metadata
language:
- fr
- en
license: mit
library_name: transformers
tags:
- french
- chocolatine
datasets:
- jpacifico/french-orca-dpo-pairs-revised
pipeline_tag: text-generation
model-index:
- name: Chocolatine-14B-Instruct-DPO-v1.2
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 68.52
name: strict accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jpacifico/Chocolatine-14B-Instruct-DPO-v1.2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 49.85
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jpacifico/Chocolatine-14B-Instruct-DPO-v1.2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 17.98
name: exact match
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jpacifico/Chocolatine-14B-Instruct-DPO-v1.2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 10.07
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jpacifico/Chocolatine-14B-Instruct-DPO-v1.2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 12.35
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jpacifico/Chocolatine-14B-Instruct-DPO-v1.2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 41.07
name: accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=jpacifico/Chocolatine-14B-Instruct-DPO-v1.2
name: Open LLM Leaderboard
QuantFactory/Chocolatine-14B-Instruct-DPO-v1.2-GGUF
This is quantized version of jpacifico/Chocolatine-14B-Instruct-DPO-v1.2 created using llama.cpp
Original Model Card
Chocolatine-14B-Instruct-DPO-v1.2
DPO fine-tuned of microsoft/Phi-3-medium-4k-instruct (14B params)
using the jpacifico/french-orca-dpo-pairs-revised rlhf dataset.
Training in French also improves the model in English, surpassing the performances of its base model.
Window context = 4k tokens
- 4-bit quantized version available here : jpacifico/Chocolatine-14B-Instruct-DPO-v1.2-Q4_K_M-GGUF
OpenLLM Leaderboard
Chocolatine is the best-performing model in size 13B on the OpenLLM Leaderboard (last update: 2024/10/18)
| Metric | Value |
|---|---|
| Avg. | 33.3 |
| IFEval | 68.52 |
| BBH | 49.85 |
| MATH Lvl 5 | 17.98 |
| GPQA | 10.07 |
| MuSR | 12.35 |
| MMLU-PRO | 41.07 |
MT-Bench-French
Chocolatine-14B-Instruct-DPO-v1.2 outperforms its previous versions and its base model Phi-3-medium-4k-instruct on MT-Bench-French, used with multilingual-mt-bench and GPT-4-Turbo as LLM-judge.
########## First turn ##########
score
model turn
gpt-4o-mini 1 9.2875
Chocolatine-14B-Instruct-4k-DPO 1 8.6375
Chocolatine-14B-Instruct-DPO-v1.2 1 8.6125
Phi-3.5-mini-instruct 1 8.5250
Chocolatine-3B-Instruct-DPO-v1.2 1 8.3750
Phi-3-medium-4k-instruct 1 8.2250
gpt-3.5-turbo 1 8.1375
Chocolatine-3B-Instruct-DPO-Revised 1 7.9875
Daredevil-8B 1 7.8875
Meta-Llama-3.1-8B-Instruct 1 7.0500
vigostral-7b-chat 1 6.7875
Mistral-7B-Instruct-v0.3 1 6.7500
gemma-2-2b-it 1 6.4500
French-Alpaca-7B-Instruct_beta 1 5.6875
vigogne-2-7b-chat 1 5.6625
########## Second turn ##########
score
model turn
gpt-4o-mini 2 8.912500
Chocolatine-14B-Instruct-DPO-v1.2 2 8.337500
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
Daredevil-8B 2 7.087500
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
French-Alpaca-7B-Instruct_beta 2 5.487395
vigogne-2-7b-chat 2 2.775000
########## Average ##########
score
model
gpt-4o-mini 9.100000
Chocolatine-14B-Instruct-DPO-v1.2 8.475000
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
Daredevil-8B 7.487500
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
French-Alpaca-7B-Instruct_beta 5.587866
vigogne-2-7b-chat 4.218750
Usage
You can run this model using my Colab notebook
You can also run Chocolatine 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 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, 2024
- Model type: LLM
- Language(s) (NLP): French, English
- License: MIT
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 33.30 |
| IFEval (0-Shot) | 68.52 |
| BBH (3-Shot) | 49.85 |
| MATH Lvl 5 (4-Shot) | 17.98 |
| GPQA (0-shot) | 10.07 |
| MuSR (0-shot) | 12.35 |
| MMLU-PRO (5-shot) | 41.07 |