  Chocolatine 3B Instruct DPO V1.0   URL Share it on

  477   
  Autotrain compatible   Conversational   Custom code   En   Endpoints compatible   Fr   French   Instruct   Phi-3   Phi-3-3b   Phi3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/jpacifico/Chocolatine-3B-Instruct-DPO-v1.0 

Chocolatine 3B Instruct DPO V1.0 Benchmarks

MMLU Pro: 32.63
GPQA: 8.72
MUSR: 19.47
BBH: 36.55
IFEval: 37.37 vs 88 (so35)-57.5%
MATH Lvl 5: 16.47
LLME Score: 0.30325
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Chocolatine 3B Instruct DPO V1.0 (jpacifico/Chocolatine-3B-Instruct-DPO-v1.0)

Chocolatine 3B Instruct DPO V1.0 Parameters and Internals

Model Type 
LLM, NLP
Use Cases 
Areas:
general model
Limitations:
does not have any moderation mechanisms
Additional Notes 
This model aims to demonstrate the ease of fine-tuning a base 3B model to specialize in a specific language such as French.
Supported Languages 
French (high), English (medium)
Training Details 
Data Sources:
AIffl/french_orca_dpo_pairs
Data Volume:
12k DPO Intel/orca_dpo_pairs translated in French
Methodology:
fine-tuning
Context Length:
4000
LLM NameChocolatine 3B Instruct DPO V1.0
Repository 🤗https://huggingface.co/jpacifico/Chocolatine-3B-Instruct-DPO-v1.0 
Model Size3b
Required VRAM7.7 GB
Updated2024-12-21
Maintainerjpacifico
Model Typephi3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Supported Languagesfr en
Model ArchitecturePhi3ForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typefloat16

Best Alternatives to Chocolatine 3B Instruct DPO V1.0

Best Alternatives
Context / RAM
Downloads
Likes
...ocolatine 3B Instruct DPO V1.2128K / 7.7 GB31199
MedIT Mesh 3B Instruct128K / 7.7 GB550
3Bgeneral ECE PRYMMAL Martial128K / 7.7 GB200
3Blareneg ECE PRYMMAL Martial128K / 7.7 GB260
ECE EIFFEL 3B128K / 7.7 GB110
Chocolatine Admin 3B SFT V0.3B128K / 7.7 GB874
ECE GRENELLE 3B128K / 7.7 GB560
Phi3 3B Ultrachat Svd Model128K / 7.7 GB131
Orpo Phi3 3B 128K128K / 7.7 GB154
...latine 3B Instruct DPO Revised4K / 7.7 GB100826
Note: green Score (e.g. "73.2") means that the model is better than jpacifico/Chocolatine-3B-Instruct-DPO-v1.0.

Rank the Chocolatine 3B Instruct DPO V1.0 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