Commit History

add flash attention, reorder examples
bd17394

leonardlin commited on

add flash_attn
39c14f3

leonardlin commited on

better chat rebuild, added system prompt, load_in_4bit
22b3942

leonardlin commited on

Update README.md
82777d3

leonardlin commited on

Update app.py
1a6b000

leonardlin commited on

Updated settings
d259634

lhl commited on

switch to gradio
1def3a1

lhl commited on

try to fit on T4 (16GB RAM)
d387874

lhl commited on

swap models, examples, check for multigpu, example
f00ac1d

leonardlin commited on

working streaming interface
0e02ca5

leonardlin commited on

Update app.py
4a8282c

lhl commited on

Update app.py
45c171e

lhl commited on

switch to pipelines
5835e21

leonardlin commited on

Update app.py
bc897bf

lhl commited on

Update requirements.txt
9cacdb6

lhl commited on

Update requirements.txt
fd7cabe

lhl commited on

Create requirements.txt
dada0c3

lhl commited on

testing pipelines
812f70a

lhl commited on

mostly working
764f34e

leonardlin commited on

switch to gradio
ba913e7

leonardlin commited on

initial commit
c8d8112

leonardlin commited on