Rajesh Mani Kumar GxLAM — Salesforce’s Large Action ModelIn the ever-evolving landscape of artificial intelligence and machine learning, Large Action Models (LAMs) are advanced large language…3d ago3d ago
Rajesh Mani Kumar GLocal Language Translator using Local Tool LibreTranslateIn today’s increasingly connected world, language barriers can often hinder communication and collaboration across cultures. Traditional…Aug 31Aug 31
Rajesh Mani Kumar GMastering AI Prompt Types: Samples for Your Day-to-Day ActivitiesPrompt: Prompts are instructions or cues given to an AI Large Language Models to generate responses that are relevant and accurate. It may…Aug 25Aug 25
Rajesh Mani Kumar GOpenBMB MiniCPM-V MLLM Tiny & Mighty Multimodal LLMMiniCPM-V 2.6 from Openbmb is built on SigLip-400M and Qwen2–7B with a total of 8B parameters. With many new features like Multi Image…Aug 11Aug 11
Rajesh Mani Kumar GFlux Schnell — the best Open Source AI Art Generator alternative to Midjourney and IdeogreamOpen Source GenAI Text to Image models are nowadays improved a lot. I like to express my gratitude to the communities that are doing a…Aug 3Aug 3
Rajesh Mani Kumar GLlama 3.1 Simple RAG using Embedchain via Local OllamaLlama 3.1- new 128K context length — open source model from Meta with state-of-the-art capabilities in general knowledge, steerability…Jul 28Jul 28
Rajesh Mani Kumar GInstagram Influencer Crew AI Agent Powered by Local LLMsCrew AI Agent, equipped with the latest language models LLaMA3 and LLaVA, is poised to redefine the influencer landscape.Jul 211Jul 211
Rajesh Mani Kumar GBoost Your Productivity with Aider an AI Pair ProgrammerAider helps you as an AI pair programmer with any LLM. Aider works best with GPT-4o & Claude 3.5 Sonnet and any Open Source LLMs too.Jul 13Jul 13
Rajesh Mani Kumar GLocal AI Companion: Voice-Activated and Ready to AssistThink about the possibility of having a personal assistant who is always at your disposal, prepared to chat or respond to your inquiries. A…Jul 6Jul 6
Rajesh Mani Kumar GUnlocking Insights from Images: Microsoft Florence-2 AIVision models are revolutionizing the way we interact with images by bridging the gap between visual information and textual understanding.Jun 30Jun 30