Sublime

Fine-tune 100+ LLMs directly from a UI! LLaMA-Factory lets you train and fine-tune open-source LLMs and VLMs without writing any code. Supports 100+ models, multimodal fine-tuning, PPO, DPO, experiment tracking, and much more! 100% open-source with 50k stars! https://t.co/5bS2xNakeF

GitHub AI Model Playground with Llama 3.1 405B, GPT-4o, Mistral Large, Phi-3 and other opensource models for RAG. (100% free right in GitHub). Plus, deploy these LLMs in production using Azure AI Inference SDK. https://t.co/hUm6CTgufC

Introducing OpenCoder@beta, the Claude Code open source alternative 🌟 Complete Claude Code replacement with similar UI and UX 🌟 Built on top of the @vercel's ai sdk (`streamText` + `useChat`). 💯 code quality 🌟 Works with any @aisdk models (OpenAI, Anthropic, Ollama, Google, OpenRouter etc... See more

We took @karpathy's advice and released MLGym, a gym environment for solving ML tasks. MLGym makes it easy to add new tasks so we hope the OSS community will help us scale it up. https://t.co/rrKC7zvwJd

Fine-tune 100+ LLMs directly from a UI! LLaMA-Factory lets you train and fine-tune open-source LLMs and VLMs without writing any code. Supports 100+ models, multimodal fine-tuning, PPO, DPO, experiment tracking, and much more! 100% open-source, 57k stars! https://t.co/nNqBkBZ3V0