metadata
license: openrail
language:
- fr
pipeline_tag: text-generation
library_name: transformers
tags:
- LLM
inference: false
Vigogne-MPT-7B-Instruct: A French Instruction-following MPT Model
Vigogne-MPT-7B-Instruct is a MPT-7B model fine-tuned to follow the French instructions.
For more information, please visit the Github repo: https://github.com/bofenghuang/vigogne
Usage
import torch
from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, GenerationConfig
from vigogne.preprocess import generate_instruct_prompt
model_name_or_path = "bofenghuang/vigogne-mpt-7b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
config = AutoConfig.from_pretrained(model_name_or_path, trust_remote_code=True)
# config.attn_config['attn_impl'] = 'triton'
config.init_device = 'cuda:0' # For fast initialization directly on GPU!
model = AutoModelForCausalLM.from_pretrained(
model_name_or_path,
config=config,
torch_dtype=torch.float16,
device_map="auto",
trust_remote_code=True,
)
user_query = "Expliquez la différence entre DoS et phishing."
prompt = generate_instruct_prompt(user_query)
input_ids = tokenizer(prompt, return_tensors="pt")["input_ids"].to(model.device)
input_length = input_ids.shape[1]
generated_outputs = model.generate(
input_ids=input_ids,
generation_config=GenerationConfig(
temperature=0.1,
do_sample=True,
repetition_penalty=1.0,
max_new_tokens=512,
),
return_dict_in_generate=True,
pad_token_id=tokenizer.eos_token_id,
)
generated_tokens = generated_outputs.sequences[0, input_length:]
generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)
print(generated_text)
You can also infer this model by using the following Google Colab Notebook.
Limitations
Vigogne is still under development, and there are many limitations that have to be addressed. Please note that it is possible that the model generates harmful or biased content, incorrect information or generally unhelpful answers.