mirror of
https://github.com/SakanaAI/doc-to-lora.git
synced 2026-07-23 17:01:04 +02:00
d99fa8732b
- work with vllm self-gen data (everything is tokenized during self-gen) - fix chat template! - not use liger kernel for distillation (for both training and eval)
32 lines
391 B
Text
32 lines
391 B
Text
.venv/
|
|
.cursorrules
|
|
tmp/
|
|
openai_batches/
|
|
models/
|
|
results/
|
|
datasets/
|
|
llm-comparator/
|
|
# Ignore data files but not scripts
|
|
/data/processed_datasets/
|
|
/data/raw_datasets/
|
|
/data/distil/
|
|
__pycache__/
|
|
*egg-info/
|
|
.vscode/
|
|
.ipynb_checkpoints/
|
|
wandb/
|
|
*.bak
|
|
*outputs/
|
|
plots/
|
|
*.out
|
|
*.pt
|
|
*.pth
|
|
*.bin
|
|
*.safetensors
|
|
*tfevents*
|
|
watcher_state.yaml
|
|
eval_results/
|
|
.github/
|
|
*.code-workspace
|
|
.wandb/
|
|
.ruff_cache/
|