This is a model that is assumed to perform well, but may require more testing and user feedback. Be aware, only models featured within the GUI of GPT4All, are curated and officially supported by Nomic. Use at your own risk.
About
- Static quants of https://huggingface.co/jpacifico/Chocolatine-3B-Instruct-DPO-Revised at commit fa3e742
- Quantized by ThiloteE with llama.cpp commit e09a800
These quants were created with a customized configuration that have been proven to not cause visible end of string (eos) tokens during inference with GPT4All. The config.json, generation_config.json and tokenizer_config.json differ from the original configuration as can be found in the original model's repository at the time of creation of these quants.
Prompt Template (for GPT4All)
Example System Prompt:
<|system|>
Vous trouverez ci-dessous une instruction décrivant une tâche. Rédigez une réponse qui réponde de manière appropriée à la demande.<|end|>
Chat Template:
<|user|>
%1<|end|>
<|assistant|>
%2<|end|>
Context Length
4096
Use a lower value during inference, if you do not have enough RAM or VRAM.
Provided Quants
Link | Type | Size/GB | Notes |
---|---|---|---|
GGUF | Q4_0 | 2.44 | fast, recommended |
About GGUF
If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.
Here is a handy graph by ikawrakow comparing some quant types (lower is better):
And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
Thanks
I thank Mradermacher and TheBloke for Inspiration to this model card and their contributions to open source. Also 3Simplex for lots of help along the way. Shoutout to the GPT4All and llama.cpp communities :-)
Original Model card:
Chocolatine-3B-Instruct-DPO-Revised
DPO fine-tuned of microsoft/Phi-3-mini-4k-instruct (3.82B 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
Benchmarks
Chocolatine is the best-performing 3B model on the OpenLLM Leaderboard (august 2024)
Metric | Value |
---|---|
Avg. | 27.63 |
IFEval (0-Shot) | 56.23 |
BBH (3-Shot) | 37.16 |
MATH Lvl 5 (4-Shot) | 14.5 |
GPQA (0-shot) | 9.62 |
MuSR (0-shot) | 15.1 |
MMLU-PRO (5-shot) | 33.21 |
MT-Bench-French
Chocolatine-3B-Instruct-DPO-Revised is outperforming GPT-3.5-Turbo on MT-Bench-French by Bofeng Huang,
used with multilingual-mt-bench
########## First turn ##########
score
model turn
gpt-3.5-turbo 1 8.1375
Chocolatine-3B-Instruct-DPO-Revised 1 7.9875
Daredevil-8B 1 7.8875
Daredevil-8B-abliterated 1 7.8375
Chocolatine-3B-Instruct-DPO-v1.0 1 7.6875
NeuralDaredevil-8B-abliterated 1 7.6250
Phi-3-mini-4k-instruct 1 7.2125
Meta-Llama-3-8B-Instruct 1 7.1625
vigostral-7b-chat 1 6.7875
Mistral-7B-Instruct-v0.3 1 6.7500
Mistral-7B-Instruct-v0.2 1 6.2875
French-Alpaca-7B-Instruct_beta 1 5.6875
vigogne-2-7b-chat 1 5.6625
vigogne-2-7b-instruct 1 5.1375
########## Second turn ##########
score
model turn
Chocolatine-3B-Instruct-DPO-Revised 2 7.937500
gpt-3.5-turbo 2 7.679167
Chocolatine-3B-Instruct-DPO-v1.0 2 7.612500
NeuralDaredevil-8B-abliterated 2 7.125000
Daredevil-8B 2 7.087500
Daredevil-8B-abliterated 2 6.873418
Meta-Llama-3-8B-Instruct 2 6.800000
Mistral-7B-Instruct-v0.2 2 6.512500
Mistral-7B-Instruct-v0.3 2 6.500000
Phi-3-mini-4k-instruct 2 6.487500
vigostral-7b-chat 2 6.162500
French-Alpaca-7B-Instruct_beta 2 5.487395
vigogne-2-7b-chat 2 2.775000
vigogne-2-7b-instruct 2 2.240506
########## Average ##########
score
model
Chocolatine-3B-Instruct-DPO-Revised 7.962500
gpt-3.5-turbo 7.908333
Chocolatine-3B-Instruct-DPO-v1.0 7.650000
Daredevil-8B 7.487500
NeuralDaredevil-8B-abliterated 7.375000
Daredevil-8B-abliterated 7.358491
Meta-Llama-3-8B-Instruct 6.981250
Phi-3-mini-4k-instruct 6.850000
Mistral-7B-Instruct-v0.3 6.625000
vigostral-7b-chat 6.475000
Mistral-7B-Instruct-v0.2 6.400000
French-Alpaca-7B-Instruct_beta 5.587866
vigogne-2-7b-chat 4.218750
vigogne-2-7b-instruct 3.698113
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'])
4-bit quantized version is available here : jpacifico/Chocolatine-3B-Instruct-DPO-Revised-Q4_K_M-GGUF
Ollama: jpacifico/chocolatine-3b
ollama run jpacifico/chocolatine-3b
Ollama Modelfile example :
FROM ./chocolatine-3b-instruct-dpo-revised-q4_k_m.gguf
TEMPLATE """{{ if .System }}<|system|>
{{ .System }}<|end|>
{{ end }}{{ if .Prompt }}<|user|>
{{ .Prompt }}<|end|>
{{ end }}<|assistant|>
{{ .Response }}<|end|>
"""
PARAMETER stop """{"stop": ["<|end|>","<|user|>","<|assistant|>"]}"""
SYSTEM """You are a friendly assistant called Chocolatine."""
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
- Downloads last month
- 1,853