-
Notifications
You must be signed in to change notification settings - Fork 4.9k
Pull requests: hiyouga/LLaMA-Factory
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
fixed slot args for FunctionFormatter in Qwen Templates
#6854
opened Feb 8, 2025 by
keatonelvins
Loading…
2 tasks done
Support padding-free for DPO
pending
This problem is yet to be addressed
#6753
opened Jan 24, 2025 by
yinzhijian
Loading…
2 tasks
A new training approach:RAFT
pending
This problem is yet to be addressed
#6689
opened Jan 17, 2025 by
yuhkalhic
Loading…
2 tasks done
Feature: Basic distilling.
pending
This problem is yet to be addressed
#6527
opened Jan 3, 2025 by
marko1616
Loading…
2 tasks
add Sequence Parallelism
pending
This problem is yet to be addressed
#6506
opened Jan 2, 2025 by
HaoshengZou
Loading…
2 tasks done
refactor(data): 重构mask方式，sharegpt 支持更精细的mask控制
#6498
opened Dec 31, 2024 by
zzc0430
Loading…
2 tasks done
Add the
logit_bias option in API serving
#6444
opened Dec 25, 2024 by
MrZhengXin
Loading…
2 tasks done
support continuous obvervation and optional pre-cutoff
#6441
opened Dec 25, 2024 by
AlongWY
Loading…
1 of 2 tasks
Add a loss_mask to control which outputs from the history are involved in the model's loss calculation.
pending
This problem is yet to be addressed
#6396
opened Dec 19, 2024 by
summerwuxia
Loading…
2 tasks done
Add PEFT add_weighted_adapter() Function for Merging Multiple Adapters
pending
This problem is yet to be addressed
#6310
opened Dec 11, 2024 by
Dlemonha
Loading…
add custom dataset config file as input
#6129
opened Nov 25, 2024 by
ex-yanminmin001
Loading…
2 tasks done
Improve error handling for missing image files in _convert_images
#6128
opened Nov 24, 2024 by
noahc1510
Loading…
2 tasks done
Set 'torch_device' as 'cpu' when loading pretrained adapter
#5993
opened Nov 11, 2024 by
LZHgrla
Loading…
2 tasks done
feat: Long Text Fine-Tuning Support
in-progress
The related features are in the progress
pending
This problem is yet to be addressed
#5532
opened Sep 24, 2024 by
glide-the
Loading…
[Update] loader.py , evaluate will run separate evaluations on each eval_dataset
pending
This problem is yet to be addressed
#5522
opened Sep 24, 2024 by
SrWYG
Loading…
Correctly pass gen_kwarg to eval during model runs
pending
This problem is yet to be addressed
#5451
opened Sep 16, 2024 by
aliencaocao
Loading…
1 of 2 tasks
[WIP] add florence2
pending
This problem is yet to be addressed
#5424
opened Sep 12, 2024 by
Sanster
Loading…
2 of 3 tasks
add dpop training
pending
This problem is yet to be addressed
#5339
opened Sep 3, 2024 by
threestone965
Loading…
2 tasks done
Support push model to ModelScope community
pending
This problem is yet to be addressed
#5326
opened Sep 2, 2024 by
tastelikefeet
Loading…
1 of 2 tasks
Load huggingface data with revision
pending
This problem is yet to be addressed
#5233
opened Aug 21, 2024 by
noiji
Loading…
2 tasks done
overwrite training_step for CustomDPOTrainer to clear cuda cache every train step
pending
This problem is yet to be addressed
#5019
opened Jul 30, 2024 by
zzc0430
Loading…
2 tasks done
Previous Next
ProTip!
Follow long discussions with comments:>50.