Hugging Face's logo

Spaces:
Dovakiins
/
qwerrwe
Build error

App Files Community
qwerrwe

Commit History

Merge pull request #182 from OpenAccess-AI-Collective/fix-llama-ref
0124825
unverified

winglian commited on

fix for local variable 'LlamaForCausalLM' referenced before assignment
14163c1

winglian commited on

Merge pull request #181 from OpenAccess-AI-Collective/xpos-rope
41e4f6c
unverified

winglian commited on

Merge pull request #180 from Glavin001/feat/stream-inference
215d775
unverified

winglian commited on

formatting for linter
f36e227
unverified

winglian commited on

add option to readme
5878bb1

winglian commited on

add support to extend context with xpos rope
a03a7d7

winglian commited on

Add streaming inference & fix stopping at EOS
fec6bcc

Glavin001 commited on

Merge pull request #179 from OpenAccess-AI-Collective/fix-max_seq_len
931e606
unverified

winglian commited on

fix for max sequence len across different model types
7f09106

winglian commited on

Merge pull request #178 from PocketDocLabs/main
6b50200
unverified

Nanobit commited on

Update README.md to reflect current gradient checkpointing support
16f9e28
unverified

PocketDoc commited on

Merge pull request #176 from NanoCode012/fix/peft-import
b9083a7
unverified

Nanobit commited on

Fix backward compat for peft
aefb2fc

Nanobit commited on

Merge pull request #169 from NanoCode012/feat/landmark
b5aa8d8
unverified

Nanobit commited on

Merge pull request #171 from OpenAccess-AI-Collective/NanoCode012-falcon-lora-matrix
4d6490b
unverified

Nanobit commited on

Fix falcon support lora
b242b69
unverified

Nanobit commited on

Merge pull request #170 from OpenAccess-AI-Collective/NanoCode012-lambdalabs-fix
320beb2
unverified

Nanobit commited on

Improve lambda labs instruction
2e13cef
unverified

Nanobit commited on

Fix grad checkpoint and outputs param
2a801b0

Nanobit commited on

Fix patching via import instead of hijacking
e44c9e0

Nanobit commited on

Feat: Add landmark attention
55b8542

Nanobit commited on

Merge pull request #168 from bratao/main
febe902
unverified

winglian commited on

Disable Wandb
f4df266

Bruno Cabral commited on

Merge pull request #167 from NanoCode012/fix/redundant-save-eval-steps
281dc3d
unverified

Nanobit commited on

Refactor out unmodified save_steps and eval_steps
2ef4634

Nanobit commited on

Merge pull request #166 from NanoCode012/fix/seed
7eae903
unverified

Nanobit commited on

Merge pull request #132 from utensil/falcon-7b-qlora
c8242de
unverified

Nanobit commited on

Set to use cfg.seed or 42 for backward compat
2cfe9e9

Nanobit commited on

Trim trailing whitespace
79a8f52
unverified

utensil commited on

Merge pull request #164 from NanoCode012/fix/falcon-fsdp-validate
afaa0d2
unverified

Nanobit commited on

Fix failing test
bfd27ba

Nanobit commited on

Validate falcon with fsdp
babf0fd

Nanobit commited on

Default `wandb_project` to empty as suggested
a52f481
unverified

utensil Nanobit commited on

Merge pull request #163 from NanoCode012/feat/matmul-tf32
81911d1
unverified

Nanobit commited on

Set matmul tf32
52765ac

Nanobit commited on

Merge pull request #143 from NanoCode012/fix/deprecate-prepare-8bit-training
73e9ea4
unverified

Nanobit commited on

Merge pull request #162 from NanoCode012/fix/custom-prompt-readme
f8d3798
unverified

Nanobit commited on

Merge pull request #161 from NanoCode012/fix/peft-setup
04a1b77
unverified

Nanobit commited on

Move custom prompts out of hidden
2097a09

Nanobit commited on

Add peft install for quickstart
cfff94b

Nanobit commited on

Update peft and gptq instruction
2b222de

Nanobit commited on

Fix future deprecate prepare_model_for_int8_training
df9528f

Nanobit commited on

Merge pull request #158 from OpenAccess-AI-Collective/prompter-fixes
6abfd87
unverified

winglian commited on

fix camel ai, add guanaco/oasst mapping for sharegpt
59bb219

winglian commited on

Merge pull request #155 from OpenAccess-AI-Collective/misc-fixes
9a02e7e
unverified

winglian commited on

update docs
5b33e29

winglian commited on

new prompters, misc fixes for output dir missing using fsdp, and changing max seq len
4ac9e25

winglian commited on

Default micro_batch_size to 1 for a safer start
c9c0503
unverified

utensil commited on

Add comments/alternatives for falcon-qlora configs
ca11ae9
unverified

utensil commited on