qwerrwe / README.md

Commit History

Attention mask and position id fixes for packing (#285)
2bb0b78
unverified

winglian commited on

Add wandb_entity to wandb options, update example configs, update README (#361)
7019509
unverified

Morgan McGuire Morgan McGuire winglian commited on

Feat: Add rope scaling (#343)
b521206
unverified

Nanobit commited on

Update README.md on pretraining_dataset (#360)
fae6ed8
unverified

Nanobit commited on

Clarify pre-tokenize before multigpu (#359)
94d03c8
unverified

Nanobit commited on

note pattern when using groups
b4d1d22

tmm1 commited on

update comment for group_by_length
9f99104

tmm1 commited on

python 3.10 and 3.11 both work fine, as does pytorch 2.1.0.dev
58d6659

tmm1 commited on

there is no configs folder
cc7e800

tmm1 commited on

update README for updated docker images (#328)
41a4d15
unverified

winglian commited on

Merge pull request #306 from ethanhs/xgen
dcdec44
unverified

winglian commited on

don't resize embeddings to multiples of 32x by default
1066751

winglian commited on

Add XGen info to README and example config
3881143

ethanhs commited on

Fix(readme): Improve wording for push model
165907f
unverified

Nanobit commited on

fix(readme): remove accelerate config
b64f411
unverified

Nanobit commited on

Merge pull request #279 from NanoCode012/feat/multi-gpu-readme
469c08c
unverified

winglian commited on

Add dataset name to all yaml options in README
3cdd8e4

chargoddard commited on

Feat(readme): improve docs on multi-gpu
cf5ae6b

Nanobit commited on

Fix formatting mistake
46032a1

chargoddard commited on

Add example of dataset with configuration name to README
8bba642

chargoddard commited on

Merge pull request #275 from NanoCode012/feat/safetensors
231031a
unverified

Nanobit commited on

Feat: Add save_safetensors
5491278

Nanobit commited on

Feat(docs): Add model_revision arg
896c1ae
unverified

Nanobit commited on

Fix for linter
41da98b
unverified

Nanobit commited on

Fix local path loading and custom strategy type
9e64f42
unverified

Nanobit commited on

Fix future deprecation push_to_hub_model_id
e79c8e6

Nanobit commited on

open orca support
78a1e1f

winglian commited on

Update README.md
c146880
unverified

Nanobit commited on

optionally define whether to use_fast tokenizer
47d601f

winglian commited on

add docs
c969f0a

winglian commited on

hint to what AMP means
d7635b7

winglian commited on

add float16 docs and tweak typehints
88e17ff

winglian commited on

Merge pull request #92 from OpenAccess-AI-Collective/flash-optimum
16bb627
unverified

winglian commited on

Fix sharegpt type
3513885
unverified

Nanobit commited on

Update README.md to include a community showcase
5ff547d
unverified

PocketDoc commited on

Merge branch 'main' into flash-optimum
fd2c981
unverified

winglian commited on

Merge pull request #192 from OpenAccess-AI-Collective/sharegpt-custom-prompt
74ef5cc
unverified

winglian commited on

Fix config path after config moved
52cde69

Nanobit commited on

add new sharegpt, refactor prompt so it can be customized later, add exception if no data is processed
aac4b76

winglian commited on

Add save_steps and eval_steps to Readme
4cd1dee
unverified

Nanobit commited on

gptq lora llama is obviously good
336aa3f

winglian commited on

update openllama and clean up paths
d0d7eaa

winglian commited on

fix table formatting
a6ebf57

winglian commited on

more matrix updates
280832c

winglian commited on

update the support matrix
a43bae9

winglian commited on

pass a prompt in from stdin for inference
c4e4f81

winglian commited on

add streaming dataset support for pretraining datasets
eea2731

winglian commited on

add option to readme
5878bb1

winglian commited on

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

PocketDoc commited on