 Beto
|
64bea6e60b
updating readme ahead of release
|
vor 10 Monaten |
|
Beto
|
f63ba19827
Fixing tokenizer used for llama 3. Changing quantization configs on safety_utils.
|
vor 10 Monaten |
|
Beto
|
bcdb5b31fe
Fixing quantization config. Removing prints
|
vor 10 Monaten |
|
Beto
|
825cdad951
Adding Llama Guard 2 categories and prompt treatment updates. Adding params to inference script and updating the documentation.
|
vor 10 Monaten |
|
Beto
|
5979dbe996
Merging local with remote
|
vor 10 Monaten |
|
Beto
|
d4cbfa1cc1
Merging upstream llama-recipes to current repo
|
vor 10 Monaten |
 Hamid Shojanazeri
|
aaa9e2c863
Adding a feature that will stop the training/eval process after reaching some max_steps (#428)
|
vor 10 Monaten |
 Kai Wu
|
e6f69f84ad
add max_steps_reached to reduce redundancy
|
vor 10 Monaten |
|
Kai Wu
|
362cda0fa6
fixing test_gradient_accumulation and test_save_to_json
|
vor 10 Monaten |
|
Kai Wu
|
fa0a389f74
add max_step feature for training and eval
|
vor 10 Monaten |
|
Hamid Shojanazeri
|
37c8f72211
Update location and name of llm.py example notebook (#417)
|
vor 11 Monaten |
 Thomas Robinson
|
79266217ef
Update location and name of llm.py example notebook
|
vor 11 Monaten |
|
Hamid Shojanazeri
|
f7aa02af9f
only save training params on rank 0 (#415)
|
vor 11 Monaten |
 jpgard
|
6954b16b3b
only save training params on rank 0
|
vor 11 Monaten |
 varunfb
|
a404c9249c
Notebook to demonstrate using llama and llama-guard together using OctoAI
|
vor 11 Monaten |
|
Beto
|
18d76ed36f
merging into private llama recipes repo
|
vor 11 Monaten |
|
Hamid Shojanazeri
|
64e189914f
update due to peft new release (#407)
|
vor 11 Monaten |
|
Hamid Shojanazeri
|
11f51db28c
adding the kbit prep in the code
|
vor 11 Monaten |
|
Hamid Shojanazeri
|
f058ff6ccd
update due to peft new release
|
vor 11 Monaten |
|
Hamid Shojanazeri
|
6a7478a6aa
Reorg inference throughput folder structure (#404)
|
vor 11 Monaten |
 Chester Hu
|
367e4869ac
Reorg inference throughput folder structure
|
vor 11 Monaten |
|
Hamid Shojanazeri
|
d6eb83f6c5
Add llm class so that externally-hosted models can be called (#398)
|
vor 11 Monaten |
|
Thomas Robinson
|
0346d0d5b8
Add documentation and examples
|
vor 11 Monaten |
|
Hamid Shojanazeri
|
43a1e5cdb0
Fix dead links after directory structure refactor (#397)
|
vor 11 Monaten |
 Suraj Subramanian
|
e2a35420c0
Remove octoai link that is 401-ing
|
vor 11 Monaten |
|
Suraj Subramanian
|
12602f32e2
Merge branch 'main' into subramen-patch-deadlinks
|
vor 11 Monaten |
|
Hamid Shojanazeri
|
c8f4bdac41
Adding open in colab option for notebook (#395)
|
vor 11 Monaten |
|
Thomas Robinson
|
81984a9a44
Remove unnecessary spec format
|
vor 11 Monaten |
 Suraj Subramanian
|
f53f17138b
fix dead links after refactor
|
vor 11 Monaten |
|
Thomas Robinson
|
eee39a7463
Add llm.py class in order to call remotely hosted models
|
vor 11 Monaten |
