Chocolatine-2-14B
DPO fine-tuning of the merged model jpacifico/Chocolatine-2-14B-Merged-base-Phi-4 (Microsoft/Phi-4 architecture, 14B params)
using the jpacifico/french-orca-dpo-pairs-revised rlhf dataset.
Training in French also improves the base model's overall capabilities.
[!TIP] Window context : up to 16K tokens
LLM Leaderboard FR
[Updated 2025-06-26]
BAC FR benchmark Number 1 all categories on the French Government Leaderboard LLM FR
MT-Bench-French
Chocolatine-2 outperforms its previous versions and its base architecture Phi-4 model on MT-Bench-French, used with multilingual-mt-bench and GPT-4-Turbo as a LLM-judge.
My goal was to achieve GPT-4o-mini's performance on the French language, this version equals the performance of the OpenAI model according to this benchmark
########## First turn ##########
score
model turn
gpt-4o-mini 1 9.287500
Chocolatine-2-14B-Instruct-v2.0 1 8.912500
Qwen2.5-14B-Instruct 1 8.887500
Chocolatine-14B-Instruct-4k-DPO 1 8.637500
Chocolatine-14B-Instruct-DPO-v1.2 1 8.612500
Phi-3.5-mini-instruct 1 8.525000
Chocolatine-3B-Instruct-DPO-v1.2 1 8.375000
DeepSeek-R1-Distill-Qwen-14B 1 8.375000
phi-4 1 8.300000
Phi-3-medium-4k-instruct 1 8.225000
gpt-3.5-turbo 1 8.137500
Chocolatine-3B-Instruct-DPO-Revised 1 7.987500
Meta-Llama-3.1-8B-Instruct 1 7.050000
vigostral-7b-chat 1 6.787500
Mistral-7B-Instruct-v0.3 1 6.750000
gemma-2-2b-it 1 6.450000
########## Second turn ##########
score
model turn
Chocolatine-2-14B-Instruct-v2.0 2 9.275000
gpt-4o-mini 2 8.912500
Qwen2.5-14B-Instruct 2 8.912500
Chocolatine-14B-Instruct-DPO-v1.2 2 8.337500
DeepSeek-R1-Distill-Qwen-14B 2 8.200000
phi-4 2 8.131250
Chocolatine-3B-Instruct-DPO-Revised 2 7.937500
Chocolatine-3B-Instruct-DPO-v1.2 2 7.862500
Phi-3-medium-4k-instruct 2 7.750000
Chocolatine-14B-Instruct-4k-DPO 2 7.737500
gpt-3.5-turbo 2 7.679167
Phi-3.5-mini-instruct 2 7.575000
Meta-Llama-3.1-8B-Instruct 2 6.787500
Mistral-7B-Instruct-v0.3 2 6.500000
vigostral-7b-chat 2 6.162500
gemma-2-2b-it 2 6.100000
########## Average ##########
score
model
gpt-4o-mini 9.100000
Chocolatine-2-14B-Instruct-v2.0 9.093750
Qwen2.5-14B-Instruct 8.900000
Chocolatine-14B-Instruct-DPO-v1.2 8.475000
DeepSeek-R1-Distill-Qwen-14B 8.287500
phi-4 8.215625
Chocolatine-14B-Instruct-4k-DPO 8.187500
Chocolatine-3B-Instruct-DPO-v1.2 8.118750
Phi-3.5-mini-instruct 8.050000
Phi-3-medium-4k-instruct 7.987500
Chocolatine-3B-Instruct-DPO-Revised 7.962500
gpt-3.5-turbo 7.908333
Meta-Llama-3.1-8B-Instruct 6.918750
Mistral-7B-Instruct-v0.3 6.625000
vigostral-7b-chat 6.475000
gemma-2-2b-it 6.275000
Usage
You can run this model using my Colab notebook
You can also run Chocolatine-2 using the following code:
import transformers
from transformers import AutoTokenizer
# Format prompt
message = [
{"role": "system", "content": "You are a helpful assistant chatbot."},
{"role": "user", "content": "What is a Large Language Model?"}
]
tokenizer = AutoTokenizer.from_pretrained(new_model)
prompt = tokenizer.apply_chat_template(message, add_generation_prompt=True, tokenize=False)
# Create pipeline
pipeline = transformers.pipeline(
"text-generation",
model=new_model,
tokenizer=tokenizer
)
# Generate text
sequences = pipeline(
prompt,
do_sample=True,
temperature=0.7,
top_p=0.9,
num_return_sequences=1,
max_length=200,
)
print(sequences[0]['generated_text'])
Limitations
The Chocolatine model series is a quick demonstration that a base model can be easily fine-tuned to achieve compelling performance.
It does not have any moderation mechanism.
- Developed by: Jonathan Pacifico, 2025
- Model type: LLM
- Language(s) (NLP): French, English
- License: MIT
Made with ❤️ in France