yilinjz / astchunkLinks
ASTChunk is a Python toolkit for code chunking using Abstract Syntax Trees (ASTs), designed to create structurally sound and meaningful code segments.
☆30Updated 2 weeks ago
Alternatives and similar repositories for astchunk
Users that are interested in astchunk are comparing it to the libraries listed below
Sorting:
- Enable tool-use ability for any LLM model (DeepSeek V3/R1, etc.)☆51Updated last month
- LLMs as Collaboratively Edited Knowledge Bases☆45Updated last year
- Submodular optimization for context engineering: query fan-out, text selection, passage reranking☆33Updated this week
- An open-source toolkit helping developers build natural language database query solutions☆21Updated 2 months ago
- Nexusflow function call, tool use, and agent benchmarks.☆24Updated 7 months ago
- a tool for gerenate dataset from doc☆12Updated 3 months ago
- ☆13Updated 2 months ago
- Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth☆122Updated this week
- ☆48Updated 5 months ago
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated last year
- XVERSE-MoE-A36B: A multilingual large language model developed by XVERSE Technology Inc.☆39Updated 10 months ago
- Query, ask and chat with a document-index via transformer models!☆17Updated 2 years ago
- ☆18Updated last month
- OVALChat is a customizable Web app aimed at conducting user studies with chatbots☆28Updated last year
- AgentParse is a high-performance parsing library designed to map various structured data formats (such as Pydantic models, JSON, YAML, an…☆13Updated 2 weeks ago
- Official Repository for Task-Circuit Quantization☆20Updated last month
- Query Expension for Better Query Embedding using LLMs☆52Updated 4 months ago
- Implemented a script that automatically adjusts Qwen3's inference and non-inference capabilities, based on an OpenAI-like API. The infere…☆21Updated 2 months ago
- Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];☆40Updated last year
- Reasoning by Communicating with Agents☆29Updated 2 months ago
- ☆40Updated 7 months ago
- ☆17Updated 11 months ago
- Very minimal (and stateless) agent framework☆44Updated 6 months ago
- ☆29Updated 2 weeks ago
- Official repository for RAGViz: Diagnose and Visualize Retrieval-Augmented Generation [EMNLP 2024]☆85Updated 5 months ago
- ☆35Updated 2 years ago
- ☆47Updated 9 months ago
- Minimal zero-shot intent classifier for arbitrary intent slot filling, via LLM prompting w LangChain.☆33Updated 2 years ago
- The minimal, ad-hoc way of plug and play NebulaGraph with pip install, even inside Colab Notebook!☆17Updated last year
- Self-host LLMs with LMDeploy and BentoML☆20Updated last week