Democratizing Reinforcement Learning for LLMs
- agent-framework
- agentic-workflow
- distributed-training
- llm-training
Repository Index
55,140 visible repositories in the index
25–48 of 48 · Most stars
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
Visualize and compare datasets, target values and associations, with one line of code.
- pandas-dataframe
- eda
- pandas
- data-exploration
A command-line tool that helps you clean up Git branches that have been merged into master.
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
A free AI assistant and survival library that runs on your own computer, with no internet needed. Shows the source of every answer.
When Claude keeps giving you bad answers, make 100 versions of it fight to the death. Same task, 100 different strategies, a bracket, one answer left. Free Claude Code skill.
iOS 16 userland + XNU on Redmi Note 10 Pro (sweet, SM7150)
TranslatedMake a complete hand-drawn explainer video from a topic or an article: part-by-part outline drawing, character-by-character writing, VoiceStudio voiceover, and five built-in production dependencies.
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.
ansible-playbook + buildah = a sweet container image
- ansible
- buildah
[Reimplementation Antol et al 2015] Keras-based LSTM/CNN models for Visual Question Answering
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
- calibration
- cuda
- cuda-graphs
- decision-making
🤖 A Slack bot that integrates with OpenAI's ChatGPT to provide answers, written in Python
Stress tests for the Raspberry Pi :sweat_smile:
- raspberry-pi
- stress-test
- temperature
- pypi
Enhance the standard unittest package with features for testing asyncio libraries
Extract knowledge from all information sources using gpt and other language models. Index and make Q&A session with information sources.
The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.
- ai-agents
- benchmark
- coding-agents
- embodied-ai
Can AI agents rebuild websites through browser exploration?
- benchmark
- harbor
- website-reconstruction
- agent-evaluation
How many bugs can LMs find & fix in large codebases?
Free global SEO/GEO skill for Claude Code, Codex & 10 agent hosts — 18 market portals, 56 stdlib scripts, 672 golden tests, self-update intel loop, monitoring daemon, CI gates. Multilingual GEO, pSEO, CWV, penalty recovery.
- agent-skills
- ai-seo
- answer-engine-optimization
- backlinks
TranslatedSay "¥35, not spicy, no ice" → one answer + a copyable order card. Official calculate-price only. Zero-dependency MCP skill. McDonald's ordering Skill.
An NLP library for Uralic languages such as Finnish, Skolt Sami, Moksha and so on. Also supporting some non-Uralic languages such as Spanish, French, Arabic, Swedish, Norwegian, Russian and English. LLMs, FSTs and More!
- nlp-library
- uralic-languages
- finnish
- sami
Self-hosted challenge board for sweet open hackathons 🐝
- time-tracking
- collaborative
- organizing
- open-hackathon