bzz's Stars
amazon-science/CodeSage
CodeSage: Code Representation Learning At Scale (ICLR 2024)
gitbugactions/gitbug-java
A Reproducible Benchmark of Recent Java Bugs
joernio/joern
Open-source code analysis platform for C/C++/Java/Binary/Javascript/Python/Kotlin based on code property graphs. Discord https://discord.gg/vv4MH284Hc
pytorch/torchtune
A Native-PyTorch Library for LLM Fine-tuning
thuiar/TEXTOIR
TEXTOIR is the first opensource toolkit for text open intent recognition. (ACL 2021)
gems-uff/merge-nature
Companion website for the paper "On the Nature of Software Merge Conflicts"
herrera-sergio/AlmostRERERE
A framework for automating the resolution of merge conflicts which learns from the resolutions made by developers and encodes such knowledge into conflict resolution rules applicable to conflicts not seen before
ibm-granite/granite-code-models
Granite Code Models: A Family of Open Foundation Models for Code Intelligence
bigscience-workshop/architecture-objective
dqbd/tiktokenizer
Online playground for OpenAPI tokenizers
EleutherAI/improved-t5
Experiments for efforts to train a new and improved t5
QwenLM/CodeQwen1.5
CodeQwen1.5 is the code version of Qwen, the large language model series developed by Qwen team, Alibaba Cloud.
microsoft/ToolTalk
Evaluating tool-augmented LLMs in conversation settings
google-deepmind/penzai
A JAX research toolkit for building, editing, and visualizing neural networks.
WM-SEMERU/galeras-benchmark
Benchmarking Causl Study to Interpret Large Language Models for Source Code
open-compass/T-Eval
[ACL2024] T-Eval: Evaluating Tool Utilization Capability of Large Language Models Step by Step
codefuse-ai/codefuse-evaluation
Industrial-level evaluation benchmarks for Coding LLMs in the full life-cycle of AI native software developing.企业级代码大模型评测体系,持续开放中
Kaleidophon/deep-significance
Enabling easy statistical significance testing for deep neural networks.
Kaleidophon/awesome-experimental-standards-deep-learning
Repository collecting resources and best practices to improve experimental rigour in deep learning research.
hzy312/Awesome-LLM-Watermark
UP-TO-DATE LLM Watermark paper. 🔥🔥🔥
HazyResearch/meerkat
Creative interactive views of any dataset.
google-research/pynsy
Heavyweight Python dynamic analysis framework
google-deepmind/onetwo
codetlingua/codetlingua
SLAB-NLP/Multi-Prompt-LLM-Evaluation
State of What Art? A Call for Multi-Prompt LLM Evaluation
i-Eval/FairEval
TabbyML/interview-questions
TabbyML/tabby
Self-hosted AI coding assistant
OpenCodeInterpreter/OpenCodeInterpreter
OpenCodeInterpreter is a suite of open-source code generation systems aimed at bridging the gap between large language models and sophisticated proprietary systems like the GPT-4 Code Interpreter. It significantly enhances code generation capabilities by integrating execution and iterative refinement functionalities.
WM-SEMERU/CausalSE
Causal Interpretability for SE