 Beto
|
980455ce17
Fixing typo, adding HuggingFace and llamaguard to the wordlist
|
11 months ago |
|
Beto
|
56937a68d7
Merging with latest from main
|
11 months ago |
|
Beto
|
fe40d7f60e
Adding the new llama inference code into the relevant readmes
|
11 months ago |
|
Beto
|
3e710f71f8
renaming the prompt format file to conform to repo standards
|
11 months ago |
|
Beto
|
5f83e6d30b
Formatting and updating Readme files, removing test methods and unnecesary prints.
|
11 months ago |
 Chester Hu
|
a31afa5cc7
Fix more spellcheck and add to wordlist for ignore
|
11 months ago |
|
Chester Hu
|
3436e7cefb
Fix spelling
|
11 months ago |
|
Chester Hu
|
72916646d5
PR for inference throughput benchmark on-perm vllm
|
11 months ago |
 Hamid Shojanazeri
|
9ba2e028b1
Merge branch 'main' into ssdp
|
11 months ago |
 Jeff Tang
|
79bd012437
Messenger Llama2 Chatbot Tutorial (#311)
|
11 months ago |
|
Jeff Tang
|
8d3800ac03
README update
|
11 months ago |
 exhyy
|
69db75d425
fix incorrect split of InstructionDataset
|
1 year ago |
|
Beto
|
c0886a0a89
Fixing typo in self
|
11 months ago |
|
Beto
|
f22a2442d7
Removing example from file name
|
11 months ago |
|
Beto
|
0ab6c9ff46
Adding example using the prompt_template and HF inference classes. Adding INTS tags to the prompt template
|
11 months ago |
 Michael Tontchev
|
f30007c128
PR comment changes
|
11 months ago |
 Matthias Reso
|
e7b8afd671
Fix test_finetuning for env without cuda
|
11 months ago |
 Dong Wang
|
cf0c589dc6
add doc string
|
11 months ago |
|
Dong Wang
|
35acf4934e
update fore comments: use module
|
11 months ago |
|
Dong Wang
|
4ff821109a
typo again
|
11 months ago |
|
Dong Wang
|
d915814ed9
fix typo
|
11 months ago |
|
Dong Wang
|
e755ed1d8f
Add example conversion script to convert hf to consolidated weight format
|
11 months ago |
|
Michael Tontchev
|
fc19074085
comment fixes, type fixes
|
11 months ago |
|
Michael Tontchev
|
fa2a314820
Create finetuning data formatter plus tests
|
11 months ago |
|
Beto
|
d92226a873
Removing option for local model, it's not working as expected. Would need further testing with the models from HF
|
11 months ago |
|
Beto
|
7881b3bb99
Changing safety utils to use HF classes to load Llama Guard. Removing Llama plain inference code
|
11 months ago |
|
Chester Hu
|
348d47fe6a
Update PR number
|
11 months ago |
|
Chester Hu
|
6cd89b7d38
PR to add Azure API examples
|
11 months ago |
|
Jeff Tang
|
78f94b7712
messenger llama tutorial update with Gunicorn link
|
11 months ago |
|
Jeff Tang
|
3ec886993d
messenger llama tutorial update
|
11 months ago |
