Llama 3.1 8B Italian Instruct

Published by @ai_italiano · Community adapter

Italian instruction following tuned on parliamentary debates, news agencies, and curated conversational data. Accurate grammatical gender agreement and subjunctive usage.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")
base = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")
model = PeftModel.from_pretrained(base, "modelforgelab/llama31-8b-it-instruct-lora")

inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Compatibility

• transformers>=4.43
• vLLM