File size: 1,153 Bytes
70c8597 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 | """Quick smoke-test for the exported HuggingFace model."""
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
def main():
model_dir = "."
print("Loading model and tokenizer …")
tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
model_dir, trust_remote_code=True, torch_dtype=torch.float32
)
if torch.cuda.is_available():
model = model.to("cuda")
prompts = [
"एक समय की बात है",
"एक जंगल में",
"एक छोटी लड़की",
]
for prompt in prompts:
print(f"\n{'='*60}")
print(f"Prompt: {prompt}")
print(f"{'='*60}")
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
**inputs,
max_new_tokens=150,
do_sample=True,
top_k=40,
top_p=0.95,
temperature=0.8,
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
if __name__ == "__main__":
main()
|