PR #1910 Support input float tensor directly

add interface for float input

ningshanwutuobang committed 2 years ago

fixed inpL shape and type

ningshanwutuobang committed 2 years ago

add examples of input floats

ningshanwutuobang committed 2 years ago

add test example for embd input

ningshanwutuobang committed 2 years ago

fixed sampling

ningshanwutuobang committed 2 years ago

add free for context

ningshanwutuobang committed 2 years ago

fixed add end condition for generating

ningshanwutuobang committed 2 years ago

add examples for llava.py

ningshanwutuobang committed 2 years ago

add READMD for llava.py

ningshanwutuobang committed 2 years ago

add READMD for llava.py

ningshanwutuobang committed 2 years ago

Merge remote-tracking branch 'origin/master' into embd_inp

ningshanwutuobang committed 2 years ago

add example of PandaGPT

ningshanwutuobang committed 2 years ago

refactor the interface and fixed the styles

ningshanwutuobang committed 2 years ago

Merge branch 'master' into embd_inp

ningshanwutuobang committed 2 years ago

add cmake build for embd-input

ningshanwutuobang committed 2 years ago

add cmake build for embd-input

ningshanwutuobang committed 2 years ago

Add MiniGPT-4 example

ningshanwutuobang committed 2 years ago

change the order of the args of llama_eval_internal

ningshanwutuobang committed 2 years ago

Merge remote-tracking branch 'origin/master' into embd_inp

ningshanwutuobang committed 2 years ago

fix ci error

ningshanwutuobang committed 2 years ago

llama.cpp Support input float tensor directly #1910 Merged