Spaces:

Dovakiins
/

qwerrwe

Build error

App Files Files Community

qwerrwe / examples /code-llama

Commit History

update outputs path so that we can mount workspace to /workspace/data (#1623)

4fde300
unverified

winglian commited on May 15

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

a7a9a14
unverified

Nanobit commited on Feb 21

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

782b6a4
unverified

winglian

Nanobit commited on Jan 22

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

1d70f24
unverified

jrc joecummings

winglian commited on Jan 18

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

5f79b82
unverified

winglian commited on Dec 12, 2023

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

a1da39c
unverified

Nanobit commited on Dec 4, 2023

don't compile deepspeed or bitsandbytes from source (#837)

f544ab2
unverified

winglian commited on Nov 9, 2023

fix eval_steps to be a sane default (#797)

8b79ff0
unverified

winglian commited on Oct 28, 2023

simplify by removing duplicate base_model_config (#772)

2d8def6
unverified

winglian commited on Oct 23, 2023

prepared dataset caching, other misc fixes (#665)

e50a64e
unverified

winglian commited on Oct 3, 2023

Fix Codellama examples (#582)

1aa4007
unverified

Doan Minh Phuong commited on Sep 15, 2023

recommend padding when using sample packing (#531)

3437149
unverified

winglian commited on Sep 6, 2023

Feat(cfg): Add code-llama configs for all sizes (#479)

3513071
unverified

mhenrichsen mhenrichsen commited on Aug 27, 2023

Commit History

update outputs path so that we can mount workspace to /workspace/data (#1623) 4fde300 unverified

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

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

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

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

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

don't compile deepspeed or bitsandbytes from source (#837) f544ab2 unverified

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

simplify by removing duplicate base_model_config (#772) 2d8def6 unverified

prepared dataset caching, other misc fixes (#665) e50a64e unverified

Fix Codellama examples (#582) 1aa4007 unverified

recommend padding when using sample packing (#531) 3437149 unverified

Feat(cfg): Add code-llama configs for all sizes (#479) 3513071 unverified