ERNIE-4.5-21B-A3B-Thinking-GGUF

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "baidu/ERNIE-4.5-21B-A3B-Thinking"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map="auto",
    torch_dtype=torch.bfloat16,
)

# prepare the model input
prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], add_special_tokens=False, return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=1024
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()

# decode the generated ids
generate_text = tokenizer.decode(output_ids, skip_special_tokens=True)
print("generate_text:", generate_text)