MiniCPM4-0.5B-QAT-Int4-GPTQ-format

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

path = "openbmb/MiniCPM4-0.5B-QAT-Int4-GPTQ-format"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(path, torch_dtype=torch.bfloat16, device_map=device, trust_remote_code=True)

messages = [
    {"role": "user", "content": "推荐5个北京的景点。"},
]
model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(device)

model_outputs = model.generate(
    model_inputs,
    max_new_tokens=1024,
    top_p=0.7,
    temperature=0.7
)

output_token_ids = [
    model_outputs[i][len(model_inputs[i]):] for i in range(len(model_inputs))
]

responses = tokenizer.batch_decode(output_token_ids, skip_special_tokens=True)[0]
print(responses)

from transformers import AutoTokenizer
from vllm import LLM, SamplingParams

model_name = "openbmb/MiniCPM4-0.5B-QAT-Int4-GPTQ-format"
prompt = [{"role": "user", "content": "推荐5个北京的景点。"}]

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
input_text = tokenizer.apply_chat_template(prompt, tokenize=False, add_generation_prompt=True)

llm = LLM(
    model=model_name,
    quantization="gptq_marlin",
    trust_remote_code=True,
    max_num_batched_tokens=32768,
    dtype="bfloat16", 
    gpu_memory_utilization=0.8, 
)
sampling_params = SamplingParams(top_p=0.7, temperature=0.7, max_tokens=1024, repetition_penalty=1.02)

outputs = llm.generate(prompts=input_text, sampling_params=sampling_params)

print(outputs[0].outputs[0].text)