diff options
| author | Yuren Hao <yurenh2@illinois.edu> | 2026-04-08 22:06:05 -0500 |
|---|---|---|
| committer | Yuren Hao <yurenh2@illinois.edu> | 2026-04-08 22:06:05 -0500 |
| commit | 05704d0eb2fa59fe727652465b07db40bcb06c38 (patch) | |
| tree | 8904aca836cf552fd1a5ae8c2174e9f91e70bbbc /putnam-bench-anon/requirements.txt | |
Initial release: GAP framework
- Full pipeline: variant generation, multi-judge verification, evaluation
- Loaders for OpenAI / Anthropic / Google / xAI / OpenRouter / vLLM
- Framework-level mechanism analyses: paired structural overlap, repairability rescue, self-correction probe, cross-model agreement, topic x problem-type interaction
- Unicode -> bare-LaTeX cleaner + audit + spot-check
- Mirrors https://huggingface.co/datasets/blackhao0426/PutnamGAP
Diffstat (limited to 'putnam-bench-anon/requirements.txt')
| -rw-r--r-- | putnam-bench-anon/requirements.txt | 35 |
1 files changed, 35 insertions, 0 deletions
diff --git a/putnam-bench-anon/requirements.txt b/putnam-bench-anon/requirements.txt new file mode 100644 index 0000000..d36dc4a --- /dev/null +++ b/putnam-bench-anon/requirements.txt @@ -0,0 +1,35 @@ +# Core AI provider clients +openai>=1.0.0 +anthropic>=0.25.0 +google-generativeai>=0.3.0 + +# Local model support +transformers>=4.30.0 +torch>=2.0.0 +accelerate>=0.20.0 + +# Optional: VLLM for local model serving +vllm>=0.3.0 + +# System utilities +psutil>=5.9.0 +six>=1.16.0 + +# Development and utility libraries +asyncio-throttle>=1.0.0 +aiohttp>=3.8.0 +requests>=2.25.0 + +# Data handling +numpy>=1.21.0 +pandas>=1.3.0 + +# JSON and data processing +jsonschema>=4.0.0 + +# Math and scientific computing +sympy>=1.9.0 +matplotlib>=3.5.0 + +# Progress bars and UI +tqdm>=4.60.0
\ No newline at end of file |