 Alex Cheema
|
2065c7751a
orb
|
1 年之前 |
|
Alex Cheema
|
cf4cddccc1
port github workflow to circleci
|
1 年之前 |
 Alex Cheema
|
21b0bf8777
Update config.yml
|
1 年之前 |
|
Alex Cheema
|
997fcaff35
CircleCI Commit
|
1 年之前 |
|
Alex Cheema
|
f5755ea198
give explicit node ids when running on the same instance in tests, otherewise they use the same one because of sticky node ids
|
1 年之前 |
|
Alex Cheema
|
4faa6c06f4
add support for selective model downloading. related: #16
|
1 年之前 |
|
Alex Cheema
|
be3a09c28b
rm logs
|
1 年之前 |
|
Alex Cheema
|
0bfb8e3b6d
sticky node ids #16
|
1 年之前 |
|
Alex Cheema
|
980d5d2c5b
bring back TINYGRAD_DEBUG. not sure why it was removed
|
1 年之前 |
|
Alex Cheema
|
76766253cd
fix regression introduced by image_str for tinygrad
|
1 年之前 |
|
Alex Cheema
|
1d54f10514
pass on tinygrad set_on_download_progress
|
1 年之前 |
|
Alex Cheema
|
d6a7e46324
async model downloading with download progress. fixes #102. related: #16 #104
|
1 年之前 |
|
Alex Cheema
|
5c67e24c35
smart prompt longest prefix matching to avoid sending the same text through the NN again. speeds up prefill significantly
|
1 年之前 |
|
Alex Cheema
|
94ac9463a7
fix model id for llama 3.1 405b now its finally on the hub
|
1 年之前 |
|
Alex Cheema
|
178fb75c84
fix image api prompt encoding
|
1 年之前 |
|
Alex Cheema
|
2d20000964
use AutoProcessor with use_fast=False since there's a bug with use_fast=True where whitespace is removed on single token decodes
|
1 年之前 |
|
Alex Cheema
|
0ec77e1a99
Merge pull request #88 from varshith15/main
|
1 年之前 |
|
Alex Cheema
|
af1c7ce327
add support for image upload to tinychat for vision models
|
1 年之前 |
|
Alex Cheema
|
0d45a855fb
increase max request size to send raw images, make image download from url async, use chatgpt-compatible convention for images
|
1 年之前 |
|
Alex Cheema
|
e68d06f4ef
move model-selector styles to index.css
|
1 年之前 |
|
Alex Cheema
|
78db451d7e
add pillow to main dependencies
|
1 年之前 |
|
Alex Cheema
|
824f05263f
Merge branch 'main' into HEAD
|
1 年之前 |
|
Alex Cheema
|
142682645f
bump up tinygrad version
|
1 年之前 |
 Varshith
|
8d3d3df1dd
update readme
|
1 年之前 |
|
Varshith
|
acc94b50c7
chatgpt api integration
|
1 年之前 |
|
Alex Cheema
|
33cbacf513
fix llava sanitize
|
1 年之前 |
|
Alex Cheema
|
2fb961fccd
stick to same convention as new llama
|
1 年之前 |
|
Alex Cheema
|
b44b917151
add pillow as testing dependency
|
1 年之前 |
|
Alex Cheema
|
2aa1e24ea9
remove unused torch import
|
1 年之前 |
|
Alex Cheema
|
833e7f3396
rename sharded_llava -> llava to match new convention
|
1 年之前 |
