yujunjun/olmocr
1
0
Fork 0
mirror of https://github.com/allenai/olmocr.git synced 2025-06-27 04:00:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Smaller config for now, fixing a few requirements

Browse Source
This commit is contained in:
Jake Poznanski 2024-09-23 08:20:08 -07:00
parent 256d77c232
commit b915e7de00
2 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
pdelfin/train/config/qwen2vl-2b.yaml
View File

@ -87,8 +87,8 @@ valid_data:
# Mostly pulled from https://github.com/QwenLM/Qwen2/blob/main/examples/sft/finetune.sh # Mostly pulled from https://github.com/QwenLM/Qwen2/blob/main/examples/sft/finetune.sh
hparams: hparams:
batch_size: 2 batch_size: 1
eval_batch_size: 2 eval_batch_size: 1
gradient_accumulation_steps: 4 gradient_accumulation_steps: 4
gradient_checkpointing: true gradient_checkpointing: true
clip_grad_norm: 1.0 clip_grad_norm: 1.0

3
pyproject.toml
View File

@ -24,7 +24,8 @@ dependencies = [
"pypdf", "pypdf",
"pymupdf", "pymupdf",
"pypdfium2", "pypdfium2",
"lingua-language-detector" "lingua-language-detector",
"Pillow",
] ]
license = {file = "LICENSE"} license = {file = "LICENSE"}