0.5B-qwen-x16_v3_cp6000

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "TeamPV/0.5B-qwen-x16_v3_cp6000"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "LGPL"
messages = [
    {"role": "system", "content": "Act as the Model Openness Framework (MOF) expert, specializing in abbreviation expansion. Expand the following abbreviation into its most accurate full form within the MOF context. Provide only the full form, no explanations."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]