sage-ml

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "d4g0at5h0rty/sage-ml"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

messages = [{"role": "user", "content": "Hello, how are you?"}]
input_ids = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_tensors="pt",
)

gen_tokens = model.generate(
    input_ids,
    max_new_tokens=4096,
    do_sample=True,
    temperature=0.1,
    top_p=0.95
)

print(tokenizer.decode(gen_tokens[0]))