Geeta Chauhan
|
486b880964
Pass `use_cache=False` when training with FSDP (#165)
|
1 year ago |
Andrew Gu
|
353dfcdc21
Pass `use_cache=False` when training with FSDP
|
1 year ago |
Geeta Chauhan
|
322522e9a2
Fix the chat example for generate when load peft model (#158)
|
1 year ago |
Hamid Shojanazeri
|
0e9d1dfa78
passing input_ids as peft doesn't pass position args to base_model
|
1 year ago |
Hamid Shojanazeri
|
a14363ca41
Update inference.md (#136)
|
1 year ago |
Matthias Reso
|
1437b917d0
Fix lint error
|
1 year ago |
Matthias Reso
|
34e45490ba
Exchange micro_batching_size against gradient_accumulation_steps in docs
|
1 year ago |
Matthias Reso
|
47ae6d0326
Remove print as it breaks progress bar and update progress bar description instead
|
1 year ago |
Matthias Reso
|
9def4fbafd
Remove micro_batch_training parameter and replace with gradient_accumulation_steps
|
1 year ago |
Geeta Chauhan
|
fbc513ec47
adding notes how to get the HF models (#151)
|
1 year ago |
Hamid Shojanazeri
|
bcfafd9a0b
adding notes how to get the HF models
|
1 year ago |
Geeta Chauhan
|
cfba150311
adding llama code inference (#144)
|
1 year ago |
Hamid Shojanazeri
|
6105a3f886
clarifying the infilling use-case
|
1 year ago |
Hamid Shojanazeri
|
8b0008433c
fix typos
|
1 year ago |
Hamid Shojanazeri
|
564ef2f628
remove padding logic
|
1 year ago |
Hamid Shojanazeri
|
277a292fbc
adding autotokenizer
|
1 year ago |
Hamid Shojanazeri
|
3f2fb9167e
adding notes to model not supporting infilling
|
1 year ago |
sekyonda
|
1e0e4fb8a9
Update inference.md
|
1 year ago |
sekyondaMeta
|
37d7151494
Merge branch 'facebookresearch:main' into promptInfo
|
1 year ago |
Hamid Shojanazeri
|
c62428b99c
setting defaults of temp and top_p
|
1 year ago |
Hamid Shojanazeri
|
c014ae7cb8
setting BT option to true
|
1 year ago |
Hamid Shojanazeri
|
4fa44e16d9
add note for python llama not suited for llama infilling
|
1 year ago |
Hamid Shojanazeri
|
b18a186385
removing the option to take prompt from cli
|
1 year ago |
Hamid Shojanazeri
|
75991d8795
fix the extra line added and remove take prompt from cli
|
1 year ago |
Hamid Shojanazeri
|
d28fc9898a
addressing doc comments
|
1 year ago |
Hamid Shojanazeri
|
a234d1fe0c
fix typos
|
1 year ago |
Hamid Shojanazeri
|
2d9f4796e8
fixing the output format
|
1 year ago |
Hamid Shojanazeri
|
1e8ea70b26
adding llama code inference
|
1 year ago |
Geeta Chauhan
|
82e05c46e0
fix a bug in the config for use_fast_kernels (#121)
|
1 year ago |
Hamid Shojanazeri
|
971c079aa6
bugfix: remove duplicate load_peft_model (#124)
|
1 year ago |