generate.py

#
# Copyright 2016 The BigDL Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#

import torch
import time
import argparse

from transformers import LlamaTokenizer
from ipex_llm.transformers import AutoModelForCausalLM

# you could tune the prompt based on your own model,
# here the prompt tuning refers to https://huggingface.co/georgesung/llama2_7b_chat_uncensored#prompt-style
LLAMA2_PROMPT_FORMAT = """### HUMAN:
{prompt}

### RESPONSE:
"""

if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='Predict Tokens using `generate()` API for Llama2 model')
    parser.add_argument('--model', type=str, required=True,
                        help='Path to a gguf model')
    parser.add_argument('--prompt', type=str, default="What is AI?",
                        help='Prompt to infer')
    parser.add_argument('--n-predict', type=int, default=32,
                        help='Max tokens to predict')
    parser.add_argument('--low_bit', type=str, default="sym_int4",
                        help='what low_bit to run bigdl-llm')

    args = parser.parse_args()

    model_path = args.model

    # Load gguf model and vocab, then convert them to IPEX-LLM model and huggingface tokenizer
    model, tokenizer = AutoModelForCausalLM.from_gguf(model_path)
    model = model.to('xpu')

    # Generate predicted tokens
    with torch.inference_mode():
        prompt = LLAMA2_PROMPT_FORMAT.format(prompt=args.prompt)
        input_ids = tokenizer.encode(prompt, return_tensors="pt").to('xpu')
        st = time.time()
        output = model.generate(input_ids,
                                max_new_tokens=args.n_predict)
        torch.xpu.synchronize()
        end = time.time()
        output = output.cpu()
        output_str = tokenizer.decode(output[0], skip_special_tokens=True)
        print(f'Inference time: {end-st} s')
        print('-'*20, 'Output', '-'*20)
        print(output_str)