Commit graph

368 commits

Author SHA1 Message Date
Daniel Han
4e570be9ae
Fix RoPE extension (#846)
* bugs

* Update _utils.py

* flash-attn softcapping

* Update gemma2.py

* Update gemma2.py

* Update gemma2.py

* Update gemma2.py

* Update mapper.py

* Update README.md

* Update _utils.py

* Fix ROPE extension issue and device mismatch (#840)

* When an exception has been assigned using as target, it is cleared at the end of the except clause.(https://docs.python.org/3/reference/compound_stmts.html#the-try-statement)

* Update loader.py

* round up to extend rope size

* inv_freq.device changed, make sure they are on the same device

---------

Co-authored-by: xiaoyang <xiaoyang@youzan.com>
Co-authored-by: Daniel Han <danielhanchen@gmail.com>

* Update gemma.py

---------

Co-authored-by: XiaoYang <xyangk@gmail.com>
Co-authored-by: xiaoyang <xiaoyang@youzan.com>
2024-07-31 12:10:33 -07:00
Daniel Han
dfca5516e7 Update README.md 2024-07-31 09:50:11 -07:00
Daniel Han
b85670de83
Gemma (#843)
* bugs

* Update _utils.py

* flash-attn softcapping

* Update gemma2.py

* Update gemma2.py

* Update gemma2.py

* Update gemma2.py

* Update mapper.py

* Update README.md

* Update _utils.py
2024-07-31 08:54:58 -07:00
Daniel Han
4285d1b479 Update llama.py 2024-07-30 10:29:54 -07:00
Daniel Han
be0930d1f6 Update loader.py 2024-07-30 10:18:51 -07:00
XiaoYang
18900721c2
fix UnboundLocalError (#834)
* When an exception has been assigned using as target, it is cleared at the end of the except clause.(https://docs.python.org/3/reference/compound_stmts.html#the-try-statement)

* Update loader.py

---------

Co-authored-by: xiaoyang <xiaoyang@youzan.com>
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
2024-07-30 10:15:09 -07:00
Daniel Han
6f0c9d6936 Merge branch 'main' into nightly 2024-07-30 10:01:11 -07:00
Daniel Han
a7bfbe7927
Better debugging (#826)
* Update __init__.py

* Edits

* Checks

* Update _utils.py

* Update _utils.py

* Update loader.py

* Update _utils.py

* Update mapper.py

* Update loader.py

* Update loader.py

* Update _utils.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update mapper.py

* Update loader.py
2024-07-28 00:10:02 -07:00
Daniel Han
ea0a49448d Update loader.py 2024-07-27 23:04:23 -07:00
Daniel Han
858e1a2a8c Update mapper.py 2024-07-27 23:03:29 -07:00
Daniel Han
e1d61ce5d9 Update loader.py 2024-07-27 23:03:13 -07:00
Daniel Han
ed8bc007c6 Update loader.py 2024-07-27 23:02:10 -07:00
Daniel Han
b6ef709630 Update loader.py 2024-07-27 23:00:47 -07:00
Daniel Han
ddc2dde97c Update loader.py 2024-07-27 22:59:47 -07:00
Daniel Han
9d5195296f Update loader.py 2024-07-27 22:59:16 -07:00
Daniel Han
c03fd228a2 Update loader.py 2024-07-27 22:58:15 -07:00
Daniel Han
4a8c9e8824 Update _utils.py 2024-07-27 22:56:59 -07:00
Daniel Han
38b5c77635 Update loader.py 2024-07-27 22:54:49 -07:00
Daniel Han
a8e7556fc6 Update loader.py 2024-07-27 22:52:06 -07:00
Daniel Han
1f67056738 Update mapper.py 2024-07-27 22:50:38 -07:00
Daniel Han
b310f5e06a Update _utils.py 2024-07-27 22:48:52 -07:00
Daniel Han
aab503ac80 Update loader.py 2024-07-27 22:35:24 -07:00
Daniel Han
4ea5789db6 Update _utils.py 2024-07-27 22:32:39 -07:00
Daniel Han
78fa9d058d Update _utils.py 2024-07-27 22:30:48 -07:00
Daniel Han
f6c2b4aa7d Checks 2024-07-27 22:16:33 -07:00
Daniel Han
08379f8a9c Edits 2024-07-27 20:30:32 -07:00
Daniel Han
01c35f9e17 Update __init__.py 2024-07-26 16:31:40 -07:00
Daniel Han
fd753fed99 Update llama.py 2024-07-25 08:53:21 -07:00
Daniel Han
8e5054bbea Update _utils.py 2024-07-25 00:33:38 -07:00
Daniel Han
9e1ad7c319 Update _utils.py 2024-07-25 00:29:12 -07:00
Daniel Han
7fccd21d9f Update loader.py 2024-07-25 00:28:20 -07:00
Daniel Han
66e0453ea8 Update llama.py 2024-07-25 00:19:32 -07:00
Daniel Han
08d3ef4bb3 Fix PEFT 2024-07-25 00:17:19 -07:00
Daniel Han
6e30a7a006 Patch PEFT 2024-07-24 23:45:39 -07:00
Daniel Han
bd180c1357 Mistral 2024-07-24 14:05:31 -07:00
Daniel Han
ddd4e86cec Merge branch 'main' into nightly 2024-07-24 12:37:12 -07:00
Daniel Han
a96d16e44b Update README.md 2024-07-23 15:08:09 -07:00
Daniel Han
d1f3b6c1c4 Create Run.png 2024-07-23 13:14:21 -07:00
Daniel Han
cc11b78861 Update llama.py 2024-07-23 12:28:12 -07:00
Daniel Han
4dd4ad2104 Update llama.py 2024-07-23 12:27:46 -07:00
Daniel Han
caa4028287 Update _utils.py 2024-07-23 12:25:24 -07:00
Daniel Han
777453967f Update loader.py 2024-07-23 12:12:29 -07:00
Daniel Han
824511e265 Update README.md 2024-07-23 12:07:27 -07:00
Daniel Han
22968a2134 Update README.md 2024-07-23 11:51:08 -07:00
Daniel Han
c86b13d465
Llama 3.1 (#797)
* Llama 3.1

* Update _utils.py

* Llama 3.1

* Update _utils.py

* Update llama.py

* Update llama.py

* hack for rotary

* patch RoPE

* refix rope

* Update _utils.py

* Update llama.py

* Llama 3.1 check

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py
2024-07-23 11:40:49 -07:00
Daniel Han
b93a75778e Update llama.py 2024-07-23 11:24:58 -07:00
Daniel Han
ca3a1b7315 Update llama.py 2024-07-23 11:23:18 -07:00
Daniel Han
4a3fddd055 Update llama.py 2024-07-23 11:23:00 -07:00
Daniel Han
5d9245660f Update llama.py 2024-07-23 11:22:27 -07:00
Daniel Han
7c441f3480 Update llama.py 2024-07-23 11:21:29 -07:00