MoxoffSrL/Moxoff-Phi3Mini-KTO

!pip install transformers torch sentencepiece

from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cpu" # if you want to use the gpu make sure to have cuda toolkit installed and change this to "cuda"

model = AutoModelForCausalLM.from_pretrained("MoxoffSpA/Moxoff-Phi3Mini-KTO")
tokenizer = AutoTokenizer.from_pretrained("MoxoffSpA/Moxoff-Phi3Mini-KTO")

question = """Quanto è alta la torre di Pisa?"""
context = """
La Torre di Pisa è un campanile del XII secolo, famoso per la sua inclinazione. Alta circa 56 metri.
"""

prompt = f"Domanda: {question}, contesto: {context}"

messages = [
    {"role": "user", "content": prompt}
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(
    model_inputs, # The input to the model
    max_new_tokens=128, # Limiting the maximum number of new tokens generated
    do_sample=True, # Enabling sampling to introduce randomness in the generation
    temperature=0.1, # Setting temperature to control the randomness, lower values make it more deterministic
    top_p=0.95, # Using nucleus sampling with top-p filtering for more coherent generation       
    eos_token_id=tokenizer.eos_token_id # Specifying the token that indicates the end of a sequence
)

decoded_output = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
trimmed_output = decoded_output.strip()
print(trimmed_output)