Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
- python
- fine-tuning
- gguf
- huggingface
142,273 visible repositories in the index
145–168 of 1,944 · Most stars
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Source code for Twitter's Recommendation Algorithm
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
the LLM vulnerability scanner
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
Open-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.
High accuracy RAG for answering questions from scientific documents with citations
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.
ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.
Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!
Curated prompts, frameworks and papers for LLMs and agents, with an engineering bias. Prompt engineering, context engineering, agent harnesses, red teaming.
KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge bases. It can effectively overcome the shortcomings of the traditional RAG vector similarity calculation model.
ImageBind One Embedding Space to Bind Them All
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
The repository host gives no description.
slime is an LLM training framework for RL Scaling.
Real-time Claude Code usage monitor with predictions and warnings
CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)
TranslatedDaily check-in script based on 「Docker」/「QingLong Panel」/「Synology」 (supports multiple accounts). Check-in list: |iQIYI|Quanmin K Song|Youdao Cloud Notes|Baidu Tieba|Bilibili|V2EX|AcFun|Smzdm (What's Worth Buying)|Aliyun Drive|i Moutai Purchase Application|Xiaomi Sports|Baidu Search Resource Platform|Right Mountain Forum (Enshan)|Aola Star|
FreeAskInternet is a completely free, PRIVATE and LOCALLY running search aggregator & answer generate using MULTI LLMs, without GPU needed. The user can ask a question and the system will make a multi engine search and combine the search result to LLM and generate the answer based on search results. It's all FREE to use.
"ClawWork: OpenClaw as Your AI Coworker - 💰 $15K earned in 11 Hours"
Accessible large language models via k-bit quantization for PyTorch.
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.