token limit to [8192], model run on cpu need [.float()]
bdb909e
tomato
commited on
Spaces:
Paused
Paused
Commit History
use model with [int4]
0f7e2c9
tomato
commited on
remove [.half().cpu()]
f2a8b90
tomato
commited on
revoke model change, fix requirements crash
34c4693
tomato
commited on
change model from [silver/chatglm-6b-int4-slim] to [THUDM/chatglm-6b-int4]
4301845
tomato
commited on
try to fix [Logger] error
8cae0ca
tomato
commited on
unknow error [warning_once] from [Logger]
d48a51a
tomato
commited on
fix [gradio] error
152a7cc
tomato
commited on
fix [gradio.Slider] [value=5] error
58c460a
tomato
commited on
remove cuda related code
4abe175
tomato
commited on
transfer from [csebuetnlp/mT5_multilingual_XLSum] to [silver/chatglm-6b-int4-slim]
e91f2c0
tomato
commited on
use another kind of gradio interface
17409ce
tomato
commited on
from [pipeline] to using [Model Instruction]
7d93f13
tomato
commited on
fix coding error
4db7dc4
tomato
commited on
use another model [csebuetnlp/mT5_multilingual_XLSum]
e6eb31e
tomato
commited on
try to solve [runtime error], from followng [pipeline] to following [instruction]
c872f8c
tomato
commited on
try to solve [runtime error], task="Summarization" -> "summarization"
2ccf3c4
tomato
commited on
try to solve [runtime error]
fe88fa5
tomato
commited on
it's first commit, for testing model [IDEA-CCNL/Randeng-Pegasus-238M-Summary-Chinese]
9e5c5bb
tomato
commited on