davidsi/

Llama3_1-8B-Instruct-AMD-python

import torch  
from transformers import AutoTokenizer, AutoModelForCausalLM  

model_name = 'davidsi/Llama3_1-8B-Instruct-AMD-python'  
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16).to(device)

messages = [
    {"role": "system", "content": "You are a helpful assistant for AMD technologies and python."},
    {"role": "user", "content": query}
]

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(device)

outputs = model.generate(
    input_ids,
    max_new_tokens=8192,
    eos_token_id=terminators,
    pad_token_id=tokenizer.eos_token_id,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))