 Kai Wu
|
d5767a1200
changed requirement.txt and readme.md
|
%!s(int64=2) %!d(string=hai) anos |
|
Kai Wu
|
6204d5ae38
fix generate_qa function
|
%!s(int64=2) %!d(string=hai) anos |
|
Kai Wu
|
b07cbad1d7
working draft for vllm using llama3-70B
|
%!s(int64=2) %!d(string=hai) anos |
|
Kai Wu
|
230c557730
adding support for vllm local endpoint and llama3 model
|
%!s(int64=2) %!d(string=hai) anos |
 HamidShojanazeri
|
a036811950
adding chatbot-e2e
|
%!s(int64=2) %!d(string=hai) anos |
|
Hamid Shojanazeri
|
5f11aeb88a
Disable prefix tuning and limit llama adapter (#482)
|
%!s(int64=2) %!d(string=hai) anos |
|
Hamid Shojanazeri
|
3d5c701569
FMBench readme updates for Llama3 on Inf2 and config.yml cleanup (#486)
|
%!s(int64=2) %!d(string=hai) anos |
|
Hamid Shojanazeri
|
c3b26283e5
Fix lm_eval.tasks' has no attribute 'initialize_tasks' error (#488)
|
%!s(int64=2) %!d(string=hai) anos |
 Jeff Tang
|
c113695deb
Add LangChain recipes (#485)
|
%!s(int64=2) %!d(string=hai) anos |
|
Jeff Tang
|
17e68a07b6
speller check fixes
|
%!s(int64=2) %!d(string=hai) anos |
|
Jeff Tang
|
8f31a612e9
speller check
|
%!s(int64=2) %!d(string=hai) anos |
|
Jeff Tang
|
c6769a0870
folder structure change
|
%!s(int64=2) %!d(string=hai) anos |
 Keita Watanabe
|
a2a2ffd78a
fix lm_eval.tasks' has no attribute 'initialize_tasks' error
|
%!s(int64=2) %!d(string=hai) anos |
 Amit Arora
|
c1c213fd5b
the prev commit accidently deleted some comments from config.yml
|
%!s(int64=2) %!d(string=hai) anos |
|
Amit Arora
|
903c4c3db0
FMBench readme update for Llama3 on Inf2 and config file cleanup
|
%!s(int64=2) %!d(string=hai) anos |
|
Jeff Tang
|
12ac7b44c8
typo and some formating fixes; embedding model change; removal of the llama 3 special tokens not needed for ollama
|
%!s(int64=2) %!d(string=hai) anos |
 Lance Martin
|
c183da6acb
Update README.md
|
%!s(int64=2) %!d(string=hai) anos |
 Lance Martin
|
f6fbf97bc9
Add LangChain recipies
|
%!s(int64=2) %!d(string=hai) anos |
|
Keita Watanabe
|
0e54f5634a
use AutoTokenizer instead of LlamaTokenizer
|
%!s(int64=2) %!d(string=hai) anos |
|
Jeff Tang
|
6da989a774
Update prompt guide for Llama 3 (#484)
|
%!s(int64=2) %!d(string=hai) anos |
|
Jeff Tang
|
23afbd481e
some typo fixes; codellama 70; tokens generated; colab link
|
%!s(int64=2) %!d(string=hai) anos |
 Dalton Flanagan
|
aab327c2fe
Update prompt guide for Llama 3
|
%!s(int64=2) %!d(string=hai) anos |
 Matthias Reso
|
4b93dc6080
Use RuntimeError instead assert
|
%!s(int64=2) %!d(string=hai) anos |
|
Matthias Reso
|
d87277277f
Fix LLaMA ->Llama
|
%!s(int64=2) %!d(string=hai) anos |
|
Matthias Reso
|
7ca0b66578
Fix unit tests
|
%!s(int64=2) %!d(string=hai) anos |
|
Matthias Reso
|
853f928987
Add unit test for config check
|
%!s(int64=2) %!d(string=hai) anos |
|
Matthias Reso
|
091d58df17
Disable prefix tuning as its currently not supported; Limit llama_adapter usage to non-FSDP only
|
%!s(int64=2) %!d(string=hai) anos |
|
Jeff Tang
|
14e4b05bed
Q&A RAG pipeline with MongoDB, Hugging Face and Llama3 (#455)
|
%!s(int64=2) %!d(string=hai) anos |
|
Hamid Shojanazeri
|
ed713680b3
Updated fine-tuning readme to Meta Llama 3 (#479)
|
%!s(int64=2) %!d(string=hai) anos |
|
Kai Wu
|
7a08c27879
Merge branch 'main' into fix/finetune_readme
|
%!s(int64=2) %!d(string=hai) anos |
