wehub-resource-sync
20 lines
950 B
Python
Executable File
20 lines
950 B
Python
Executable File
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
import torch
|
|
|
|
device = "cuda" # the device to load the model onto
|
|
|
|
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen1.5-MoE-A2.7B-Chat", torch_dtype=torch.bfloat16, device_map="auto")
|
|
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen1.5-MoE-A2.7B-Chat")
|
|
|
|
prompt = "Give me a short introduction to large language model."
|
|
messages = [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": prompt}]
|
|
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
|
model_inputs = tokenizer([text], return_tensors="pt").to(device)
|
|
|
|
generated_ids = model.generate(model_inputs.input_ids, 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]
|
|
|
|
print(response)
|