vorenthiclabs/Vorenthos-r1

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "vorenthiclabs/Vorenthos-r1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto",
)

prompt = """<|User|>: Explain gradient descent in simple terms.
<|Assistant|>: <think>
"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.6)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

<|User|>: {your instruction here}
<|Assistant|>: <think>
{model chain-of-thought reasoning}
</think>
{final response}