423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-14 23:58:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

release v0.6.0

Browse Source 
Former-commit-id: 51910d5803eb718e4976da0b3bfcdc5eeeea48eb
This commit is contained in:
hiyouga 2024-03-25 22:38:56 +08:00
parent ac2a401b1d
commit daab85e3e6
5 changed files with 8 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

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

2
README_zh.md
View File

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

9
setup.py
View File

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

2
src/llmtuner/__init__.py
View File

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

2
src/llmtuner/train/rm/trainer.py
View File

@ -45,7 +45,7 @@ class PairwiseTrainer(Trainer):
Subclass and override to inject custom behavior. Subclass and override to inject custom behavior.
Note that the first element will be removed from the output tuple. 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 # Compute rewards
_, _, values = model(**inputs, output_hidden_states=True, return_dict=True) _, _, values = model(**inputs, output_hidden_states=True, return_dict=True)