fix requires for windows

README.md

@@ -305,7 +305,7 @@ cd LLaMA-Factory
 pip install -e .[metrics]
 ```
 
-Extra dependencies available: deepspeed, metrics, unsloth, vllm, bitsandbytes, gptq, awq, aqlm, qwen, quality
+Extra dependencies available: deepspeed, metrics, unsloth, galore, vllm, bitsandbytes, gptq, awq, aqlm, qwen, quality
 
 <details><summary>For Windows users</summary>
 

README_zh.md

@@ -305,7 +305,7 @@ cd LLaMA-Factory
 pip install -e .[metrics]
 ```
 
-可选的额外依赖项：deepspeed、metrics、unsloth、vllm、bitsandbytes、gptq、awq、aqlm、qwen、quality
+可选的额外依赖项：deepspeed、metrics、unsloth、galore、vllm、bitsandbytes、gptq、awq、aqlm、qwen、quality
 
 <details><summary>Windows 用户指南</summary>
 

requirements.txt

@@ -15,4 +15,3 @@ fastapi
 sse-starlette
 matplotlib
 fire
-galore-torch

setup.py

@@ -23,6 +23,7 @@ extra_require = {
     "deepspeed": ["deepspeed>=0.10.0"],
     "metrics": ["nltk", "jieba", "rouge-chinese"],
     "unsloth": ["torch==2.2.0", "unsloth[cu121-ampere-torch220]"],
+    "galore": ["galore-torch"],
     "vllm": ["vllm>=0.3.3"],
     "bitsandbytes": ["bitsandbytes>=0.39.0"],
     "gptq": ["optimum>=1.16.0", "auto-gptq>=0.5.0"],

src/llmtuner/chat/hf_engine.py

@@ -35,7 +35,7 @@ class HuggingfaceEngine(BaseEngine):
         self.template = get_template_and_fix_tokenizer(self.tokenizer, data_args.template)
         self.model = load_model(
             self.tokenizer, model_args, finetuning_args, is_trainable=False, add_valuehead=(not self.can_generate)
-        )
+        )  # must after fixing tokenizer to resize vocab
         self.generating_args = generating_args.to_dict()
 
     @staticmethod