jpacifico's picture
Update README.md
7e3d0cd verified
metadata
tags:
  - text-generation-inference
  - transformers
  - sft
  - chocolatine
license: mit
language:
  - fr
datasets:
  - jpacifico/sft-set-administratif-def-6996

Description model

Chocolatine-3B version specialized in French administrative language, supervised fine-tuning of microsoft/Phi-3.5-mini-instruct
based on the official lexicon
published by the French Ministère de la Fonction Publique et de la Réforme de l'Etat.

Data & Training

The dataset gathers 2362 administrative terms constituting the basis of the simulation of prompt-answer pairs.
The GPT-4o model deployed on Azure OpenAI was used to carry out the building of the dataset in several phases:

  • Extraction of the lexicon pages converted into jpg images
  • Reformulation of the definitions to make them more readable and natural to be used by an LLM in order to ensure high quality data.
  • Generation of questions from the terms and definitions
  • Generation of answers in three successive rounds taking into account the previous generations to ensure variety.

Fine tuning (SFT) done efficiently with Unsloth,
with which I saved processing time on a single T4 GPU (Compute instance from Azure ML).

Usage

The recommended usage is by loading the low-rank adapter using unsloth:

from unsloth import FastLanguageModel

model_name = "jpacifico/chocolatine-admin-3B-sft-v0.2"
model, tokenizer = FastLanguageModel.from_pretrained(
  model_name = model_name,
  max_seq_length = 2048,
  dtype = None,
  load_in_4bit = True,
)

FastLanguageModel.for_inference(model)

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
  • License: MIT
  • Finetuned from model : microsoft/Phi-3.5-mini-instruct