release v0.6.0

README.md

@@ -416,7 +416,7 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --lr_scheduler_type cosine \
     --logging_steps 10 \
     --save_steps 1000 \
-    --learning_rate 1e-6 \
+    --learning_rate 1e-5 \
     --num_train_epochs 1.0 \
     --plot_loss \
     --fp16

README_zh.md

@@ -415,7 +415,7 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --lr_scheduler_type cosine \
     --logging_steps 10 \
     --save_steps 1000 \
-    --learning_rate 1e-6 \
+    --learning_rate 1e-5 \
     --num_train_epochs 1.0 \
     --plot_loss \
     --fp16

setup.py

@@ -20,15 +20,14 @@ def get_requires():
 
 
 extra_require = {
-    "deepspeed": ["deepspeed==0.13.1"],
+    "deepspeed": ["deepspeed"],
     "metrics": ["nltk", "jieba", "rouge-chinese"],
-    "unsloth": ["torch==2.2.0", "unsloth[cu121-ampere-torch220] @ git+https://github.com/unslothai/unsloth.git"],
-    "vllm": ["vllm==0.3.3"],
+    "unsloth": ["torch==2.2.0", "unsloth[cu121-ampere-torch220]"],
+    "vllm": ["vllm>=0.3.3"],
     "bitsandbytes": ["bitsandbytes>=0.39.0"],
     "gptq": ["optimum>=1.16.0", "auto-gptq>=0.5.0"],
     "awq": ["autoawq"],
-    "aqlm": ["aqlm[gpu]>=1.1.0", "transformers @ git+https://github.com/huggingface/transformers.git"],
-    "galore": ["galore_torch @ git+https://github.com/hiyouga/GaLore.git"],
+    "aqlm": ["aqlm[gpu]>=1.1.0"],
     "qwen": ["tiktoken", "transformers_stream_generator"],
     "quality": ["ruff"],
 }

src/llmtuner/__init__.py

@@ -7,5 +7,5 @@ from .train import export_model, run_exp
 from .webui import create_ui, create_web_demo
 
 
-__version__ = "0.5.3"
+__version__ = "0.6.0"
 __all__ = ["create_app", "ChatModel", "Evaluator", "export_model", "run_exp", "create_ui", "create_web_demo"]

src/llmtuner/train/rm/trainer.py

@@ -45,7 +45,7 @@ class PairwiseTrainer(Trainer):
         Subclass and override to inject custom behavior.
 
         Note that the first element will be removed from the output tuple.
-        See: https://github.com/huggingface/transformers/blob/v4.30.2/src/transformers/trainer.py#L3509
+        See: https://github.com/huggingface/transformers/blob/v4.39.1/src/transformers/trainer.py#L3777
         """
         # Compute rewards
         _, _, values = model(**inputs, output_hidden_states=True, return_dict=True)