Commit Graph

76 Commits

Author SHA1 Message Date
Kohaku-Blueleaf
0af44f0262
Add option for output dir (#84) 2023-03-19 22:01:24 -07:00
Kohaku-Blueleaf
450206caaf
Fix torch.compile call on windows (#81)
* Windows not support compile

* Fix code style
2023-03-19 20:16:02 -07:00
Karun
81eb72f707
cleans up alphabetical prompts (#76) 2023-03-19 15:55:02 -07:00
Eric Wang
997f6cd81f slider for tokens generated 2023-03-19 15:53:21 -07:00
Eric Wang
cfad895aa1 mask prompt in loss 2023-03-19 15:53:21 -07:00
Eric J. Wang
d66908c0ca
Remove messy test code 2023-03-19 11:22:02 -07:00
Yaqub Mahmoud
0e752ea5f3
Update requirements.txt (#67)
Added appdirs package to requirements.txt
2023-03-19 11:15:07 -07:00
Eric Wang
c83e30ab78 generate.py tweaks 2023-03-18 23:00:18 -07:00
Eric Wang
80fd9833db don't share publicly 2023-03-18 16:43:53 -07:00
Eric Wang
6ced8d9907 fix HF export script 2023-03-18 16:42:58 -07:00
Eric J. Wang
8dc0f614c6
Update README.md 2023-03-18 13:24:42 -07:00
Eric J. Wang
d9c19ff34e
Update README.md 2023-03-17 22:27:58 -07:00
Kakigōri Maker
9dab7ba438
add multi-gpu support (ddp) (#54)
* add multi-gpu support (ddp)

* Update finetune.py
2023-03-17 22:27:33 -07:00
Eric Wang
a0295813b0 normalize cleaned data row with missing output 2023-03-17 20:52:14 -07:00
Eric Wang
3b160d745b HF export script 2023-03-17 17:56:10 -07:00
Eric Wang
8aecde83cd construciton 2023-03-17 15:11:35 -07:00
Eric Wang
cb046d647e min beams = 1 2023-03-17 15:07:08 -07:00
Eric Wang
f7044049ab dataset cleaning, visualizations 2023-03-17 15:04:25 -07:00
Peter Marelas
db4af6a7ff
Enable inference on CPU and Mac GPU using pytorch support for MPS (#48) 2023-03-17 13:53:21 -07:00
Eric J. Wang
9bff21cc68
huggingface -> Hugging Face
Update README.md
2023-03-17 11:08:01 -07:00
Ikko Eltociear Ashimine
65299df970
Update README.md
huggingface -> Hugging Face
2023-03-17 16:34:56 +09:00
Eric J. Wang
daf13eea40
Add notes about dataset and model updates 2023-03-16 21:17:55 -07:00
Eric J. Wang
d60701b895
Merge pull request #35 from T-Atlas/patch-1
Update generate.py
2023-03-16 19:39:43 -07:00
Lian Junhong
3a47bd18e8
Update generate.py
Adapting to the input function, a text box for inputting content has been added.
2023-03-17 10:30:27 +08:00
Eric Wang
c39da83e2b add Gradio interface to generate.py 2023-03-16 16:04:06 -07:00
Eric Wang
35029da078 Validation set 2023-03-16 15:05:17 -07:00
Eric Wang
5f6614e6fc Catch outdated installs 2023-03-16 12:11:47 -07:00
Eric Wang
6adce2f6c5 Fix req.txt specification to install from github 2023-03-16 12:11:47 -07:00
Eric Wang
060e7f4a50 README and requirements.txt updates 2023-03-16 12:11:46 -07:00
andreas.echavez
1862976b33 Update alpaca-lora to use transformers main branch 2023-03-16 12:11:29 -07:00
Eric Wang
c3d94707ec Expand sampling in generate.py for new test 2023-03-16 09:59:10 -07:00
Eric Wang
9c1933721d Update README to reflect new weights 2023-03-16 09:59:10 -07:00
Eric J. Wang
6681523bbe
Merge pull request #19 from antimatter15/patch-1
Fix LoRa weight merging in export

It can't hurt
2023-03-16 01:42:48 -07:00
Kevin Kwok
dde89950f3
Fix LoRa weight merging 2023-03-16 00:50:24 -07:00
Eric Wang
b8c32be806 Add counting test 2023-03-16 00:05:32 -07:00
Eric J. Wang
88bfa8f8b0
Add Windows install instructions
Resolves #17
2023-03-16 00:01:01 -07:00
Eric Wang
2fa1c66388 repair tokenization logic, again 2023-03-15 23:58:44 -07:00
Eric Wang
024dde7dab Revert "fix <eos> tokenization"
This reverts commit 6b69ea8665.
2023-03-15 22:52:54 -07:00
Eric Wang
6b69ea8665 fix <eos> tokenization 2023-03-15 18:21:06 -07:00
Eric Wang
6f218218f4 Add checkpoint export to README 2023-03-15 17:24:59 -07:00
Eric Wang
d68ff15ceb generate.py memory, perf updates 2023-03-15 17:22:22 -07:00
Eric Wang
056b81177a Add script for converting weights from HF 2023-03-15 17:17:32 -07:00
Eric Wang
07f5b68e0f torch.no_grad 2023-03-15 11:11:26 -07:00
Eric Wang
956dea5d28 update length notebook 2023-03-15 11:11:01 -07:00
Eric Wang
a2607faff0 fix finetuning code :( 2023-03-14 21:45:12 -07:00
Eric Wang
6149706680 add text-davinci-003 to comparisons 2023-03-14 21:41:02 -07:00
Eric Wang
d714a73e8c Update README.md with new checkpoint details 2023-03-14 21:33:12 -07:00
Eric J. Wang
6a8b163f3e
Link to HuggingFace Hub 2023-03-14 20:53:03 -07:00
Eric J. Wang
19af668cb4
Add CoLab demo 2023-03-14 20:47:10 -07:00
Eric Wang
ec98533876 Update README.md; clean up hyperparameters 2023-03-14 16:30:38 -07:00