Quantization made by Richard Erkhov.
A 7B language model. Good in French.
The French-Alpaca is a 7.24B params LLM model based on the Mistral-7B-Instruct-v0.2 foundation model,
fine-tuned from the original French-Alpaca-dataset entirely generated with OpenAI GPT-3.5-turbo.
French-Alpaca is a general model and can itself be finetuned to be specialized for specific use cases.
1#!pip install transformers accelerate
2
3from transformers import AutoTokenizer
4import transformers
5import torch
6
7model = "jpacifico/French-Alpaca-7B-Instruct-beta"
8messages = [{"role": "user", "content": "Rédige un article sur la fin des vendanges dans le Mâconnais."}]
9
10tokenizer = AutoTokenizer.from_pretrained(model)
11prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
12pipeline = transformers.pipeline(
13 "text-generation",
14 model=model,
15 torch_dtype=torch.float16,
16 device_map="auto",
17)
18
19outputs = pipeline(prompt, max_new_tokens=128, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
20print(outputs[0]["generated_text"])
You can test French-Alpaca with this dedicated and compatible colab notebook (with free T4 GPU) :
https://github.com/jpacifico/French-Alpaca/blob/main/French_Alpaca_inference_test_colab.ipynbThis quantized GGUF version availabe is available here :
https://huggingface.co/jpacifico/French-Alpaca-7B-Instruct-beta-GGUF
It can be used on a CPU device, compatible with llama.cpp and LM Studio (cf screenshot below).
The French-Alpaca model is a quick demonstration that a base 7B model can be easily fine-tuned to specialize in a particular language.
It does not have any moderation mechanisms.
