Merge branch 'main' of https://github.com/BUAADreamer/LLaMA-Factory

README.md

@@ -310,13 +310,19 @@ huggingface-cli login
 
 ### Installation
 
+> [!IMPORTANT]
+> Installation is mandatory.
+
 ```bash
 git clone https://github.com/hiyouga/LLaMA-Factory.git
 cd LLaMA-Factory
-pip install -e .[metrics]
+pip install -e .[torch,metrics]
 ```
 
-Extra dependencies available: metrics, deepspeed, bitsandbytes, vllm, galore, badam, gptq, awq, aqlm, qwen, modelscope, quality
+Extra dependencies available: torch, metrics, deepspeed, bitsandbytes, vllm, galore, badam, gptq, awq, aqlm, qwen, modelscope, quality
+
+> [!TIP]
+> Use `pip install --no-deps -e .` to resolve package conflicts.
 
 <details><summary>For Windows users</summary>
 

README_zh.md

@@ -310,13 +310,19 @@ huggingface-cli login
 
 ### 安装 LLaMA Factory
 
+> [!IMPORTANT]
+> 此步骤为必需。
+
 ```bash
 git clone https://github.com/hiyouga/LLaMA-Factory.git
 cd LLaMA-Factory
-pip install -e .[metrics]
+pip install -e .[torch,metrics]
 ```
 
-可选的额外依赖项：metrics、deepspeed、bitsandbytes、vllm、galore、badam、gptq、awq、aqlm、qwen、modelscope、quality
+可选的额外依赖项：torch、metrics、deepspeed、bitsandbytes、vllm、galore、badam、gptq、awq、aqlm、qwen、modelscope、quality
+
+> [!TIP]
+> 遇到包冲突时，可使用 `pip install --no-deps -e .` 解决。
 
 <details><summary>Windows 用户指南</summary>
 

data/dataset_info.json

@@ -41,7 +41,7 @@
   },
   "glaive_toolcall": {
     "file_name": "glaive_toolcall_10k.json",
-    "file_sha1": "a6917b85d209df98d31fdecb253c79ebc440f6f3",
+    "file_sha1": "36aea64548fbf6aa300bef411b9221092ed84902",
     "formatting": "sharegpt",
     "columns": {
       "messages": "conversations",

requirements.txt

@@ -1,4 +1,3 @@
-torch>=1.13.1
 transformers>=4.37.2
 datasets>=2.14.3
 accelerate>=0.27.2

setup.py

@@ -20,6 +20,7 @@ def get_requires():
 
 
 extra_require = {
+    "torch": ["torch>=1.13.1"],
     "metrics": ["nltk", "jieba", "rouge-chinese"],
     "deepspeed": ["deepspeed>=0.10.0,<=0.14.0"],
     "bitsandbytes": ["bitsandbytes>=0.39.0"],

src/llmtuner/api/app.py

@@ -1,6 +1,8 @@
 import os
 from contextlib import asynccontextmanager
-from typing import Annotated, Optional
+from typing import Optional
+
+from typing_extensions import Annotated
 
 from ..chat import ChatModel
 from ..extras.misc import torch_gc