Mistral-7B-v0.1 for Italian Language Text Generation
Model Architecture
The Mistral-7B-v0.1 model is a transformer-based model that can handle a variety of tasks including but not limited to translation, summarization, and text completion. It's particularly designed for the Italian language.
Evaluation
For a detailed comparison of model performance, check out the Leaderboard for Italian Language Models.
Here's a breakdown of the performance metrics:
Metric | hellaswag_it acc_norm | arc_it acc_norm | m_mmlu_it 5-shot acc | Average |
---|---|---|---|---|
Accuracy Normalized | 0.6934 | 0.5583 | 0.5491 | 0.6002 |
How to Use
How to utilize my Mistral for Italian text generation
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
MODEL_NAME = "DeepMount00/Mistral-Ita-7b_v2"
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.bfloat16).eval()
model.to(device)
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
def generate_answer(prompt):
messages = [
{"role": "user", "content": prompt},
]
model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=200, do_sample=True,
temperature=0.001, eos_token_id=tokenizer.eos_token_id)
decoded = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
return decoded[0]
prompt = "Come si apre un file json in python?"
answer = generate_answer(prompt)
print(answer)
Developer
[Michele Montebovi]
- Downloads last month
- 2