Commit graph

88 commits

Author SHA1 Message Date
Daniel Han-Chen
c79d2c31cd DPO 2023-12-31 18:26:17 +11:00
Daniel Han-Chen
0a3477993a DPO 2023-12-31 17:57:45 +11:00
Daniel Han-Chen
74826077da Fix Kaggle issues 2023-12-31 01:20:04 +11:00
Daniel Han
ad02ea81b7
Prelim Qwen, Deepseek support (#58)
* Pytorch 2.1.1 install path, 4bit loading

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Spelling errors

* Update __init__.py

* DPO loss fix

* Update fast_lora.py

* Update fast_lora.py

* Out of bounds tokenization

* Fix Mistral SWA

* Prelim support Qwen, Deepseek etc
2023-12-30 04:35:35 +11:00
Daniel Han
24133feda6
DPO, SWA fixes (#57)
* Pytorch 2.1.1 install path, 4bit loading

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Spelling errors

* Update __init__.py

* DPO loss fix

* Update fast_lora.py

* Update fast_lora.py

* Out of bounds tokenization

* Fix Mistral SWA
2023-12-29 04:55:01 +11:00
Daniel Han
0369e7aa7a
Nightly (#56)
* Pytorch 2.1.1 install path, 4bit loading

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Spelling errors

* Update __init__.py
2023-12-28 04:19:12 +11:00
Daniel Han-Chen
a3ed0dc4f4 Fix inference 2023-12-27 03:51:31 +11:00
Daniel Han-Chen
1128ecb82a Fix FastLanguageModel 2023-12-27 03:01:45 +11:00
Daniel Han
51dd120e35
Fix RoPE Scaling issues (#52)
* Fix RoPE Scaling

* Update llama.py

* Update llama.py
2023-12-26 04:32:04 +11:00
Daniel Han-Chen
627acc4bb3 Fix Pytorch 2.1.1 2023-12-25 23:28:05 +11:00
Daniel Han
de855c2afa
Small fixes (#48)
* Fix generation for GQA

* Update _utils.py

* flash attn

* Update _utils.py

* Update llama.py

* Update mistral.py

* platform

* Update _utils.py

* Update llama.py

* Logo changed

* Update README.md

* Update README.md
2023-12-23 04:22:48 +11:00
Daniel Han
725e581539 Fix typo 2023-12-18 12:27:31 +11:00
shimmy
275483f7de Update __init__.py
Fixing typo extra '='
2023-12-18 12:19:24 +11:00
Daniel Han-Chen
b0f5ef5526 Torch version, docs, readme, general loader 2023-12-18 04:23:16 +11:00
Daniel Han-Chen
f380cc1170 Fix Mistral
BlockDiagonalCausalMask fix courtesy of https://github.com/Rypo
2023-12-16 13:14:33 +11:00
Daniel Han-Chen
399f8ed56f Update Colab to CUDA 12.1 2023-12-15 16:35:24 +11:00
Daniel Han-Chen
c931ec40c6 Fix packaging, readme 2023-12-15 12:57:08 +11:00
Daniel Han
27bbd6b2cd Update README.md 2023-12-14 15:10:17 +11:00
Daniel Han
50f55b2a38 Update README.md 2023-12-14 12:33:51 +11:00
Daniel Han-Chen
badf6a4980 Update llama.py 2023-12-12 13:07:38 +11:00
Daniel Han-Chen
82dcf52980 Update llama.py 2023-12-12 02:54:54 +11:00
Daniel Han-Chen
2d5d884874 tokenizer pad fix 2023-12-12 02:40:37 +11:00
Daniel Han-Chen
28f3b971d2 Update mistral.py 2023-12-12 00:59:30 +11:00
Daniel Han-Chen
e699f1d09e Update llama.py 2023-12-12 00:57:06 +11:00
Daniel Han-Chen
08787b7021 Mistral, GQA support 2023-12-11 23:58:36 +11:00
Daniel Han-Chen
54ca9035b8 Fix generation 2023-12-07 00:13:29 +11:00
Daniel Han
4b97a810b5
Pre-release 2023 December version (Mistral, Prelim DPO, WSL, bug fixes) (#16)
* Immediate bug fixes

* Update README.md

* Update README.md

* Update llama.py

* Update llama.py

* Rope Scaling and max_seq_len will change

* Update llama.py

* new images

* Update README.md

* Images

* Update README.md

* Update pyproject.toml

* GQA

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py
2023-12-06 02:59:22 +11:00
Daniel Han-Chen
3aa16bb452 Sticker 2023-12-02 03:08:16 +11:00
Daniel Han
8dae2ee050
Update README.md 2023-12-01 21:54:31 +11:00
Daniel Han
0718910789
Update README.md 2023-12-01 19:54:04 +11:00
Daniel Han
c2197c2210
Update README.md 2023-12-01 17:50:40 +11:00
Daniel Han
28cc035fba
Update README.md 2023-12-01 16:07:53 +11:00
Daniel Han
0edd953258
Update README.md 2023-12-01 16:07:38 +11:00
Daniel Han-Chen
4fcb929a9f Create Discord.png 2023-12-01 16:04:15 +11:00
Daniel Han
afa8ee77ac
Update README.md 2023-12-01 14:42:52 +11:00
Daniel Han
4e519995d0
Update README.md 2023-12-01 14:42:42 +11:00
Daniel Han
d9743a3089
Update README.md 2023-12-01 14:38:03 +11:00
Daniel Han
b69c8989f3
Update README.md 2023-12-01 14:35:51 +11:00
Daniel Han
17172ab180
Update README.md 2023-12-01 14:11:49 +11:00
Daniel Han
b2df01eb08
Update README.md 2023-12-01 13:57:28 +11:00
Daniel Han
fc58d3f5bd
Update README.md 2023-12-01 13:52:05 +11:00
Daniel Han-Chen
04c5c07ea0 Merge branch 'main' of https://github.com/unslothai/unsloth 2023-12-01 13:51:33 +11:00
Daniel Han-Chen
a31fb33bc9 Create Slim Orca 2GPUs.png 2023-12-01 13:51:05 +11:00
Daniel Han
c5ec42291b
Update README.md 2023-12-01 13:50:13 +11:00
Daniel Han
f383e5dbd7
Update README.md 2023-12-01 13:49:53 +11:00
Daniel Han
ee641a0754
Update README.md 2023-12-01 13:43:26 +11:00
Daniel Han
ef43dc3f4e
Update README.md 2023-12-01 13:40:52 +11:00
Daniel Han
0d1a04511e
Update README.md 2023-12-01 13:40:39 +11:00
Daniel Han
ff86769c3e
Update README.md 2023-12-01 13:37:27 +11:00
Daniel Han
81089a0d25
Update README.md 2023-12-01 03:29:31 +11:00