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

Chocolatine 14B Instruct 4K DPO by jpacifico

 »  All LLMs  »  jpacifico  »  Chocolatine 14B Instruct 4K DPO   URL Share it on

  625   
  Autotrain compatible   Chocolatine   Conversational   Custom code Dataset:jpacifico/french-orca-...   En   Endpoints compatible   Fr   French   Instruct   Phi3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/jpacifico/Chocolatine-14B-Instruct-4k-DPO 

Chocolatine 14B Instruct 4K DPO Benchmarks

MMLU Pro: 41.82
GPQA: 12.19
MUSR: 15.15
BBH: 48.02
IFEval: 46.89 vs 88 (so35)-46.7%
MATH Lvl 5: 17.82
LLME Score: 0.26484
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Chocolatine 14B Instruct 4K DPO (jpacifico/Chocolatine-14B-Instruct-4k-DPO)
🌟 Advertise your project 🚀

Chocolatine 14B Instruct 4K DPO Parameters and Internals

Model Type 
LLM
Use Cases 
Areas:
Demonstration, Research
Primary Use Cases:
Fine-tuning demonstrations
Limitations:
No moderation mechanism
Additional Notes 
Fine-tuned model for French and English language tasks; trained to surpass performance of base model
Supported Languages 
French (High), English (High)
Training Details 
Data Sources:
jpacifico/french-orca-dpo-pairs-revised
Methodology:
DPO fine-tuning
Context Length:
4000
Input Output 
Input Format:
Prompt as chat message
Accepted Modalities:
text
Output Format:
Generated text
Performance Tips:
Optimal performance with a context window of 4k tokens
LLM NameChocolatine 14B Instruct 4K DPO
Repository 🤗https://huggingface.co/jpacifico/Chocolatine-14B-Instruct-4k-DPO 
Model Size14b
Required VRAM28 GB
Updated2025-10-09
Maintainerjpacifico
Model Typephi3
Instruction-BasedYes
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   4.9 GB: 3-of-6   4.8 GB: 4-of-6   4.8 GB: 5-of-6   3.6 GB: 6-of-6
Supported Languagesfr en
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typefloat16

Best Alternatives to Chocolatine 14B Instruct 4K DPO

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3 Medium 128K Instruct128K / 28 GB6406383
...ess V2.5 Phi 3 Medium 128K 14B128K / 28 GB11214
Finetuned Phi3 Medium 128K128K / 28 GB50
Shisa V1 Phi3 14B128K / 28 GB52
Mahou 1.2 Phi 14B128K / 28 GB11
...colatine 14B Instruct DPO V1.316K / 29.4 GB160
Phi4 Slerp2 14B16K / 28 GB50
Phi 3 Medium 4K Instruct4K / 28 GB11465220
...colatine 14B Instruct DPO V1.24K / 28 GB130914
...ium 4K Instruct Abliterated V34K / 28 GB95924
Note: green Score (e.g. "73.2") means that the model is better than jpacifico/Chocolatine-14B-Instruct-4k-DPO.

Rank the Chocolatine 14B Instruct 4K DPO 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? 51545 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 v20241124
  Support LLM Explorer