Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 1 addition & 4 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
## 🚀 Quick Start

### Installation
0. 0. Install uv (optional if you already have it): `curl -LsSf https://astral.sh/uv/install.sh | sh` (or see [uv installation guide](https://docs.astral.sh/uv/getting-started/installation/))
0. Install uv (optional if you already have it): `curl -LsSf https://astral.sh/uv/install.sh | sh` (or see [uv installation guide](https://docs.astral.sh/uv/getting-started/installation/))
1. Create a virtual environment: `uv venv`
2. Activate it: `source .venv/bin/activate` (or use direnv with the provided .envrc)
3. Install dependencies: `uv sync`
Expand All @@ -17,9 +17,6 @@
```bash
# Interactive mode with step-by-step guidance
graid generate-dataset

# Or using uv run (equivalent, but not necessary after uv sync)
uv run graid generate-dataset
```

**Key Features:**
Expand Down
5 changes: 2 additions & 3 deletions graid/src/graid/cli_helpers.py
Original file line number Diff line number Diff line change
Expand Up @@ -730,7 +730,6 @@ def _create_dataset_readme(dataset_dict, config, question_stats):
readme_content += f"""- **Total QA Pairs**: {total_qa_pairs:,}
- **Source Dataset**: {dataset_config['source_info']}
- **Generation Date**: {datetime.now().strftime('%Y-%m-%d')}
- **Image Format**: Embedded in parquet files (no separate image files)
- **Question Types**: {len(question_stats.get('question_counts', {})) if question_stats else 'Multiple'} different reasoning patterns

## Dataset Splits
Expand All @@ -741,7 +740,7 @@ def _create_dataset_readme(dataset_dict, config, question_stats):
for split_name in sorted(dataset_dict.keys()):
split_size = len(dataset_dict[split_name])
percentage = (split_size / total_qa_pairs) * 100
readme_content += f"- **{split_name}**: {split_size:,} ({percentage:.1f}%)\n"
readme_content += f"- **{split_name}**: {split_size:,} ({percentage:.2f}%)\n"

readme_content += "\n## Question Type Distribution\n\n"

Expand All @@ -757,7 +756,7 @@ def _create_dataset_readme(dataset_dict, config, question_stats):
if 'detailed_stats' in question_stats and qtype in question_stats['detailed_stats']:
question_text = question_stats['detailed_stats'][qtype].get("question_text", qtype)

readme_content += f"- **{question_text}**: {count:,} ({percentage:.1f}%)\n"
readme_content += f"- **{question_text}**: {count:,} ({percentage:.2f}%)\n"

# Add performance profiling information if available
if question_stats and 'detailed_stats' in question_stats:
Expand Down
11 changes: 2 additions & 9 deletions pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,6 @@ dependencies = [
"torchmetrics>=1.6.0,<2",
"sqlitedict>=2.1.0,<3",
"numpy==1.26.4",
"ray>=2.43.0,<3",
"fairscale>=0.4.13,<0.5",
"ijson>=3.3.0,<4",
"openai>=1.69.0,<2",
Expand Down Expand Up @@ -105,14 +104,8 @@ include = ["graid/src/graid"]
"graid/src/graid" = "graid"

[build-system]
requires = [ "setuptools", "wheel", "torch"]
build-backend = "setuptools.build_meta:__legacy__"

[tool.setuptools.packages.find]
where = ["graid/src"]

[tool.setuptools.package-dir]
"" = "graid/src"
requires = ["hatchling"]
build-backend = "hatchling.build"

[tool.isort]
profile = "black"
Loading
Loading