readme: Update inference code

Signed-off-by: huangyi <[email protected]>

README.md

@@ -171,9 +171,13 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from transformers.generation.utils import GenerationConfig
 
-tokenizer = AutoTokenizer.from_pretrained("OrionStarAI/Orion-MOE8x7B-Base", use_fast=False, trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("OrionStarAI/Orion-MOE8x7B", device_map="auto",
-                                             torch_dtype=torch.bfloat16, trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("OrionStarAI/Orion-MOE8x7B-Base",
+                                          use_fast=False,
+                                          trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("OrionStarAI/Orion-MOE8x7B-Base",
+                                             device_map="auto",
+                                             torch_dtype=torch.bfloat16,
+                                             trust_remote_code=True)
 
 model.generation_config = GenerationConfig.from_pretrained("OrionStarAI/Orion-MOE8x7B-Base")
 messages = [{"role": "user", "content": "Hello, what is your name? "}]
@@ -190,10 +194,7 @@ device, you can use something like `export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7`
 ```shell
 
 # base model
-CUDA_VISIBLE_DEVICES=0 python demo/text_generation_base.py --model OrionStarAI/Orion-MOE8x7B --tokenizer OrionStarAI/Orion-MOE8x7B --prompt hello
-
-# chat model
-CUDA_VISIBLE_DEVICES=0 python demo/text_generation.py --model OrionStarAI/Orion-MOE8x7B-Chat --tokenizer OrionStarAI/Orion-MOE8x7B-Chat --prompt hi
+CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python demo/text_generation_base.py --model OrionStarAI/Orion-MOE8x7B-Base --tokenizer OrionStarAI/Orion-MOE8x7B-Base --prompt hello
 
 ```
 

README_zh.md

@@ -1,4 +1,3 @@
-
 <!-- markdownlint-disable first-line-h1 -->
 <!-- markdownlint-disable html -->
 <div align="center">
@@ -14,7 +13,7 @@
 <div align="center">
 
 <div align="center">
-     <b>🇨🇳中文</b> | <a href="./README.md">🌐English</a> 
+     <b>🇨🇳中文</b> | <a href="./README.md">🌐English</a>
 </div>
 
 <h4 align="center">
@@ -170,9 +169,13 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from transformers.generation.utils import GenerationConfig
 
-tokenizer = AutoTokenizer.from_pretrained("OrionStarAI/Orion-MOE8x7B-Base", use_fast=False, trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("OrionStarAI/Orion-MOE8x7B-Base", device_map="auto",
-                                             torch_dtype=torch.bfloat16, trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("OrionStarAI/Orion-MOE8x7B-Base",
+                                          use_fast=False,
+                                          trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("OrionStarAI/Orion-MOE8x7B-Base",
+                                             device_map="auto",
+                                             torch_dtype=torch.bfloat16,
+                                             trust_remote_code=True)
 
 model.generation_config = GenerationConfig.from_pretrained("OrionStarAI/Orion-MOE8x7B-Base")
 messages = [{"role": "user", "content": "你好! 你叫什么名字!"}]
@@ -188,17 +191,14 @@ print(response)
 ## 4.2. 脚本直接推理
 
 ```shell
-# base model
-CUDA_VISIBLE_DEVICES=0 python demo/text_generation_base.py --model OrionStarAI/Orion-14B --tokenizer OrionStarAI/Orion-14B --prompt 你好,你叫什么名字
 
-# chat model
-CUDA_VISIBLE_DEVICES=0 python demo/text_generation.py --model OrionStarAI/Orion-14B-Chat --tokenizer OrionStarAI/Orion-14B-Chat --prompt 你好,你叫什么名字
+# base model
+CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python demo/text_generation_base.py --model OrionStarAI/Orion-MOE8x7B-Base --tokenizer OrionStarAI/Orion-MOE8x7B-Base --prompt 你好,你叫什么名字
 
 ```
 
 
 
-
 <a name="zh_declarations-license"></a><br>
 # 5. 声明、协议