import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
torch.set_default_device('cuda')
model = AutoModelForCausalLM.from_pretrained("typeof/phi-2-qlora-ft", trust_remote_code=True, torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("typeof/phi-2-qlora-ft", trust_remote_code=True, torch_dtype="auto")
prompt = "Are textbooks all you need?"
inputs = tokenizer(prompt,return_tensors="pt", return_attention_mask=False)
outputs = model.generate(
**inputs,
max_length=200,
do_sample=True,
pad_token_id=tokenizer.eos_token_id,
eos_token_id=tokenizer.eos_token_id,
)
text = tokenizer.batch_decode(outputs)[0]
print(text)
Install from pip and serve model
# Install vLLM from pip: pip install vllm# Start the vLLM server: vllm serve "typeof/phi-2-qlora-ft"# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "typeof/phi-2-qlora-ft", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'