Instella-3B-Long-Instruct

from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "amd/Instella-3B-Long-Instruct"

tokenizer = AutoTokenizer.from_pretrained(checkpoint, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto", trust_remote_code=True)

prompt = [{"role": "user", "content": "What are the benefits of open-source AI research?"}]
inputs = tokenizer.apply_chat_template(
    prompt,
    add_generation_prompt=True,
    return_tensors='pt'
)

tokens = model.generate(
    inputs.to(model.device),
    max_new_tokens=1024,
    temperature=0.8,
    do_sample=True
)

print(tokenizer.decode(tokens[0], skip_special_tokens=False))