-
Notifications
You must be signed in to change notification settings - Fork 1.3k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Support baichuan2 for level0 pipeline (#12289)
- Loading branch information
Showing
9 changed files
with
472 additions
and
174 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
99 changes: 99 additions & 0 deletions
99
python/llm/example/NPU/HF-Transformers-AutoModels/LLM/Pipeline-Models/baichuan2.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,99 @@ | ||
| # | ||
| # 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 ipex_llm.transformers.npu_model import AutoModelForCausalLM | ||
| from transformers import AutoTokenizer | ||
| from transformers.utils import logging | ||
|
|
||
| logger = logging.get_logger(__name__) | ||
|
|
||
| def get_prompt(message: str, chat_history: list[tuple[str, str]], | ||
| system_prompt: str) -> str: | ||
| texts = [f'<s>[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n'] | ||
| # The first user input is _not_ stripped | ||
| do_strip = False | ||
| for user_input, response in chat_history: | ||
| user_input = user_input.strip() if do_strip else user_input | ||
| do_strip = True | ||
| texts.append(f'{user_input} [/INST] {response.strip()} </s><s>[INST] ') | ||
| message = message.strip() if do_strip else message | ||
| texts.append(f'{message} [/INST]') | ||
| return ''.join(texts) | ||
|
|
||
| if __name__ == "__main__": | ||
| parser = argparse.ArgumentParser( | ||
| description="Predict Tokens using `generate()` API for npu model" | ||
| ) | ||
| parser.add_argument( | ||
| "--repo-id-or-model-path", | ||
| type=str, | ||
| default="baichuan-inc/Baichuan2-7B-Chat", | ||
| help="The huggingface repo id for the Baichuan2 model to be downloaded" | ||
| ", or the path to the huggingface checkpoint folder", | ||
| ) | ||
| 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("--max-context-len", type=int, default=1024) | ||
| parser.add_argument("--max-prompt-len", type=int, default=960) | ||
| parser.add_argument("--disable-transpose-value-cache", action="store_true", default=False) | ||
|
|
||
| args = parser.parse_args() | ||
| model_path = args.repo_id_or_model_path | ||
|
|
||
| model = AutoModelForCausalLM.from_pretrained(model_path, | ||
| optimize_model=True, | ||
| pipeline=True, | ||
| max_context_len=args.max_context_len, | ||
| max_prompt_len=args.max_prompt_len, | ||
| torch_dtype=torch.float16, | ||
| attn_implementation="eager", | ||
| transpose_value_cache=not args.disable_transpose_value_cache, | ||
| trust_remote_code=True) | ||
|
|
||
| tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) | ||
|
|
||
| DEFAULT_SYSTEM_PROMPT = """\ | ||
| """ | ||
|
|
||
| print("-" * 80) | ||
| print("done") | ||
| with torch.inference_mode(): | ||
| print("finish to load") | ||
| for i in range(5): | ||
| prompt = get_prompt(args.prompt, [], system_prompt=DEFAULT_SYSTEM_PROMPT) | ||
| _input_ids = tokenizer.encode(prompt, return_tensors="pt") | ||
| print("input length:", len(_input_ids[0])) | ||
| st = time.time() | ||
| output = model.generate( | ||
| _input_ids, max_new_tokens=args.n_predict, do_print=True | ||
| ) | ||
| end = time.time() | ||
| print(f"Inference time: {end-st} s") | ||
| input_str = tokenizer.decode(_input_ids[0], skip_special_tokens=False) | ||
| print("-" * 20, "Input", "-" * 20) | ||
| print(input_str) | ||
| output_str = tokenizer.decode(output[0], skip_special_tokens=False) | ||
| print("-" * 20, "Output", "-" * 20) | ||
| print(output_str) | ||
|
|
||
| print("-" * 80) | ||
| print("done") | ||
| print("success shut down") |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.