基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等
Repository Index
66,263 visible repositories in the index
625–648 of 896 · Most stars
A modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.
Unsupervised Learning for Image Registration
- image-registration
- image-alignment
- machine-learning
- deep-learning
Let Skills Evolve Collectively with Agentic Evolver
A CLI tool to query your local WeChat data — chat history, contacts, sessions, favorites, and more. Designed for LLM integration.
A production-ready FastAPI template for building AI agent applications with LangGraph integration. This template provides a robust foundation for building scalable, secure, and maintainable AI agent services.
Control Any Computer Using LLMs.
Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.
- agent-skill
- claude-code
- codex
- cursor
dLLM: Simple Diffusion Language Modeling
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
- low-precision
- pruning
- sparsity
- auto-tuning
vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"
- cross-modal-learning
- cross-modality
- deep-learning
- language-model
A GPU task manager for Windows, Linux, and WSL: per-process VRAM, GPU activity, and LLM model/KV-cache insights (Windows AMD and NVIDIA).
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
- apple-silicon
- local-ai
- mlx
- mtp
Lightweight Python library for adding real-time multi-object tracking to any detector.
- tracking
- tracking-algorithm
- kalman-filter
- object-tracking
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
- kv-cache
- llm-inference
- local-llm
- quantization
Project Page for "LISA: Reasoning Segmentation via Large Language Model"
- large-language-model
- llm
- multi-modal
- segmentation
Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)
- fine-tuning-llm
- large-language-models
- long-context
- llm
Build, personalize and control your own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6
- deep-learning
- fine-tuning
- gpt-2
- gpt-j
Interactive architecture diagrams for codebases
Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
[EMNLP-2024] Build multimodal language agents for fast prototype and production
- large-language-models
- multimodal-agent
- vision-and-language
- agent
[NeurIPS 2025] OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from simple icons to intricate anime characters.
[NeurIPS 2026] Safety failures in coding agents and frontier LLMs. Reproducible workspaces for studying when AI agents generate unsafe data during task completion.