Spaces:

Dovakiins
/

qwerrwe

Build error

App Files Files Community

qwerrwe / src /axolotl /utils /data.py

Commit History

whoops, gt vs lt

84c7bc4

winglian commited on May 12, 2023

optimize dataloading to use cache, fix model token embedding sizes

aa3c3f9

winglian commited on May 12, 2023

black formatting

2bc1a5b

winglian commited on May 10, 2023

fix conditional so alpaca doesn't choke

a27d594

winglian commited on May 10, 2023

Add CompletionPrompt type

cf68153

Nanobit commited on May 8, 2023

Jeopardy bot! (#17)

a12fb0a
unverified

winglian commited on May 8, 2023

fix dataset handling, support galactica

4a17a4c

winglian commited on Apr 24, 2023

tweaks to data loading, 8 bit adam, accelerate and deepspeed

097d367

winglian commited on Apr 22, 2023

shuffle and split dataset after save/load

4f2584f

winglian commited on Apr 20, 2023

fix sharegpt handling from hf, don't worry about loading llama if using earlier transformers release

8d43785

winglian commited on Apr 20, 2023

various bugfixes

94f5e41

winglian commited on Apr 19, 2023

WIP large refactor to make finetune script a little more manageable (#3)

6045345
unverified

winglian commited on Apr 18, 2023

Commit History

whoops, gt vs lt 84c7bc4

optimize dataloading to use cache, fix model token embedding sizes aa3c3f9

black formatting 2bc1a5b

fix conditional so alpaca doesn't choke a27d594

Add CompletionPrompt type cf68153

Jeopardy bot! (#17) a12fb0a unverified

fix dataset handling, support galactica 4a17a4c

tweaks to data loading, 8 bit adam, accelerate and deepspeed 097d367

shuffle and split dataset after save/load 4f2584f

fix sharegpt handling from hf, don't worry about loading llama if using earlier transformers release 8d43785

various bugfixes 94f5e41

WIP large refactor to make finetune script a little more manageable (#3) 6045345 unverified