Daniel Han
|
d0c15bb508
|
Hotfix - fix DoRA, Gemma prompt template (#202) (#203)
* Update save.py
* saving
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update __init__.py
* Update save.py
* Update save.py
* Update save.py
* save
* trainer
* spaces
* original
* Gemma
* Update pyproject.toml
* Update mapper.py
* Update fast_lora.py
* FastGemmaModel
* model_type
* Update llama.py
* Update llama.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update llama.py
* Update llama.py
* Update fast_lora.py
* Update llama.py
* Update llama.py
* Update cross_entropy_loss.py
* Update llama.py
* Update llama.py
* gemma
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update fast_lora.py
* Update fast_lora.py
* Fast CE Loss
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* CE
* Update llama.py
* Update llama.py
* Update cross_entropy_loss.py
* Update geglu.py
* Update cross_entropy_loss.py
* revert
* Update llama.py
* Update llama.py
* norm
* Update gemma.py
* Update gemma.py
* position_ids
* Update gemma.py
* Update gemma.py
* pos
* Update llama.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update cross_entropy_loss.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update llama.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update llama.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* revert
* revert
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update llama.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update cross_entropy_loss.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* rope
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* llama
* Update llama.py
* gemma
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update save.py
* RoPE
* Update llama.py
* Update llama.py
* Update llama.py
* Update gemma.py
* correct_dtype
* Update gemma.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Chat Templates
* Update README.md
* Update README.md
* Update llama.py
* DoRA
* Update _utils.py
* Update chat_templates.py
|
2024-02-29 00:17:03 +11:00 |
|
Daniel Han-Chen
|
54b26c0466
|
Update llama.py
|
2024-02-29 00:16:19 +11:00 |
|
Daniel Han-Chen
|
074aa737ce
|
Merge branch 'main' into nightly
|
2024-02-29 00:14:42 +11:00 |
|
Daniel Han-Chen
|
b1892b5511
|
Update chat_templates.py
|
2024-02-29 00:09:00 +11:00 |
|
Daniel Han-Chen
|
072dc0c447
|
Update _utils.py
|
2024-02-29 00:02:40 +11:00 |
|
Daniel Han-Chen
|
d37f284eaa
|
DoRA
|
2024-02-28 23:59:49 +11:00 |
|
Daniel Han-Chen
|
967fed83c7
|
Update llama.py
|
2024-02-28 22:02:18 +11:00 |
|
Daniel Han
|
f946bed7b3
|
2.4x faster Gemma (#197)
* Update save.py
* Update save.py
* linking
* llama.cpp bugs
* Update save.py
* Update save.py
* saving
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update __init__.py
* Update save.py
* Update save.py
* Update save.py
* save
* trainer
* spaces
* original
* Gemma
* Update pyproject.toml
* Update mapper.py
* Update fast_lora.py
* FastGemmaModel
* model_type
* Update llama.py
* Update llama.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update llama.py
* Update llama.py
* Update fast_lora.py
* Update llama.py
* Update llama.py
* Update cross_entropy_loss.py
* Update llama.py
* Update llama.py
* gemma
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update fast_lora.py
* Update fast_lora.py
* Fast CE Loss
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* CE
* Update llama.py
* Update llama.py
* Update cross_entropy_loss.py
* Update geglu.py
* Update cross_entropy_loss.py
* revert
* Update llama.py
* Update llama.py
* norm
* Update gemma.py
* Update gemma.py
* position_ids
* Update gemma.py
* Update gemma.py
* pos
* Update llama.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update cross_entropy_loss.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update llama.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update llama.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* revert
* revert
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update llama.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update cross_entropy_loss.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* rope
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* llama
* Update llama.py
* gemma
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update save.py
* RoPE
* Update llama.py
* Update llama.py
* Update llama.py
* Update gemma.py
* correct_dtype
* Update gemma.py
* Update cross_entropy_loss.py
* Update cross_entropy_loss.py
* Chat Templates
* Update README.md
* Update README.md
|
2024-02-27 01:42:10 +11:00 |
|
Daniel Han-Chen
|
a4cd4a6e41
|
Update README.md
|
2024-02-27 01:40:45 +11:00 |
|
Daniel Han-Chen
|
90a5c2c121
|
Update README.md
|
2024-02-27 01:39:52 +11:00 |
|
Daniel Han-Chen
|
4b7df80abd
|
Chat Templates
|
2024-02-27 00:16:57 +11:00 |
|
Daniel Han-Chen
|
54ff6eb169
|
Update cross_entropy_loss.py
|
2024-02-26 17:27:42 +11:00 |
|
Daniel Han-Chen
|
7cf69dd9f2
|
Update cross_entropy_loss.py
|
2024-02-26 16:19:39 +11:00 |
|
Daniel Han-Chen
|
1f450cd6ee
|
Update gemma.py
|
2024-02-26 14:44:22 +11:00 |
|
Daniel Han-Chen
|
7a5db6758c
|
correct_dtype
|
2024-02-26 14:39:43 +11:00 |
|
Daniel Han-Chen
|
cf16811ab9
|
Update gemma.py
|
2024-02-26 14:38:27 +11:00 |
|
Daniel Han-Chen
|
637d01643c
|
Update llama.py
|
2024-02-26 14:37:48 +11:00 |
|
Daniel Han-Chen
|
3d73560df3
|
Update llama.py
|
2024-02-26 14:37:09 +11:00 |
|
Daniel Han-Chen
|
0d24acf0f5
|
Update llama.py
|
2024-02-26 14:36:39 +11:00 |
|
Daniel Han-Chen
|
1aeca6f00c
|
RoPE
|
2024-02-26 14:35:44 +11:00 |
|
Daniel Han-Chen
|
4ec1b216e0
|
Update save.py
|
2024-02-26 14:15:37 +11:00 |
|
Daniel Han-Chen
|
11c9ea4d1b
|
Update gemma.py
|
2024-02-26 05:06:04 +11:00 |
|
Daniel Han-Chen
|
24e9d0af28
|
Update gemma.py
|
2024-02-26 05:05:41 +11:00 |
|
Daniel Han-Chen
|
0b693df646
|
Update gemma.py
|
2024-02-26 04:37:12 +11:00 |
|
Daniel Han-Chen
|
ae336e9663
|
Update gemma.py
|
2024-02-26 04:36:10 +11:00 |
|
Daniel Han-Chen
|
1d53b366a0
|
Update gemma.py
|
2024-02-26 04:32:49 +11:00 |
|
Daniel Han-Chen
|
b1864710c5
|
Update gemma.py
|
2024-02-26 04:30:29 +11:00 |
|
Daniel Han-Chen
|
686d9fa4c4
|
Update gemma.py
|
2024-02-26 04:27:55 +11:00 |
|
Daniel Han-Chen
|
40169f9fd3
|
Update gemma.py
|
2024-02-26 04:23:38 +11:00 |
|
Daniel Han-Chen
|
b0b38f770b
|
Update gemma.py
|
2024-02-26 04:20:19 +11:00 |
|
Daniel Han-Chen
|
13e06a062b
|
Update gemma.py
|
2024-02-26 03:56:34 +11:00 |
|
Daniel Han-Chen
|
fd5389a485
|
Update cross_entropy_loss.py
|
2024-02-26 03:55:15 +11:00 |
|
Daniel Han-Chen
|
a5abe39ded
|
Update cross_entropy_loss.py
|
2024-02-26 03:53:49 +11:00 |
|
Daniel Han-Chen
|
78c96ef83c
|
Update cross_entropy_loss.py
|
2024-02-26 03:50:34 +11:00 |
|
Daniel Han-Chen
|
88cfe5eeb2
|
Update cross_entropy_loss.py
|
2024-02-26 03:48:16 +11:00 |
|
Daniel Han-Chen
|
dba4c0355d
|
Update cross_entropy_loss.py
|
2024-02-26 03:46:18 +11:00 |
|
Daniel Han-Chen
|
199460d5ef
|
Update cross_entropy_loss.py
|
2024-02-26 03:43:22 +11:00 |
|
Daniel Han-Chen
|
13718b9847
|
Update cross_entropy_loss.py
|
2024-02-26 03:36:38 +11:00 |
|
Daniel Han-Chen
|
48736a0755
|
Update cross_entropy_loss.py
|
2024-02-26 03:35:45 +11:00 |
|
Daniel Han-Chen
|
c1dbf6710e
|
Update cross_entropy_loss.py
|
2024-02-26 03:29:19 +11:00 |
|
Daniel Han-Chen
|
b55d7ad4b2
|
Update cross_entropy_loss.py
|
2024-02-26 03:29:11 +11:00 |
|
Daniel Han-Chen
|
bc3ff0f3a6
|
Update cross_entropy_loss.py
|
2024-02-26 03:28:22 +11:00 |
|
Daniel Han-Chen
|
7bbce701c8
|
Update cross_entropy_loss.py
|
2024-02-26 03:26:42 +11:00 |
|
Daniel Han-Chen
|
9c0b3cd431
|
Update cross_entropy_loss.py
|
2024-02-26 03:19:26 +11:00 |
|
Daniel Han-Chen
|
e696487e84
|
Update cross_entropy_loss.py
|
2024-02-26 03:18:01 +11:00 |
|
Daniel Han-Chen
|
c675220373
|
Update cross_entropy_loss.py
|
2024-02-26 03:16:31 +11:00 |
|
Daniel Han-Chen
|
bb6b6f238e
|
Update cross_entropy_loss.py
|
2024-02-26 03:15:19 +11:00 |
|
Daniel Han-Chen
|
096544eff4
|
Update cross_entropy_loss.py
|
2024-02-26 03:14:04 +11:00 |
|
Daniel Han-Chen
|
b5eff3bfbc
|
Update cross_entropy_loss.py
|
2024-02-26 03:12:23 +11:00 |
|
Daniel Han-Chen
|
fdaa9493be
|
Update cross_entropy_loss.py
|
2024-02-26 03:09:37 +11:00 |
|