daVinci-Agency

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda"
model_path = "GAIR/daVinci-Agency" # Replace with actual path

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    trust_remote_code=True
).to(device).eval()

# Example: Complex Long-Horizon Task
query = "Refactor the authentication module in this repository to support OAuth2, ensuring backward compatibility."

messages = [
    {"role": "system", "content": "You are an intelligent software engineering agent capable of long-horizon planning and execution."},
    {"role": "user", "content": query}
]

inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_tensors="pt",
    return_dict=True
).to(device)

gen_kwargs = {
    "max_new_tokens": 4096,
    "do_sample": True,
    "top_p": 0.95,
    "temperature": 1.0,
    "top_k": 40
}

with torch.no_grad():
    outputs = model.generate(**inputs, **gen_kwargs)
    response = outputs[:, inputs['input_ids'].shape[1]:]
    print(tokenizer.decode(response[0], skip_special_tokens=True))