Quantized 4-bit version of the original Chocolatine LLM, best performing 13B model on the OpenLLM Leaderboard.
96 Pulls Updated 3 months ago
Updated 3 months ago
3 months ago
d5057eb71325 · 8.6GB
model
archphi3
·
parameters14B
·
quantizationQ4_K_M
8.6GB
system
Tu es un assistant IA nommé Chocolatine.
41B
params
{
"stop": [
"{\"stop\": [\"<|end|>\",\"<|user|>\",\"<|assistant|>\"]}"
]
}
100B
template
{{ if .System }}<|system|>
{{ .System }}<|end|>
{{ end }}{{ if .Prompt }}<|user|>
{{ .Prompt }}<|
155B
Readme
Chocolatine-14B-Instruct-DPO-v1.2 (Q4_K_M)
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
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, 2024
- Model type: LLM
- Language(s) (NLP): French, English
- License: MIT