Hugging Face's logo

Spaces:
Dovakiins
/
qwerrwe
Build error

App Files Community
qwerrwe / src

Commit History

add support for cohere chat template (#1478)
05b0b7e
unverified

winglian commited on

don't use deepspeed or fsdp when merging loras (#1479)
87ca3f9
unverified

winglian commited on

refactor utils.data module for line count linter (#1476)
e0fcef4
unverified

winglian commited on

Pretrain multipack v2 (#1470)
5aa5097
unverified

winglian commited on

fix pretraining_ on odd datasets (#1463)
586bd8d
unverified

monsoon-nlp commited on

reduce verbosity of the special tokens (#1472)
0b10377
unverified

winglian commited on

LISA (#1469)
0ddfb24
unverified

winglian tmm1 commited on

qwen2_moe support w multipack (#1455)
6086be8
unverified

winglian commited on

fix some of the edge cases for Jamba (#1452)
05b398a
unverified

winglian commited on

Support loading datasets saved via save_to_disk (#1432)
e634118
unverified

Keith Stevens commited on

Jamba (#1451)
02af082
unverified

winglian commited on

fix layer_replication arg to peft (#1446)
4155e99
unverified

winglian commited on

support layer replication for peft and fix rslora integration (#1445)
25afd35
unverified

winglian commited on

fix for accelerate env var for auto bf16, add new base image and expand torch_cuda_arch_list support (#1413)
da265dd
unverified

winglian commited on

Remove seq_len arg in rotary_emb (#1443)
e07347b
unverified

wenbopan winglian commited on

Fix falcon tokenization step (#1441) [skip ci]
bcdc9b1
unverified

Far El winglian commited on

make sure to capture non-null defaults from config validation (#1415)
601b77b
unverified

winglian commited on

fix(dataset): normalize tokenizer config and change hash from tokenizer class to tokenizer path (#1298)
ff939d8
unverified

Nanobit commited on

Fix ORPO multi gpu (#1433)
34ba634
unverified

winglian commited on

strip out hacky qlora-fsdp workarounds now that qlora-fsdp fixes are upstreamed (#1428)
2a1589f
unverified

winglian commited on

HF / FEAT: Optimize HF tags (#1425) [skip ci]
7d55607
unverified

Younes Belkada winglian commited on

fixes for dpo and orpo template loading (#1424)
7803f09
unverified

winglian commited on

support galore once upstreamed into transformers (#1409)
dd449c5
unverified

winglian commited on

Feat: Add sharegpt multirole (#1137)
40a88e8
unverified

Nanobit commited on

Add a config not to shuffle merged dataset (#1394) [skip ci]
43bdc5d
unverified

seungduk winglian commited on

fix(config): passing gradient_checkpoint_kwargs (#1412)
b1e3e1b
unverified

Nanobit commited on

ORPO (#1419)
2ea70eb
unverified

winglian commited on

chore(script): remove redundant setting (#1411)
d485a08
unverified

Nanobit commited on

beta support for multipack with gemmoe: (#1402)
8df7b88
unverified

winglian commited on

Train parameters exclusively in specific ranges (#1390)
05bcc9e
unverified

seungduk commited on

Don't disable existing loggers when configuring axolotl logging (#1395)
3bd8203
unverified

chiragjn commited on

Update ChatTemplate enum to include alpaca and gemma (#1396)
0976781
unverified

chiragjn commited on

add handling for argilla dpo-mix (#1397)
8a82d2e
unverified

winglian commited on

chore: lint (#1389)
4326520
unverified

winglian commited on

Add Glaive conversation format support (#1365)
b7d8a7d
unverified

Brian Fitzgerald winglian commited on

Fix pydantic configuration for the max_memory input (#1385) [skip ci]
0bc114d
unverified

dandm1 winglian commited on

support for rslora (#1387) [skip ci]
7659c00
unverified

winglian commited on

validation for fsdp and deepspeed (#1388) [skip ci]
3fd8093
unverified

winglian commited on

FDSP + QLoRA (#1378)
9b6ee83
unverified

winglian commited on

support for DoRA w/ PEFT (#1363)
0cfdb2c
unverified

winglian commited on

allow the sharegpt handler to also better handle datasets destined for openai finetuning (#1361)
2598c9f
unverified

winglian commited on

lora+ support (#1352)
decb66e
unverified

winglian commited on

plain input/output prompt strategy w/o chat templates (#1346)
4d09b42
unverified

winglian commited on

Fix validation for early stopping (#1358)
b5b4492
unverified

chiragjn commited on

fix for protected model_ namespace w pydantic (#1345)
6b3b271
unverified

winglian commited on

Fix `use_mlflow` to be bool instead of str (#1344)
3a5a2d2
unverified

chiragjn commited on

more fixes 20240228 (#1342) [skip ci]
0f985e1
unverified

winglian commited on

add gemma instruct chat template (#1341)
c1a7b3d
unverified

winglian commited on

Update fastchat_conversation_turns.py (#1294) [skip ci]
2b9687f
unverified

eltociear commited on