| .. |
|
configs
|
fa0a389f74
add max_step feature for training and eval
|
hai 1 ano |
|
data
|
4913d3ad24
Add missing copyright header
|
hai 1 ano |
|
datasets
|
69db75d425
fix incorrect split of InstructionDataset
|
%!s(int64=2) %!d(string=hai) anos |
|
inference
|
a414ca6a57
Update chat format for llama3
|
hai 1 ano |
|
model_checkpointing
|
ce9501f22c
remove relative imports
|
%!s(int64=2) %!d(string=hai) anos |
|
policies
|
ce9501f22c
remove relative imports
|
%!s(int64=2) %!d(string=hai) anos |
|
tools
|
4913d3ad24
Add missing copyright header
|
hai 1 ano |
|
utils
|
17a6d16289
Test batching for both llama versions
|
hai 1 ano |
|
finetuning.py
|
113ea18bf1
Replace LlamaTokenizer with AutoTokenizer
|
hai 1 ano |
Matthias Reso
17a6d16289
Test batching for both llama versions