File size: 679 Bytes
2c3ef26 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 | """Quick generation example for ForgePlex-M2.2-10M."""
from pathlib import Path
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = Path(__file__).resolve().parent
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
model_path,
trust_remote_code=True,
torch_dtype=torch.float32,
device_map="auto",
)
prompt = "Once upon a time"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.inference_mode():
out = model.generate(**inputs, max_new_tokens=64, do_sample=False)
print(tokenizer.decode(out[0], skip_special_tokens=True))
|