Commit History
Merge pull request #169 from NanoCode012/feat/landmark
b5aa8d8
unverified
Fix falcon support lora
b242b69
unverified
Improve lambda labs instruction
2e13cef
unverified
Feat: Add landmark attention
55b8542
Merge pull request #132 from utensil/falcon-7b-qlora
c8242de
unverified
Merge pull request #162 from NanoCode012/fix/custom-prompt-readme
f8d3798
unverified
Move custom prompts out of hidden
2097a09
Add peft install for quickstart
cfff94b
Update peft and gptq instruction
2b222de
update docs
5b33e29
Update README.md for correct image tags
618816d
unverified
added docker-compose file
84169d1
FarisHijazi
commited on
Merge pull request #142 from NanoCode012/feat/custom-prompt-readme
ecfe8d0
unverified
Remove redundant instruction
078a43e
Add pygmalion
33e1890
Add other prompt_strategies
1c38253
Add short instruction for custom prompts
496b83f
Add lambdalabs instruction
ff68a95
Update doc for grad_accu and add validation tests for batch size
3c71c8d
Merge pull request #130 from OpenAccess-AI-Collective/gas
f94dd62
unverified
Axolotl supports falcon + qlora
8afb0fb
unverified
swap batch size for gradient accumulation steps to decouple from num gpu
c2a0792
add badge info to readme
b267d24
Merge pull request #118 from NanoCode012/feat/torch-readme
0e4be62
unverified
Update README.md
bdc4bd7
unverified
Merge pull request #124 from OpenAccess-AI-Collective/xformers-fix
2d0ba3b
unverified
update readme for SDP
2675fb7
remove unused import and update readme
e3c494c
FIx(readme): Fix torch missing from readme
cf61f14
Merge pull request #108 from OpenAccess-AI-Collective/docker-gptq
bbc5bc5
unverified
Update pip install to also setup tests
b1cc54b
Add badge and update contribution section
afb31e1
cleanup from pr feedback
48612f8
update docs
d91a769
default to qlora support, make gptq specific image
6ef96f5
new hf_use_auth_token setting so login to hf isn't required
1c33eb8
Add `dataset_shard_num` and `dataset_shard_idx`
8626b54
Merge branch 'main' into refactor/rename-4b-to-gptq
147241c
unverified
add example for falcoln support
d5f944c
refactor(param): rename load_4bit config param by gptq
dd00657
Thytu
commited on