Hugging Face's logo

Spaces:
Dovakiins
/
qwerrwe
Build error

App Files Community
qwerrwe

Commit History

Merge pull request #148 from OpenAccess-AI-Collective/fix-device-load
4ab0c8b
unverified

winglian commited on

fix device map
74ebbf4

winglian commited on

Merge pull request #147 from OpenAccess-AI-Collective/winglian-rocker-images
76a70fd
unverified

winglian commited on

Update README.md for correct image tags
618816d
unverified

winglian commited on

Merge pull request #146 from FarisHijazi/main
91992cb
unverified

winglian commited on

added docker-compose file
84169d1

FarisHijazi commited on

Merge pull request #142 from NanoCode012/feat/custom-prompt-readme
ecfe8d0
unverified

winglian commited on

Merge pull request #141 from NanoCode012/feat/lambdalabs-readme
eee44a3
unverified

winglian commited on

Remove redundant instruction
078a43e

Nanobit commited on

Add pygmalion
33e1890

Nanobit commited on

Add other prompt_strategies
1c38253

Nanobit commited on

Add short instruction for custom prompts
496b83f

Nanobit commited on

Add lambdalabs instruction
ff68a95

Nanobit commited on

falcon + qlora + xformer mbs 40 gas 2 on A6000
fb3d40f
unverified

utensil commited on

Merge pull request #135 from NanoCode012/fix/grad-accu-readme
288fd62
unverified

Nanobit commited on

Update doc for grad_accu and add validation tests for batch size
3c71c8d

Nanobit commited on

Merge pull request #134 from OpenAccess-AI-Collective/gas-batch-fix
a6f5e5e
unverified

winglian commited on

fix batch size calculation
5a631b3

winglian commited on

Merge pull request #130 from OpenAccess-AI-Collective/gas
f94dd62
unverified

winglian commited on

Merge pull request #131 from OpenAccess-AI-Collective/fix-packing-mask
5079753
unverified

winglian commited on

don't worry about duplicate code here
0136f51

winglian commited on

Create config-7b-qlora.yml
72bf8aa
unverified

utensil commited on

Axolotl supports falcon + qlora
8afb0fb
unverified

utensil commited on

fix packing so that concatenated sequences reset the attention
9b8585d

winglian commited on

Merge pull request #129 from OpenAccess-AI-Collective/builder-badge
8eb5811
unverified

winglian commited on

Fix base builder, missing tags
e0011fd

winglian commited on

Merge pull request #127 from OpenAccess-AI-Collective/py310-docker-runpod
6e9e987
unverified

winglian commited on

swap batch size for gradient accumulation steps to decouple from num gpu
c2a0792

winglian commited on

add badge info to readme
b267d24

winglian commited on

Add files via upload
5c3f5db
unverified

winglian commited on

add py310 support from base image
e3d0374

winglian commited on

Merge pull request #119 from NanoCode012/feat/update-inference
fac4600
unverified

Nanobit commited on

Increase max_new_tokens
33d4017
unverified

Nanobit winglian commited on

Merge pull request #114 from OpenAccess-AI-Collective/accelerate-dep
dcb03d6
unverified

winglian commited on

Merge pull request #118 from NanoCode012/feat/torch-readme
0e4be62
unverified

Nanobit commited on

Update README.md
bdc4bd7
unverified

Nanobit commited on

Merge pull request #124 from OpenAccess-AI-Collective/xformers-fix
2d0ba3b
unverified

winglian commited on

Merge pull request #120 from OpenAccess-AI-Collective/model-from-path
c7021e1
unverified

winglian commited on

don't worry about dupes
c56818b

winglian commited on

update readme for SDP
2675fb7

winglian commited on

Update src/axolotl/monkeypatch/llama_attn_hijack_xformers.py
1076bcb
unverified

winglian Nanobit commited on

Update src/axolotl/monkeypatch/llama_attn_hijack_xformers.py
2daa683
unverified

winglian Nanobit commited on

remove unused import and update readme
e3c494c

winglian commited on

black formatting
ad0ea6a

winglian commited on

Merge pull request #123 from OpenAccess-AI-Collective/bas-batch
876edd8
unverified

winglian commited on

copy xformers attn from ooba since we removed dep on alpaca_lora_4bit
6cb2310

winglian commited on

black formatting
6fa40bf

winglian commited on

add support for gradient accumulation steps
3aad5f3

winglian commited on

fix up tokenizer config, isort fix
39a208c

winglian commited on

split up llama model loading so config can be loaded from base config and models can be loaded from a path
2520ecd

winglian commited on