picur-120M-instruct

PREVIEW!

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "picur/picur-120M-instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

messages = [
    {"role": "system", "content": "Magázd a felhasználót."},
    {"role": "user", "content": "Írj mesét egy öreg halászról, legyen képzeletbeli, hosszú történet"}
]

# Apply Jinja chat template stored in the tokenizer
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt",
    return_dict=True
).to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=150,
    do_sample=True,
    temperature=0.7
)

# Decode only the newly generated tokens
response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(response)