JulianKrgd/julian-600m-40b-instruct-v0.1

from transformers import AutoModelForCausalLM, LlamaTokenizer
import torch

model_id = "JulianKrgd/julian-600m-40b-instruct-v0.1"

# IMPORTANT: Use LlamaTokenizer, not AutoTokenizer
tokenizer = LlamaTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# Chat format (ChatML)
messages = [
    {"role": "user", "content": "What is the capital of France?"}
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=100,
    temperature=0.7,
    top_p=0.9,
    do_sample=True,
    repetition_penalty=1.1
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

<|im_start|>user
What is the capital of France?<|im_end|>
<|im_start|>assistant
The capital of France is Paris.<|im_end|>