Pinned Loading

1. SWE-agent SWE-agent Public

   SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

   Python 13.3k 1.3k

2. tree-of-thought-llm tree-of-thought-llm Public

   [NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

   Python 4.6k 430

3. LLM-Shearing LLM-Shearing Public

   [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

   Python 539 41

4. SWE-bench SWE-bench Public

   [ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?

   Python 1.8k 306

5. SimCSE SimCSE Public

   [EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

   Python 3.4k 510

6. MeZO MeZO Public

   [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333

   Python 1k 60