Downloads · 30 days
59
2% of all-time downloads
Chocolatine-3B-Instruct-DPO-v1.0
jpacifico/Chocolatine-3B-Instruct-DPO-v1.0
Chocolatine-3B-Instruct-DPO-v1.0 is a text generation model from jpacifico. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Chocolatine v1.0 3.82B params. Window context = 4k tokens
All-time downloads
2.9K
Public
Parameters
3.8B
7.6 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors7.6 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- phi3
- Access
- Public
- Created
- Jul 11, 2024
- Updated
- Jul 19, 2024
- SHA
- 841aadfe
Model card
From the Hugging Face model README
Model Card for Model ID
Chocolatine v1.0
3.82B params.
Window context = 4k tokens
This is a French DPO fine-tune of Microsoft's Phi-3-mini-4k-instruct,
improving its global understanding performances, even in English.
Model Description
Fine-tuned with the 12k DPO Intel/orca_dpo_pairs translated in French : AIffl/french_orca_dpo_pairs.
Chocolatine is a general model and can itself be finetuned to be specialized for specific use cases.
More infos & Benchmarks very soon ^^
Limitations
Chocolatine is a quick demonstration that a base 3B model can be easily fine-tuned to specialize in a particular language.
It does not have any moderation mechanisms.
- Developed by: Jonathan Pacifico, 2024
- Model type: LLM
- Language(s) (NLP): French, English
- License: MIT
- Task
- Text Generation
- Library
- transformers
- Type
- phi3
- License
- apache-2.0
- Languages
- fr, en
- Created
- Jul 11, 2024
- Updated
- Jul 19, 2024