library_name: transformers
license: apache-2.0
language:
- fr
- en
datasets:
- jpacifico/French-Alpaca-dataset-Instruct-110K
tags:
- llama3
- french
- llama-3-8B
Model Card for Model ID
French-Alpaca based on Llama 3 8B
Instruct
8k context length.
Model Description
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.
The fine-tuning method is inspired from https://crfm.stanford.edu/2023/03/13/alpaca.html
The quantized GGUF version is available here : https://huggingface.co/jpacifico/French-Alpaca-Llama3-8B-Instruct-q8_0-v1.0-GGUF It can be used on a CPU device, compatible with llama.cpp and LM Studio
Usage
model_id = "jpacifico/French-Alpaca-Llama3-8B-Instruct-v1.0"
model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map={"":0})
tokenizer = AutoTokenizer.from_pretrained(model_id, add_eos_token=True, padding_side='left')
streamer = TextStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
def stream_frenchalpaca(user_prompt):
runtimeFlag = "cuda:0"
system_prompt = 'Tu trouveras ci-dessous une instruction qui décrit une tâche. Rédige une réponse qui complète de manière appropriée la demande.\n\n'
B_INST, E_INST = "### Instruction:\n", "### Response:\n"
prompt = f"{system_prompt}{B_INST}{user_prompt.strip()}\n\n{E_INST}"
inputs = tokenizer([prompt], return_tensors="pt").to(runtimeFlag)
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
_ = model.generate(**inputs, streamer=streamer, max_new_tokens=500)
stream_frenchalpaca("your prompt here")
Colab Notebook available on my Github:
https://github.com/jpacifico/French-Alpaca/blob/main/French_Alpaca_Llama3_inference_test_colab.ipynb
Limitations
The French-Alpaca model is a quick demonstration that a base 8B 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
- License: Apache 2.0