从零构建大模型：从预训练到RLHF的完整实践
Repository Index
78,351 visible repositories in the index
505–528 of 890 · Most stars
streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL
- captioning
- fine-tuning
- florence-2
- multimodal
The /llms.txt file, helping language models use your website
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
Repository for benchmarking graph neural networks (JMLR 2023)
- graph-representation-learning
- graph-neural-networks
- benchmark-framework
- graph-deep-learning
Self-hosted LLM router with a managed safety net. OpenAI-compatible. BYOK. Single-workspace. Streaming. For more advanced routing choose hosted OrcaRouter
- ai-gateway
- ai-gateways
- anthropic-api
- byok
[NeurIPS 2026] Safety failures in coding agents and frontier LLMs. Reproducible workspaces for studying when AI agents generate unsafe data during task completion.
A benchmark for LLMs on complicated tasks in the terminal
CodeGeeX4-ALL-9B, a versatile model for all AI software development scenarios, including code completion, code interpreter, web search, function calling, repository-level Q&A and much more.
Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
- evaluation
- evaluation-framework
- evaluation-metrics
- huggingface
A benchmark for evaluating LLMs on Chinese traditional fortune telling — Bazi (八字) and Ziwei Doushu (紫微斗数).
Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.
Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.
- finetune
- stable-diffusion
✨✨[NeurIPS 2025] VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
- large-multimodal-models
- multimodal-large-language-models
- omni-language-model
- omni-modal-video-understanding
mPLUG-Owl: The Powerful Multi-modal Large Language Model Family
OCRFlux is a lightweight yet powerful multimodal toolkit that significantly advances PDF-to-Markdown conversion, excelling in complex layout handling, complicated table parsing and cross-page content merging.
FastAPI + Playwright + Camoufox 中间层代理服务器，兼容OpenAI API且支持参数转发。项目通过浏览器自动化将API请求转发到 Google AI Studio Chat，并同样按照OpenAI标准格式返回的工具。内置调试WebUI面板。
- camoufox
- google-ai-studio
- middleware
- openai-api
The Official Python Client for Lamini's API
SkyRL: A Modular Full-stack RL Library for LLMs
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
- deep-learning
- flax
- jax
- language-model
A Lightweight LLM Post-Training Library
HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance