Hugging Face's logo

Spaces:
Dovakiins
/
qwerrwe
Build error

App Files Community
qwerrwe / examples

Commit History

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

Jamba (#1451)
02af082
unverified

winglian commited on

turn sample_packing on for training (#1438) [skip ci]
c19d060
unverified

satpalsr commited on

chore(config): refactor old mistral config (#1435)
f1ebaa0
unverified

Nanobit commited on

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

winglian commited on

Fix Gemma 7b qlora.yml (#1405)
6366b0c
unverified

rasbt commited on

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

seungduk commited on

FDSP + QLoRA (#1378)
9b6ee83
unverified

winglian commited on

Update tinyllama lora.yml to fix eval packing issue (#1362)
8984bf1
unverified

rasbt commited on

chore: enable sample_packing for Gemma (#1351)
170d4d7
unverified

Nanobit commited on

Mps mistral lora (#1292) [skip ci]
0f6af36
unverified

Maxime Nanobit winglian commited on

Add StableLM 2 Example Scripts (#1327) [skip ci]
f30d062
unverified

ncoop57 commited on

multipack for gemma (#1313)
2752d5f
unverified

winglian commited on

Adding Google's gemma Model (#1312)
9e300ac
unverified

aaditya commited on

Add instructions for playing with qlora model to colab example (#1290)
6ab69ec
unverified

Jared Palmer Nanobit JohanWork commited on

fix(examples): remove is_*_derived as it's parsed automatically (#1297)
a7a9a14
unverified

Nanobit commited on

Add seq2seq eval benchmark callback (#1274)
5a5d474
unverified

LeonardoEmili commited on

Add MPS support (#1264)
fac2d98
unverified

Maxime winglian commited on

lock pytorch (#1247) [skip ci]
1c7ed26
unverified

JohanWork commited on

Pretrain transforms (#1261)
c7cf381
unverified

winglian commited on

Peft lotfq (#1222)
4cb7900
unverified

winglian commited on

Update qlora.yml - remove `max_packed_sequence_len` (#1210) [skip ci]
5407ddd
unverified

7flash commited on

add colab example (#1196) [skip ci]
ee0b5f6
unverified

JohanWork commited on

Mixtral fixes 20240124 (#1192) [skip ci]
54d2ac1
unverified

winglian commited on

Phi2 multipack (#1173)
814aee6
unverified

winglian commited on

Fine-Tuning Mistral-7b for Real-World Chatbot Applications Using Axolotl (Lora used) (#1155)
cc25039
unverified

Tilemachos Chatzipapas twenty8th winglian commited on

Falcon embeddings (#1149) [skip docker]
e799e08
unverified

winglian commited on

set fp16 to false if bf16, update bf16: auto in example YAMLs (#1122) [skip ci]
782b6a4
unverified

winglian Nanobit commited on

Add shifted sparse attention (#973) [skip-ci]
1d70f24
unverified

jrc joecummings winglian commited on

pin model_revision for phi2 (#1123)
c1b741d
unverified

winglian commited on

Phi2 rewrite (#1058)
732851f
unverified

winglian commited on

streaming multipack for pretraining dataset (#959)
553c80f
unverified

jinwonkim93 jinwonkim93@github.com winglian commited on

fix: lint (#1037)
8ba27f3
unverified

Nanobit commited on

added tiny llama examples for lora and qlora (#1027)
c75f916
unverified

Tim Dolan commited on

Set eval_sample_packing to false in mistral config.yaml (#1003)
384b817
unverified

Kevin Sydney commited on

Add an example config for finetuning a 34B model on a 24GB GPU (#1000)
6ef46f8
unverified

Evan Griffiths commited on

set output_router_logits for mixtral config: (#995)
628b754
unverified

winglian commited on

change val size (#992)
93ebec1
unverified

mhenrichsen commited on

Fix Deepspeed loading (#950)
5ea3aa3
unverified

winglian commited on

new evals_per_epoch and saves_per_epoch to make things cleaner (#944)
5f79b82
unverified

winglian commited on

Mixtral official (#942)
7fabc4d
unverified

winglian commited on

update to latest transformers for mixstral support (#929)
35f9b0f
unverified

winglian commited on

Mixtral multipack (#928)
68b227a
unverified

winglian commited on

support for mamba (#915)
40a6362
unverified

winglian commited on

Feat(wandb): Refactor to be more flexible (#767)
a1da39c
unverified

Nanobit commited on

feature: loss watchdog for terminating training runs that are failing (#899)
58ec8b1
unverified

user735 Karl-Johan Alm commited on

fix: remove FA for qwen examples (#900)
a48dbf6
unverified

Nanobit commited on

Feat: Add Qwen (#894)
1115c50
unverified

Nanobit commited on