Views
No views yet
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model_id = "olimebberson/lattice-pulse"
4tokenizer = AutoTokenizer.from_pretrained(model_id)
5model = AutoModelForCausalLM.from_pretrained(model_id).to("cuda")
6
7messages = [{"role": "user", "content": "Hello!"}]
8text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
9inputs = tokenizer(text, return_tensors="pt").to("cuda")
10out = model.generate(**inputs, max_new_tokens=128, do_sample=True, temperature=0.7)
11print(tokenizer.decode(out[0], skip_special_tokens=True))