Hugging Face's logo

Spaces:
Dovakiins
/
qwerrwe
Build error

App Files Community
qwerrwe / README.md

Commit History

Agnostic cloud gpu docker image and Jupyter lab (#1097)
ece0211
unverified

winglian commited on

Add `layers_to_transform` for `lora_config` (#1118)
8487b97
unverified

xzuyn commited on

fix(readme): clarify custom user prompt [no-ci] (#1124)
9cd27b2
unverified

Nanobit commited on

Add link on README to Docker Debugging (#1107)
2dc4310
unverified

hamel winglian commited on

Update README.md (#1103)
b502392
unverified

hamel commited on

Add Debugging Guide (#1089)
7512c3a
unverified

hamel winglian commited on

paired kto support (#1069)
d7057cc
unverified

winglian commited on

Add: mlflow for experiment tracking (#1059) [skip ci]
090c24d
unverified

Johan Hansson winglian commited on

Cosine learning rate schedule - minimum learning rate (#1062)
04b978b
unverified

ricdomolm winglian commited on

Sponsors (#1065)
1496441
unverified

winglian commited on

feature: better device mapping for large models (#918)
bdfefaf
unverified

kallewoof Karl-Johan Alm winglian commited on

set default for merge (#1044)
63fb3eb
unverified

hamel commited on

[Docs] delete unused cfg value `lora_out_dir` (#1029)
a3e8783
unverified

hamel Nanobit commited on

chore(readme): update instruction to set config to load from cache (#1030)
b31038a
unverified

Nanobit commited on

use recommended setting for use_reentrant w gradient checkpointing (#1021)
4d2e842
unverified

winglian commited on

Adds chat templates (#1022)
f8ae59b
unverified

mhenrichsen commited on

feat: expose bnb kwargs (#1018)
41353d2
unverified

Nanobit hamel commited on

feat: remove need to add load_in* during merge (#1017)
f6ecf14
unverified

Nanobit commited on

[Docs] Nit: Remind people to auth to wandb if they are going to use it (#1013)
dec66d7
unverified

hamel commited on

Update README.md (#1012)
76357dc
unverified

hamel commited on

remove landmark attn and xpos rope implementations (#1010)
70b46ca
unverified

winglian commited on

Update README.md (#966)
d25c34c
unverified

eltociear commited on

Add docs (#947)
712fd27
unverified

hamel winglian commited on

fix: switch to using the HuggingFace Transformers NEFT implementation (#941)
ef24342
unverified

kallewoof commited on

More hints on what to do with CUDA Out of memory errors (#925)
b0cf397
unverified

Juraj Bednar commited on

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

winglian commited on

Mixtral multipack (#928)
68b227a
unverified

winglian commited on

chore: clarify Readme on sharegpt system role
d339beb
unverified

Nanobit commited on

Support device_map=sequential & max_memory config parameters (#903)
992e742
unverified

Bryan Thornbury 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

Feat: Add Qwen (#894)
1115c50
unverified

Nanobit commited on

Feat: Add warmup_ratio (#893)
fb12895
unverified

Nanobit commited on

chore(doc): Add info on changing role in sharegpt (#886)
9fc29e0
unverified

Nanobit commited on

Install from git url (#874)
ddf8150
unverified

marksaroufim commited on

try #2: pin hf transformers and accelerate to latest release, don't reinstall pytorch (#867)
0de1457
unverified

winglian commited on

Feat: Add dataset loading from S3, GCS (#765)
3cc67d2
unverified

Nanobit commited on

allow overriding of model_config parameters from the YML (#853)
1bc1186
unverified

winglian commited on

make docker command more robust (#861)
8a8d1c4
unverified

winglian commited on

lint fix that didn't get caught by linter (#866)
332984d
unverified

winglian commited on

Docs: add instructions to 1-click launching on public clouds (#862)
b33c1d5
unverified

zongheng commited on

chore(doc): Separate section on runpod (#860)
501b4d1
unverified

Nanobit commited on

feat(doc): add more info on train_on_split (#855)
306fe19
unverified

Nanobit commited on

Feat: Added Gradio support (#812)
738a057
unverified

stillerman commited on

update table for rwkv4 support, fix process count for dataset (#822)
cdc71f7
unverified

winglian commited on

fix eval_steps to be a sane default (#797)
8b79ff0
unverified

winglian commited on

Add docker advanced instruction to README (#792)
2e71ff0
unverified

gordicaleksa commited on

Create preprocess CLI (#785)
e50ab07
unverified

casperhansen commited on

chore(readme): Improve documentation on conversation field (#782)
20aa4b5
unverified

Nanobit commited on

Fix: Cannot tokenize with bf16 and on cpu (#766)
afedc47
unverified

Nanobit commited on