fix import issue and update pip install itrex (#397)

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

intel_extension_for_transformers/neural_chat/docs/notebooks/amp_optimization_on_spr.ipynb

@@ -43,7 +43,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%cd ../../\n",
+    "!git clone https://github.com/intel/intel-extension-for-transformers.git\n",
+    "!cd ./intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/\n",
     "!pip install -r requirements.txt"
    ]
   },

intel_extension_for_transformers/neural_chat/docs/notebooks/build_chatbot_on_icx.ipynb

@@ -51,7 +51,8 @@
    },
    "outputs": [],
    "source": [
-    "%cd ../../\n",
+    "!git clone https://github.com/intel/intel-extension-for-transformers.git\n",
+    "!cd ./intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/\n",
     "!pip install -r requirements.txt"
    ]
   },

intel_extension_for_transformers/neural_chat/docs/notebooks/build_chatbot_on_nv_a100.ipynb

@@ -43,7 +43,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%cd ../../\n",
+    "!git clone https://github.com/intel/intel-extension-for-transformers.git\n",
+    "!cd ./intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/\n",
     "!pip install -r requirements.txt"
    ]
   },

intel_extension_for_transformers/neural_chat/docs/notebooks/build_chatbot_on_spr.ipynb

@@ -45,7 +45,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%cd ../../\n",
+    "!git clone https://github.com/intel/intel-extension-for-transformers.git\n",
+    "!cd ./intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/\n",
     "!pip install -r requirements.txt"
    ]
   },

intel_extension_for_transformers/neural_chat/docs/notebooks/build_chatbot_on_xpu.ipynb

@@ -20,8 +20,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%%bash\n",
-    "%pip install intel-extension-for-transformers"
+    "!pip install intel-extension-for-transformers"
    ]
   },
   {
@@ -37,7 +36,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%cd ../../\n",
+    "!git clone https://github.com/intel/intel-extension-for-transformers.git\n",
+    "!cd ./intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/\n",
     "!pip install -r requirements.txt"
    ]
   },

intel_extension_for_transformers/neural_chat/docs/notebooks/customize_chatbot_with_finetuned_models.ipynb

@@ -25,7 +25,29 @@
    },
    "outputs": [],
    "source": [
-    "pip install intel-extension-for-transformers"
+    "!pip install intel-extension-for-transformers"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Install requirements:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "shellscript"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "!git clone https://github.com/intel/intel-extension-for-transformers.git\n",
+    "!cd ./intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/\n",
+    "!pip install -r requirements.txt"
    ]
   },
   {
@@ -47,34 +69,34 @@
    ]
   },
   {
-    "cell_type": "code",
-    "execution_count": null,
-    "metadata": {},
-    "outputs": [],
-    "source": [
-     "!git lfs install\n",
-     "!git clone https://huggingface.co/decapoda-research/llama-7b-hf"
-    ]
-   },
-   {
-    "cell_type": "markdown",
-    "metadata": {},
-    "source": [
-     "To avoid unexpexted confliction issues, we advise the user to modify the local `config.json` and `tokenizer_config.json` files according to the following recommendations:\n",
-     "\n",
-     "1. The `tokenizer_class` in `tokenizer_config.json` should be changed from `LLaMATokenizer` to `LlamaTokenizer`;\n",
-     "2. The `architectures` in `config.json` should be changed from `LLaMAForCausalLM` to `LlamaForCausalLM`"
-    ]    
-   },
-   {
-    "cell_type": "code",
-    "execution_count": null,
-    "metadata": {},
-    "outputs": [],
-    "source": [
-     "!curl -OL https://raw.githubusercontent.com/tatsu-lab/stanford_alpaca/main/alpaca_data.json"
-    ]
-   },
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!git lfs install\n",
+    "!git clone https://huggingface.co/decapoda-research/llama-7b-hf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To avoid unexpexted confliction issues, we advise the user to modify the local `config.json` and `tokenizer_config.json` files according to the following recommendations:\n",
+    "\n",
+    "1. The `tokenizer_class` in `tokenizer_config.json` should be changed from `LLaMATokenizer` to `LlamaTokenizer`;\n",
+    "2. The `architectures` in `config.json` should be changed from `LLaMAForCausalLM` to `LlamaForCausalLM`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!curl -OL https://raw.githubusercontent.com/tatsu-lab/stanford_alpaca/main/alpaca_data.json"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},

intel_extension_for_transformers/neural_chat/docs/notebooks/customize_chatbot_with_optimized_models.ipynb

@@ -25,7 +25,29 @@
    },
    "outputs": [],
    "source": [
-    "pip install intel-extension-for-transformers"
+    "!pip install intel-extension-for-transformers"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Install requirements:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "shellscript"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "!git clone https://github.com/intel/intel-extension-for-transformers.git\n",
+    "!cd ./intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/\n",
+    "!pip install -r requirements.txt"
    ]
   },
   {

intel_extension_for_transformers/neural_chat/docs/notebooks/deploy_chatbot_on_icx.ipynb

@@ -43,7 +43,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%cd ../../\n",
+    "!git clone https://github.com/intel/intel-extension-for-transformers.git\n",
+    "!cd ./intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/\n",
     "!pip install -r requirements.txt"
    ]
   },

intel_extension_for_transformers/neural_chat/docs/notebooks/deploy_chatbot_on_nv_a100.ipynb

@@ -43,7 +43,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%cd ../../\n",
+    "!git clone https://github.com/intel/intel-extension-for-transformers.git\n",
+    "!cd ./intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/\n",
     "!pip install -r requirements.txt"
    ]
   },

intel_extension_for_transformers/neural_chat/docs/notebooks/deploy_chatbot_on_spr.ipynb

@@ -45,7 +45,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%cd ../../\n",
+    "!git clone https://github.com/intel/intel-extension-for-transformers.git\n",
+    "!cd ./intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/\n",
     "!pip install -r requirements.txt"
    ]
   },

intel_extension_for_transformers/neural_chat/docs/notebooks/deploy_chatbot_on_xpu.ipynb

@@ -43,7 +43,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%cd ../../\n",
+    "!git clone https://github.com/intel/intel-extension-for-transformers.git\n",
+    "!cd ./intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/\n",
     "!pip install -r requirements.txt"
    ]
   },

intel_extension_for_transformers/neural_chat/docs/notebooks/finetuning_on_nv_a100.ipynb

@@ -34,7 +34,25 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install intel-extension-for-transformers"
+    "!pip install intel-extension-for-transformers"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Install requirements:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!git clone https://github.com/intel/intel-extension-for-transformers.git\n",
+    "!cd ./intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/\n",
+    "!pip install -r requirements.txt"
    ]
   },
   {

intel_extension_for_transformers/neural_chat/docs/notebooks/setup_talking_chatbot_service_on_spr.ipynb

@@ -27,9 +27,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!git clone https://github.com/intel/intel-extension-for-transformers.git && cd ./intel-extension-for-transformers/\n",
-    "!pip install -r requirements.txt && pip install -v .\n",
-    "!cd ./intel_extension_for_transformers/neural_chat/ && pip install -r requirements.txt"
+    "!pip install intel-extension-for-transformers\n",
+    "!git clone https://github.com/intel/intel-extension-for-transformers.git\n",
+    "!cd ./intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/\n",
+    "!pip install -r requirements.txt"
    ]
   },
   {

intel_extension_for_transformers/neural_chat/docs/notebooks/setup_text_chatbot_service_on_spr.ipynb

@@ -27,9 +27,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!git clone https://github.com/intel/intel-extension-for-transformers.git && cd ./intel-extension-for-transformers/ && pip install -r requirements.txt\n",
-    "!pip install -v .\n",
-    "!cd ./intel_extension_for_transformers/neural_chat/ && pip install -r requirements.txt\n",
+    "!pip install intel-extension-for-transformers\n",
+    "!git clone https://github.com/intel/intel-extension-for-transformers.git\n",
+    "!cd ./intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/\n",
+    "!pip install -r requirements.txt\n",
     "!sudo apt install numactl\n",
     "!conda install astunparse ninja pyyaml mkl mkl-include setuptools cmake cffi typing_extensions future six requests dataclasses -y\n",
     "!conda install jemalloc gperftools -c conda-forge -y"

intel_extension_for_transformers/neural_chat/docs/notebooks/single_node_finetuning_on_spr.ipynb

@@ -34,7 +34,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install intel-extension-for-transformers"
+    "!pip install intel-extension-for-transformers\n",
+    "!git clone https://github.com/intel/intel-extension-for-transformers.git\n",
+    "!cd ./intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/\n",
+    "!pip install -r requirements.txt"
    ]
   },
   {

intel_extension_for_transformers/neural_chat/docs/notebooks/weight_only_optimization_on_nv_a100.ipynb

@@ -43,7 +43,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%cd ../../\n",
+    "!git clone https://github.com/intel/intel-extension-for-transformers.git\n",
+    "!cd ./intel-extension-for-transformers/intel_extension_for_transformers/neural_chat/\n",
     "!pip install -r requirements.txt"
    ]
   },

intel_extension_for_transformers/neural_chat/models/neuralchat_model.py

@@ -17,7 +17,7 @@
 
 from .base_model import BaseModel, register_model_adapter
 import logging
-from fastchat.conversation import get_conv_template, Conversation, register_conv_template, SeparatorStyle
+from fastchat.conversation import get_conv_template, Conversation
 
 logging.basicConfig(
     format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
@@ -26,41 +26,6 @@
 )
 logger = logging.getLogger(__name__)
 
-# neuralchat-v2 prompt template
-register_conv_template(
-    Conversation(
-        name="neural-chat-7b-v2",
-        system_message="""### System:
-    - You are a helpful assistant chatbot trained by Intel.
-    - You answer questions.
-    - You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
-    - You are more than just an information source, you are also able to write poetry, \
-short stories, and make jokes.</s>\n""",
-        roles=("### User:", "### Assistant:"),
-        sep_style=SeparatorStyle.NO_COLON_TWO,
-        sep="\n",
-        sep2="</s>",
-    )
-)
-
-# neuralchat-v1.1 prompt template
-register_conv_template(
-    Conversation(
-        name="neural-chat-7b-v1.1",
-        system_template="""<|im_start|>system
-{system_message}""",
-        system_message="""- You are a helpful assistant chatbot trained by Intel.
-- You answer questions.
-- You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
-- You are more than just an information source, you are also able to write poetry, short stories, and make jokes.""",
-        roles=("<|im_start|>user", "<|im_start|>assistant"),
-        sep_style=SeparatorStyle.CHATML,
-        sep="<|im_end|>",
-        stop_token_ids=[50278, 0],
-    )
-)
-
-
 class NeuralChatModel(BaseModel):
     def match(self, model_path: str):
         """