Edit model card

Vigalpaca-French-7B-ties-GGUF

Vigalpaca-French-7B-ties is a merge of the following models:
jpacifico/French-Alpaca-7B-Instruct-beta
bofenghuang/vigostral-7b-chat

base model : jpacifico/French-Alpaca-7B-Instruct-beta

Usage

This quantized q8_0 GGUF version can be used on a CPU device, compatible with llama.cpp Ollama and LM Studio.

Ollama Modelfile example :

FROM ./Vigalpaca-French-7B-ties-quantized-q8_0.gguf

TEMPLATE """[INST] {{ .System }} {{ .Prompt }} [/INST]"""
PARAMETER stop "[INST]"
PARAMETER stop "[/INST]"
SYSTEM """Tu es un assistant IA nommé Vigalpaca. Tu dois répondre de manière concise et bienveillante aux questions posées par l'utilisateur."""

Limitations

The Vigalpaca model is a quick demonstration that a base 7B model can be easily merged/fine-tuned to specialize in a particular language. It does not have any moderation mechanisms.

  • Developed by: Jonathan Pacifico. Vigostral model by Bofeng Huang (special thanks), 2024
  • Model type: LLM
  • Language(s) (NLP): French
  • License: Apache-2.0
Downloads last month
5
GGUF
Model size
7.24B params
Architecture
llama

8-bit

Inference API
Unable to determine this model's library. Check the docs .