Hamid Shojanazeri
|
38df368a70
A tutorial of building a Llama-enabled WhatsApp Chatbot (#287)
|
1 year ago |
Jeff Tang
|
e722c12581
spell check errors fix
|
1 year ago |
Jeff Tang
|
7298487dbc
updated tutorial and added llama_chatbot.py
|
1 year ago |
gaopengzhi
|
bb7c6c1e33
Support FSDP scenario
|
1 year ago |
Jeff Tang
|
49beaefbb1
whatsapp_llama2 update based on Beto feedback
|
1 year ago |
Chester Hu
|
092c88f17b
Remove personal file path
|
1 year ago |
Chester Hu
|
5cea990a5c
original commit for PR
|
1 year ago |
Jeff Tang
|
54ff88e9a6
README update
|
1 year ago |
Jeff Tang
|
1acbb2ba13
Building Llama-enabled WhatsApp Chatbot
|
1 year ago |
Hamid Shojanazeri
|
3b77a270a8
Llama 2 On-Prem Inference Using vLLM and TGI (#279)
|
1 year ago |
Jeff Tang
|
32e9d97167
Update demo_apps/llama-on-prem.md
|
1 year ago |
Jeff Tang
|
729b2a996d
Update demo_apps/llama-on-prem.md
|
1 year ago |
Jeff Tang
|
0199c8454c
readme update
|
1 year ago |
Jeff Tang
|
1610108f5d
Update demo_apps/llama-on-prem.md
|
1 year ago |
Jeff Tang
|
f42fec84cd
spelling check failures fix
|
1 year ago |
Jeff Tang
|
f880e58c67
simplify vllm install and api server run
|
1 year ago |
Jeff Tang
|
ec72c6618c
update main README
|
1 year ago |
gaopengzhi
|
b1d9efd155
Refactor gradient clipping feature
|
1 year ago |
Jeff Tang
|
c97d28c65c
update based on PR feedback
|
1 year ago |
Jeff Tang
|
492350ae45
vllm tgi comp
|
1 year ago |
Jeff Tang
|
95db9a0193
multiple gpu vllm
|
1 year ago |
Hamid Shojanazeri
|
acce2d8770
Use bf16 parameters in bf16 mixed prec (#283)
|
1 year ago |
Jeff Tang
|
dd84ee36ae
llama-on-prem.md update on the HG access token
|
1 year ago |
Jeff Tang
|
35686f4353
main readme update
|
1 year ago |
Jeremy Howard
|
eca8410b32
Use bf16 parameters in bf16 mixed prec
|
1 year ago |
gaopengzhi
|
04befdef69
Add gradient clipping feature
|
1 year ago |
Jeff Tang
|
da8f9f0d41
more update README
|
1 year ago |
Jeff Tang
|
106327acdd
more update README
|
1 year ago |
Jeff Tang
|
54cd436352
more update README
|
1 year ago |
Jeff Tang
|
eba8310d06
readme more update
|
1 year ago |