-
-
sil_evolving_dataset Public
Self-Improving Leaderboard Evolving Dataset
Python MIT License UpdatedAug 20, 2026 -
-
gavel Public
Multi-model fusion for Claude Code: ask Claude + Codex + Gemini in parallel, then judge their answers into one and act on it.
-
-
-
-
Claude-in-Arc Public
Forked from chxsong/Claude-in-ArcA deep patching toolkit designed to inject Anthropic's Official Claude Chrome Extension natively into Arc Browser's visual structure.
JavaScript MIT License UpdatedMar 31, 2026 -
-
-
-
LangSAE-Editing Public
Code for arXiv paper - LangSAE Editing: Improving Multilingual Information Retrieval via Post-hoc Language Identity Removal
-
evalchemy Public
Forked from mlfoundations/evalchemyAutomatic evals for LLMs
-
JunRAG Public
A modular RAG library designed for multi-hop questions with support for query decomposition, parallel processing, Qdrant integration, vLLM-powered inference, and dynamic GPU assignment.
Python MIT License UpdatedDec 15, 2025 -
lm-evaluation-harness Public
Forked from EleutherAI/lm-evaluation-harnessA framework for few-shot evaluation of language models.
-
PAG-Net Public
PAG-Net: A lightweight Guide Network for spatial localization.
Jupyter Notebook MIT License UpdatedNov 25, 2025 -
JunGrad Public
A robust N-D autograd library with comprehensive operations, neural network layers, and optimizers.
Jupyter Notebook MIT License UpdatedNov 15, 2025 -
-
Benchmark-Profiling Public
Code for EMNLP 2025 paper - Benchmark Profiling: Mechanistic Diagnosis of LLM Benchmarks
-
-
-
-
mask_benchmark Public
Forked from centerforaisafety/maskCode for evaluating AI systems on the MASK honesty benchmark.
Python MIT License UpdatedJun 3, 2025 -
gpu_bpe Public
Forked from evintunador/gpu_bpetutorial for training a BPE tokenizer on multiple GPUs
Python MIT License UpdatedMay 5, 2025 -
reasoning-steering Public
Forked from nrimsky/CAAMaking models reason through CAA
Jupyter Notebook MIT License UpdatedApr 7, 2025 -
-
math-reasoning-eval Public
Forked from QwenLM/Qwen2.5-MathA framework for evaluating mathematical reasoning tasks.
Python UpdatedJan 11, 2025 -
-
arithmetic-mechanism Public
Forked from zepingyu0512/arithmetic-mechanismFork of code for EMNLP 2024 paper: Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis
Jupyter Notebook UpdatedJan 10, 2025 -
Coding-Spot Public
Code for arXiv paper - Exploring Coding Spot: Understanding Parametric Contributions to LLM Coding Performance
{{ message }}