dpo-qwen-cot-merged

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "Rina1001/rina-repo-name"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

# Test inference
prompt = "Your question here"
text = tokenizer.apply_chat_template(
    prompt,
    tokenize=False,
    add_generation_prompt=True
)
inputs = tokenizer(text, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0]))