 Rahul A R
|
09028bf893
addressing Hamid's comments
|
7 months ago |
 Matthias Reso
|
6d9d48d619
Use apply_chat_template instead of custom functions
|
7 months ago |
|
Matthias Reso
|
5efea160a2
Adapt test_finetuning to new model
|
7 months ago |
 rahul-sarvam
|
eb7ef4225f
Update recipes/multilingual/README.md
|
7 months ago |
|
rahul-sarvam
|
f1f335a591
Update recipes/multilingual/README.md
|
7 months ago |
|
rahul-sarvam
|
47556ce0a6
Update recipes/multilingual/README.md
|
7 months ago |
|
Matthias Reso
|
739483f262
Adjust test_grammar_datasets to stable sort
|
7 months ago |
|
Matthias Reso
|
b96e435cda
Adjust test_samsum_dataset to second model
|
7 months ago |
|
Matthias Reso
|
fac41298b0
Adapt test_custom_dataset to new model
|
7 months ago |
|
Matthias Reso
|
960014a3bb
Fix test_custom_dataset by introducing a stable sort algorithm
|
7 months ago |
|
Matthias Reso
|
b5583b31d5
Adapt test_grammar_dataset to new model
|
7 months ago |
|
Matthias Reso
|
17a6d16289
Test batching for both llama versions
|
7 months ago |
|
Matthias Reso
|
a414ca6a57
Update chat format for llama3
|
7 months ago |
|
Matthias Reso
|
113ea18bf1
Replace LlamaTokenizer with AutoTokenizer
|
7 months ago |
 Beto
|
5979dbe996
Merging local with remote
|
7 months ago |
|
Beto
|
d4cbfa1cc1
Merging upstream llama-recipes to current repo
|
7 months ago |
 Hamid Shojanazeri
|
aaa9e2c863
Adding a feature that will stop the training/eval process after reaching some max_steps (#428)
|
7 months ago |
 Kai Wu
|
e6f69f84ad
add max_steps_reached to reduce redundancy
|
7 months ago |
|
rahul-sarvam
|
0efb8bd31e
Update README.md
|
7 months ago |
|
rahul-sarvam
|
687c2dc5d8
Update README.md
|
7 months ago |
|
Rahul A R
|
2fa8e69b62
add new argument: tokenizer_name
|
7 months ago |
|
Rahul A R
|
f8183b96fe
use new tokenizer_name argument and resize embeddings if required
|
7 months ago |
|
Rahul A R
|
1e4e3e00fc
adding new multilingual recipe
|
7 months ago |
|
Kai Wu
|
362cda0fa6
fixing test_gradient_accumulation and test_save_to_json
|
7 months ago |
|
Kai Wu
|
fa0a389f74
add max_step feature for training and eval
|
7 months ago |
|
Hamid Shojanazeri
|
37c8f72211
Update location and name of llm.py example notebook (#417)
|
7 months ago |
 Thomas Robinson
|
79266217ef
Update location and name of llm.py example notebook
|
7 months ago |
|
Hamid Shojanazeri
|
f7aa02af9f
only save training params on rank 0 (#415)
|
7 months ago |
 jpgard
|
6954b16b3b
only save training params on rank 0
|
7 months ago |
 varunfb
|
a404c9249c
Notebook to demonstrate using llama and llama-guard together using OctoAI
|
8 months ago |
