Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
GF-John
/
video-caption
like
0
Running
on
Zero
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
video-caption
/
app.py
Commit History
try to load gemma again
5a0f6f1
John Ho
commited on
Jul 28
testing fps for internvl3 processor
3feaae8
John Ho
commited on
Jul 28
added do_sample to generate
9137c51
John Ho
commited on
Jul 28
make sure temperature is float
a792463
John Ho
commited on
Jul 28
skipping the use of gemma model for now
96a7d4d
John Ho
commited on
Jul 28
added temp and testing gemma
035a7ef
John Ho
commited on
Jul 28
updated case matching
e13ff04
John Ho
commited on
Jul 28
testing model quantization
6ec3c10
John Ho
commited on
Jul 28
skip loading of internvl3 8b model
25dfae5
John Ho
commited on
Jul 28
adding more internvl3 models
b89bc96
John Ho
commited on
Jul 28
debugging internvl3
d9bd1e8
John Ho
commited on
Jul 28
debugging internvl3
3eaf3ec
John Ho
commited on
Jul 28
debugging internvl3
4dc5aed
John Ho
commited on
Jul 28
added different inference code for internvl3
d673ad7
John Ho
commited on
Jul 28
added intern video model
15ef0c9
John Ho
commited on
Jul 28
added control for fps and max tokens
ff0b093
John Ho
commited on
Jul 28
updated app to load multiple models
4361fd1
John Ho
commited on
Jul 28
try quantization again
4e1e198
John Ho
commited on
Jul 24
trying to load model and processors outside space decorator
a83f12f
John Ho
commited on
Jul 24
trying model quantization
a7fd61f
John Ho
commited on
Jul 24
trying model quantization
d9d1598
John Ho
commited on
Jul 24
fixing issue with device map for the inputs
c7e712e
John Ho
commited on
Jul 24
added low_cpu_mem_usage and move input to device also
c697b34
John Ho
commited on
Jul 24
added low_cpu_mem_usage and move input to device also
8edc124
John Ho
commited on
Jul 24
testing more efficient model loading
b3db9ce
John Ho
commited on
Jul 24
testing more efficient model loading
f18bd0f
John Ho
commited on
Jul 24
make sure DTYPE is used
8b3dcea
John Ho
commited on
Jul 23
testing cuda for processor
1679d51
John Ho
commited on
Jul 23
added back in input.to(device)
ce0e222
John Ho
commited on
Jul 23
make flash attention an input
f10889a
John Ho
commited on
Jul 23
try use flash attention again
f87fafd
John Ho
commited on
Jul 23
trying to set device outsite of spaces.GPU decorator
2a9891d
John Ho
commited on
Jul 23
trying different torch dtype
7c03996
John Ho
commited on
Jul 23
trying without flash attention
d020ddb
John Ho
commited on
Jul 23
updated to set device automatically
d2b769f
John Ho
commited on
Jul 23
allow user to edit prompt
4c2d972
John Ho
commited on
Jul 23
forgot to load model
c74b32a
John Ho
commited on
Jul 23
debug multiple value for fps error
a32aeaf
John Ho
commited on
Jul 23
debug multiple value for fps error
c0b7fcc
John Ho
commited on
Jul 23
fixed missing import
ff62e4f
John Ho
commited on
Jul 23
added function to read fps
4fa18d9
John Ho
commited on
Jul 23
init commit
0bf8729
John Ho
commited on
Jul 23
Initial commit
71ef59e
unverified
John Ho
commited on
Jul 23