| .. |
|
base.yaml
|
[Loss] Use flash_attn.losses.cross_entropy.CrossEntropyLoss
|
2022-12-31 22:43:28 -08:00 |
|
gpt3-2.7B-flash-8k.yaml
|
Update configs, add results
|
2022-11-29 04:46:43 -08:00 |
|
gpt3-2.7B-flash-hdim128-rotary-8k.yaml
|
Fix typo in config: train.gpu -> train.gpu_mem
|
2022-12-21 13:42:30 -08:00 |
|
gpt3-2.7B-flash-hdim128-rotary.yaml
|
Fix typo in config: train.gpu -> train.gpu_mem
|
2022-12-21 13:42:30 -08:00 |
|
gpt3-2.7B-flash-hdim128.yaml
|
Update configs, add results
|
2022-11-29 04:46:43 -08:00 |
|
gpt3-2.7B-flash-rotary-8k.yaml
|
Fix typo in config: train.gpu -> train.gpu_mem
|
2022-12-21 13:42:30 -08:00 |
|
gpt3-2.7B-flash-rotary.yaml
|
Fix typo in config: train.gpu -> train.gpu_mem
|
2022-12-21 13:42:30 -08:00 |
|
gpt3-2.7B-flash.yaml
|
Update configs, add results
|
2022-11-29 04:46:43 -08:00 |
|
gpt3-2.7B-hf-hdim128.yaml
|
Update configs, add results
|
2022-11-29 04:46:43 -08:00 |
|
gpt3-2.7B-hf.yaml
|
Update configs, add results
|
2022-11-29 04:46:43 -08:00 |
|
gpt3l-flash-8k.yaml
|
Release training code
|
2022-11-28 17:34:40 -08:00 |
|
gpt3l-flash-rotary-8k.yaml
|
Release training code
|
2022-11-28 17:34:40 -08:00 |
|
gpt3l-flash-rotary-30B.yaml
|
Release training code
|
2022-11-28 17:34:40 -08:00 |
|
gpt3l-flash-rotary.yaml
|
Release training code
|
2022-11-28 17:34:40 -08:00 |
|
gpt3l-flash.yaml
|
Release training code
|
2022-11-28 17:34:40 -08:00 |
|
gpt3l-hf.yaml
|
Update configs, add results
|
2022-11-29 04:46:43 -08:00 |
|
gpt3m-flash-8k.yaml
|
Release training code
|
2022-11-28 17:34:40 -08:00 |
|
gpt3m-flash-rotary-8k.yaml
|
Release training code
|
2022-11-28 17:34:40 -08:00 |
|
gpt3m-flash-rotary-30B.yaml
|
Release training code
|
2022-11-28 17:34:40 -08:00 |
|
gpt3m-flash-rotary.yaml
|
Release training code
|
2022-11-28 17:34:40 -08:00 |
|
gpt3m-flash.yaml
|
Update configs, add results
|
2022-11-29 04:46:43 -08:00 |
|
gpt3m-hf.yaml
|
Update configs, add results
|
2022-11-29 04:46:43 -08:00 |
|
gpt3s-flash-8k.yaml
|
Release training code
|
2022-11-28 17:34:40 -08:00 |
|
gpt3s-flash-rotary-8k.yaml
|
Release training code
|
2022-11-28 17:34:40 -08:00 |
|
gpt3s-flash-rotary-30B.yaml
|
Release training code
|
2022-11-28 17:34:40 -08:00 |
|
gpt3s-flash-rotary.yaml
|
Release training code
|
2022-11-28 17:34:40 -08:00 |
|
gpt3s-flash.yaml
|
[FusedDense] Support relu, rename FusedDenseGeluDense -> FusedMLP
|
2023-01-17 18:12:27 -08:00 |
|
gpt3s-hf.yaml
|
Update configs, add results
|
2022-11-29 04:46:43 -08:00 |
|
gpt3xl-flash-8k.yaml
|
Update configs, add results
|
2022-11-29 04:46:43 -08:00 |
|
gpt3xl-flash-rotary-8k.yaml
|
Update configs, add results
|
2022-11-29 04:46:43 -08:00 |
|
gpt3xl-flash-rotary-60B.yaml
|
Update configs, add results
|
2022-11-29 04:46:43 -08:00 |
|
gpt3xl-flash-rotary.yaml
|
Update configs, add results
|
2022-11-29 04:46:43 -08:00 |
|
gpt3xl-flash.yaml
|
Update configs, add results
|
2022-11-29 04:46:43 -08:00 |
|
gpt3xl-hf.yaml
|
Update configs, add results
|
2022-11-29 04:46:43 -08:00 |