Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Spaces:
yahma
/
rwkv-14b
like
25
Runtime error
App
Files
Files
Community
1
main
rwkv-14b
Commit History
fix typo
7314be4
gururise
commited on
Feb 13, 2023
update to latest rwkvstic
f9ef5de
gururise
commited on
Feb 13, 2023
update to feb13 8bit snapshot
d8f4cef
gururise
commited on
Feb 13, 2023
keep Feb 04 snapshot for now
7a2c886
gururise
commited on
Feb 13, 2023
fix bug
e0b89dc
gururise
commited on
Feb 13, 2023
increase chunksize to 32 for better accuracy
a3cf1a2
gururise
commited on
Feb 13, 2023
update to feb 13 snapshot
baa0ba8
gururise
commited on
Feb 13, 2023
lower chunksize to speed things up
6d226a4
gururise
commited on
Feb 11, 2023
update app examples
fa36661
gururise
commited on
Feb 11, 2023
update gpu ram size for t4
30a53de
gururise
commited on
Feb 11, 2023
quantized 14b
6008249
gururise
commited on
Feb 11, 2023
switch to quantized 14b model
325fdb5
gururise
commited on
Feb 11, 2023
update to bfloat16 for faster speed
137d353
gururise
commited on
Feb 11, 2023
fix typo
2c46054
gururise
commited on
Feb 11, 2023
add additional examples
457d299
gururise
commited on
Feb 11, 2023
14b non-quantized float32 model
fb173e2
gururise
commited on
Feb 11, 2023
initial commit
66d1c99
gururise
commited on
Feb 11, 2023
initial commit
7bcd26a
yahma
commited on
Feb 11, 2023