jpacifico / french-alpaca-3b

The French General LLM

127 Pulls Updated 3 months ago

3 months ago

014b768ab174 · 2.3GB

model
llama
·
3.82B
·
Q4_K_M
template
{{ if .System }}<|system|> {{ .System }}<|end|> {{ end }}{{ if .Prompt }}<|user|> {{ .Prompt }}<|end|> {{ end }}<|assistant|> {{ .Response }}<|end|>
params
{"num_keep":4,"stop":["<|user|>","<|assistant|>","<|system|>","<|end|>","<|endoftext|>","###","<|fin|>"]}

Readme

French-Alpaca_500px.png

French-Alpaca is a general SLM in French
3.82B params
4k tokens of window context

Based on microsoft/Phi-3-mini-4k-instruct
Fine-tuned from the original French-Alpaca-dataset 110K instructions, entirely generated with OpenAI GPT-3.5-turbo.
The fine-tuning method is inspired from https://crfm.stanford.edu/2023/03/13/alpaca.html

HuggingFace model card : https://huggingface.co/jpacifico/French-Alpaca-Phi-3-mini-4k-instruct-v1.0-GGUF
Developed by: Jonathan Pacifico, 2024
License: MIT