remove llama2 changes

intel-analytics · Dec 19, 2024 · 2fce358 · 2fce358
1 parent 897e6fa
commit 2fce358
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 34 deletions.
diff --git a/python/llm/example/GPU/HuggingFace/LLM/llama2/README.md b/python/llm/example/GPU/HuggingFace/LLM/llama2/README.md
@@ -1,5 +1,5 @@
 # Llama2
-In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on Llama2 models on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) and [meta-llama/Llama-2-13b-chat-hf](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) (or [shakechen/Llama-2-7b-chat-hf](https://www.modelscope.cn/models/shakechen/Llama-2-7b-chat-hf) and [ydyajyA/Llama-2-13b-chat-hf](https://www.modelscope.cn/models/ydyajyA/Llama-2-13b-chat-hf) for ModelScope) as reference Llama2 models.
+In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on Llama2 models on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) and [meta-llama/Llama-2-13b-chat-hf](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) as reference Llama2 models.
 
 ## 0. Requirements
 To run these examples with IPEX-LLM on Intel GPUs, we have some recommended requirements for your machine, please refer to [here](../../../README.md#requirements) for more information.
@@ -14,9 +14,6 @@ conda create -n llm python=3.11
 conda activate llm
 # below command will install intel_extension_for_pytorch==2.1.10+xpu as default
 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
-
-# [optional] only needed if you would like to use ModelScope as model hub
-pip install modelscope==1.11.0
 ```
 
 #### 1.2 Installation on Windows
@@ -27,9 +24,6 @@ conda activate llm
 
 # below command will install intel_extension_for_pytorch==2.1.10+xpu as default
 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
-
-# [optional] only needed if you would like to use ModelScope as model hub
-pip install modelscope==1.11.0
 ```
 
 ### 2. Configures OneAPI environment variables for Linux
@@ -97,19 +91,14 @@ set SYCL_CACHE_PERSISTENT=1
 > For the first time that each model runs on Intel iGPU/Intel Arc™ A300-Series or Pro A60, it may take several minutes to compile.
 ### 4. Running examples
 
-```bash
-# for Hugging Face model hub
+```
 python ./generate.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --prompt PROMPT --n-predict N_PREDICT
-
-# for ModelScope model hub
-python ./generate.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --prompt PROMPT --n-predict N_PREDICT --modelscope
 ```
 
 Arguments info:
-- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the **Hugging Face** or **ModelScope** repo id for the Llama2 model (e.g. `meta-llama/Llama-2-7b-chat-hf` and `meta-llama/Llama-2-13b-chat-hf`) to be downloaded, or the path to the checkpoint folder. It is default to be `'meta-llama/Llama-2-7b-chat-hf'` for **Hugging Face** and `'shakechen/Llama-2-7b-chat-hf'` for **ModelScope**.
+- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the Llama2 model (e.g. `meta-llama/Llama-2-7b-chat-hf` and `meta-llama/Llama-2-13b-chat-hf`) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'meta-llama/Llama-2-7b-chat-hf'`.
 - `--prompt PROMPT`: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be `'What is AI?'`.
 - `--n-predict N_PREDICT`: argument defining the max number of tokens to predict. It is default to be `32`.
-- `--modelscope`: using **ModelScope** as model hub instead of **Hugging Face**.
 
 #### Sample Output
 #### [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)

diff --git a/python/llm/example/GPU/HuggingFace/LLM/llama2/generate.py b/python/llm/example/GPU/HuggingFace/LLM/llama2/generate.py
@@ -19,6 +19,7 @@
 import argparse
 
 from ipex_llm.transformers import AutoModelForCausalLM
+from transformers import LlamaTokenizer
 
 # 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
@@ -40,29 +41,16 @@ def get_prompt(message: str, chat_history: list[tuple[str, str]],
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(description='Predict Tokens using `generate()` API for Llama2 model')
-    parser.add_argument('--repo-id-or-model-path', type=str,
-                        help='The Hugging Face or ModelScope repo id for the Llama2 (e.g. `meta-llama/Llama-2-7b-chat-hf` and `meta-llama/Llama-2-13b-chat-hf`) to be downloaded'
-                             ', or the path to the checkpoint folder')
+    parser.add_argument('--repo-id-or-model-path', type=str, default="meta-llama/Llama-2-7b-chat-hf",
+                        help='The huggingface repo id for the Llama2 (e.g. `meta-llama/Llama-2-7b-chat-hf` and `meta-llama/Llama-2-13b-chat-hf`) 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('--modelscope', action="store_true", default=False, 
-                        help="Use models from modelscope")
 
     args = parser.parse_args()
-
-    if args.modelscope:
-        from modelscope import AutoTokenizer
-        Tokenizer = AutoTokenizer
-        model_hub = 'modelscope'
-    else:
-        from transformers import LlamaTokenizer
-        Tokenizer = LlamaTokenizer
-        model_hub = 'huggingface'
-
-    model_path = args.repo_id_or_model_path if args.repo_id_or_model_path else \
-        ("shakechen/Llama-2-7b-chat-hf" if args.modelscope else "meta-llama/Llama-2-7b-chat-hf")
+    model_path = args.repo_id_or_model_path
 
     # Load model in 4 bit,
     # which convert the relevant layers in the model into INT4 format
@@ -72,12 +60,11 @@ def get_prompt(message: str, chat_history: list[tuple[str, str]],
                                                  load_in_4bit=True,
                                                  optimize_model=True,
                                                  trust_remote_code=True,
-                                                 use_cache=True,
-                                                 model_hub=model_hub)
+                                                 use_cache=True)
     model = model.half().to('xpu')
 
     # Load tokenizer
-    tokenizer = Tokenizer.from_pretrained(model_path, trust_remote_code=True)
+    tokenizer = LlamaTokenizer.from_pretrained(model_path, trust_remote_code=True)
 
     # Generate predicted tokens
     with torch.inference_mode():