fix_internlm-chat-7b-8k repo name in examples (#10747)

python/llm/example/CPU/HF-Transformers-AutoModels/Model/internlm/README.md

@@ -1,6 +1,6 @@
 # InternLM
 
-In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on InternLM models. For illustration purposes, we utilize the [internlm/internlm-chat-7b-8k](https://huggingface.co/internlm/internlm-chat-7b-8k) as a reference InternLM model.
+In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on InternLM models. For illustration purposes, we utilize the [internlm/internlm-chat-7b](https://huggingface.co/internlm/internlm-chat-7b) as a reference InternLM model.
 
 ## 0. Requirements
 To run these examples with IPEX-LLM, we have some recommended requirements for your machine, please refer to [here](../README.md#recommended-requirements) for more information.
@@ -22,7 +22,7 @@ python ./generate.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --prompt PROM
 ```
 
 Arguments info:
-- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the InternLM model to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'internlm/internlm-chat-7b-8k'`.
+- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the InternLM model to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'internlm/internlm-chat-7b'`.
 - `--prompt PROMPT`: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be `'AI是什么？'`.
 - `--n-predict N_PREDICT`: argument defining the max number of tokens to predict. It is default to be `32`.
 
@@ -50,7 +50,7 @@ numactl -C 0-47 -m 0 python ./generate.py
 ```
 
 #### 2.3 Sample Output
-#### [internlm/internlm-chat-7b-8k](https://huggingface.co/internlm/internlm-chat-7b-8k)
+#### [internlm/internlm-chat-7b](https://huggingface.co/internlm/internlm-chat-7b)
 ```log
 Inference time: xxxx s
 -------------------- Prompt --------------------

python/llm/example/CPU/HF-Transformers-AutoModels/Model/internlm/generate.py

@@ -23,12 +23,12 @@ from ipex_llm.transformers import AutoModelForCausalLM
 from transformers import AutoTokenizer
 
 # you could tune the prompt based on your own model,
-# here the prompt tuning refers to https://huggingface.co/internlm/internlm-chat-7b-8k/blob/main/modeling_internlm.py#L768
+# here the prompt tuning refers to https://huggingface.co/internlm/internlm-chat-7b/blob/main/modeling_internlm.py#L1053
 INTERNLM_PROMPT_FORMAT = "<|User|>:{prompt}\n<|Bot|>:"
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(description='Predict Tokens using `generate()` API for InternLM model')
-    parser.add_argument('--repo-id-or-model-path', type=str, default="internlm/internlm-chat-7b-8k",
+    parser.add_argument('--repo-id-or-model-path', type=str, default="internlm/internlm-chat-7b",
                         help='The huggingface repo id for the InternLM model to be downloaded'
                              ', or the path to the huggingface checkpoint folder')
     parser.add_argument('--prompt', type=str, default="AI是什么？",

python/llm/example/CPU/HF-Transformers-AutoModels/Model/internlm2/generate.py

@@ -22,7 +22,7 @@ import numpy as np
 from transformers import AutoTokenizer
 
 # you could tune the prompt based on your own model,
-# here the prompt tuning refers to https://huggingface.co/internlm/internlm-chat-7b-8k/blob/main/modeling_internlm.py#L768
+# here the prompt tuning refers to https://huggingface.co/internlm/internlm-chat-7b/blob/main/modeling_internlm.py#L1053
 INTERNLM_PROMPT_FORMAT = "<|User|>:{prompt}\n<|Bot|>:"
 
 if __name__ == '__main__':

python/llm/example/CPU/PyTorch-Models/Model/internlm2/generate.py

@@ -23,7 +23,7 @@ from ipex_llm import optimize_model
 from transformers import AutoTokenizer
 
 # you could tune the prompt based on your own model,
-# here the prompt tuning refers to https://huggingface.co/internlm/internlm-chat-7b-8k/blob/main/modeling_internlm.py#L768
+# here the prompt tuning refers to https://huggingface.co/internlm/internlm-chat-7b/blob/main/modeling_internlm.py#L1053
 INTERNLM_PROMPT_FORMAT = "<|User|>:{prompt}\n<|Bot|>:"
 
 if __name__ == '__main__':

python/llm/example/GPU/HF-Transformers-AutoModels/Model/internlm/README.md

@@ -1,5 +1,5 @@
 # InternLM
-In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on InternLM models on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [internlm/internlm-chat-7b-8k](https://huggingface.co/internlm/internlm-chat-7b-8k) as a reference InternLM model.
+In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on InternLM models on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [internlm/internlm-chat-7b](https://huggingface.co/internlm/internlm-chat-7b) as a reference InternLM model.
 
 ## 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.
@@ -100,12 +100,12 @@ python ./generate.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --prompt PROM
 ```
 
 Arguments info:
-- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the InternLM model (e.g. `internlm/internlm-chat-7b-8k`) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'internlm/internlm-chat-7b-8k'`.
+- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the InternLM model (e.g. `internlm/internlm-chat-7b`) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'internlm/internlm-chat-7b'`.
 - `--prompt PROMPT`: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be `'AI是什么？'`.
 - `--n-predict N_PREDICT`: argument defining the max number of tokens to predict. It is default to be `32`.
 
 #### Sample Output
-#### [internlm/internlm-chat-7b-8k](https://huggingface.co/internlm/internlm-chat-7b-8k)
+#### [internlm/internlm-chat-7b](https://huggingface.co/internlm/internlm-chat-7b)
 ```log
 Inference time: xxxx s
 -------------------- Prompt --------------------

python/llm/example/GPU/HF-Transformers-AutoModels/Model/internlm/generate.py

@@ -22,12 +22,12 @@ from ipex_llm.transformers import AutoModelForCausalLM
 from transformers import AutoTokenizer
 
 # you could tune the prompt based on your own model,
-# here the prompt tuning refers to https://huggingface.co/internlm/internlm-chat-7b-8k/blob/main/modeling_internlm.py#L768
+# here the prompt tuning refers to https://huggingface.co/internlm/internlm-chat-7b/blob/main/modeling_internlm.py#L1053
 INTERNLM_PROMPT_FORMAT = "<|User|>:{prompt}\n<|Bot|>:"
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(description='Predict Tokens using `generate()` API for InternLM model')
-    parser.add_argument('--repo-id-or-model-path', type=str, default="internlm/internlm-chat-7b-8k",
+    parser.add_argument('--repo-id-or-model-path', type=str, default="internlm/internlm-chat-7b",
                         help='The huggingface repo id for the InternLM model to be downloaded'
                              ', or the path to the huggingface checkpoint folder')
     parser.add_argument('--prompt', type=str, default="AI是什么？",

python/llm/example/GPU/HF-Transformers-AutoModels/Model/internlm2/generate.py

@@ -23,7 +23,7 @@ from ipex_llm import optimize_model
 import intel_extension_for_pytorch as ipex
 
 # you could tune the prompt based on your own model,
-# here the prompt tuning refers to https://huggingface.co/internlm/internlm-chat-7b-8k/blob/main/modeling_internlm.py#L768
+# here the prompt tuning refers to https://huggingface.co/internlm/internlm-chat-7b/blob/main/modeling_internlm.py#L1053
 INTERNLM_PROMPT_FORMAT = "<|User|>:{prompt}\n<|Bot|>:"
 
 if __name__ == '__main__':

python/llm/example/GPU/PyTorch-Models/Model/internlm2/generate.py

@@ -23,7 +23,7 @@ from ipex_llm import optimize_model
 import intel_extension_for_pytorch as ipex
 
 # you could tune the prompt based on your own model,
-# here the prompt tuning refers to https://huggingface.co/internlm/internlm-chat-7b-8k/blob/main/modeling_internlm.py#L768
+# here the prompt tuning refers to https://huggingface.co/internlm/internlm-chat-7b/blob/main/modeling_internlm.py#L1053
 INTERNLM_PROMPT_FORMAT = "<|User|>:{prompt}\n<|Bot|>:"
 
 if __name__ == '__main__':

python/llm/portable-zip/README.md

@@ -15,7 +15,7 @@ This portable zip includes everything you need to run an LLM with IPEX-LLM optim
 - ChatGLM2-6b
 - Baichuan-13B-Chat
 - Baichuan2-7B-Chat
-- internlm-chat-7b-8k
+- internlm-chat-7b
 - Llama-2-7b-chat-hf
 
 ## How to use