Take a look at MCP : Agent Skill, Claude Code, GenAI Model Context Protocol. Projects include travel agents. aiflx.xyz/courses/mcp-agent-… #AD #MCP

Explore AI Agents & Agentic AI with Hugging Face and LangChain. Build agents that interact with APIs. aiflx.xyz/courses/ai-agents-… #AD #AIAgents

Consider Gen AI Course with Ollama, RAG, LangChain and LangGraph. Work through RAG code examples using FAISS. aiflx.xyz/courses/gen-ai-cou… #AD #RAG

LLMs, RAG, MCP, LangGraph & Multi-Agent Systems is worth a look. Build customer support agents through hands-on projects. aiflx.xyz/courses/llms-rag-m… #AD #AIAgents

Try Agentic AI with LangGraph, CrewAI & AutoGen. Use Python to build applications that generate and debug code. aiflx.xyz/courses/agentic-ai… #AD #Python

Take a look at Agentic AI & LLM: Build AI Agents with ChatGPT, Ollama & RAG. Projects include research assistants. aiflx.xyz/courses/agentic-ai… #AD #AIAgents

Explore Agentic AI, Generative AI, LLMs, RAG & MCP. Build document analysis systems with Python. aiflx.xyz/courses/agentic-ai… #AD #Python

DeepSeek just open sourced its high-performance, large-scale inference framework DeepInfer in Apache-2.0 license. github.com/deepseek-ai/DeepI… Supported features: - Optimized kernels, model and sampler runtime - Parallelism: Attention DP / balanced CP, MoE EP + EPLB - DSpark and confidence-scheduled verification - SWA bounded replay - Asynchronous scheduling (zero-overhead batch scheduler) - Batch-invariant inference - Deterministic sampling - Structured output

Gemini 4 Argon built a 3D periodic table synced to Tom Lehrer’s song, “The Elements.” Created in @Antigravity, it animates orbiting electrons, atomic data, and light spectra.

Indra OCR 1.1 is out now! - 1M param main OCR model, 44 pages/s on CPU - Within 4 points of 3.4B param DeepSeek OCR 2 on OmniParseBench - 15x faster than Tesseract, and more accurate - 80+ languages, plus handwriting

Cloudflare open-sourced the security audit skill that seeded its own vulnerability hunting harness. Your coding agent can now run it on your code. How it works, in 6 phases: → maps your codebase → hunts for bugs area by area so nothing gets skipped → sends every finding to a fresh agent that didn't find it, to confirm it's real → writes structured results → verifies each record again, independently → writes the final report You get a findings file split into confirmed, needs validation and rejected, so you fix the real problems first. Install: npx skills add github.com/cloudflare/securi… --skill security-audit Then open your agent in your project and type: "security audit this codebase" MIT licensed, 31.3K stars.

We plugged Google Research’s Harness² into JEV 1.14. Zero weights touched, yet driving massive gains on vision benchmarks round after round. Under the hood, the system: ⚡️ Rewrites its own prompts 🛠️ Builds its own tools 🧠 Distills its own experience JEV-Harness² repo drops soon. Stay tuned.

MiniMax M3.1 Flash: Space Performance + Bunny Speed 🚀🐰 Yes, Space Bunny - which has topped global leaderboards with 200T+ tokens - was an earlier version of M3.1 Flash. 💰Redefining the performance economics of agentic AI. M3.1 Flash achieves frontier-level intelligence across key tasks such as Cowork (Automation-Bench: 62%; ALE: 30%), Coding (DeepSWE: 74%) and Visual Reasoning (BabyVision: 91%), at 1/3 the cost of M3 and 3x the speed. API pricing (flat rate): $0.15 / $0.60 per 1M input/output tokens, with cache reads at $0.015 / 1M tokens. Model weights will arrive on Oct 23. API: platform.minimax.io M Plan: minimax.io/m-plan MiniMax Code for desktop: agent.minimax.io/download

I have been fine-tuning LLMs for over 3 years now. Here are 5 LLM fine-tuning techniques, explained with visuals: Traditional fine‑tuning is impractical for LLMs (billions of params; 100s of GB). Since this kind of compute isn't accessible to everyone, parameter-efficient fine-tuning techniques (PEFT) were built. Before we go into details of each technique, here's some background that will help you better understand these techniques: LLM weights are matrices of numbers adjusted during fine-tuning. Most PEFT techniques involve finding a lower-rank adaptation of these matrices, a smaller-dimensional matrix that can still represent the information stored in the original. Now with a basic understanding of the rank of a matrix, we're in a good position to understand the different fine-tuning techniques. (refer to the image below for a visual explanation of each technique) 1) LoRA - Add two low-rank trainable matrices, A and B, alongside the weight matrices. - Instead of fine-tuning W, adjust the updates in these low-rank matrices. Even for the largest LLMs, LoRA matrices take up a few MBs of memory. 2) LoRA-FA While LoRA significantly decreases the total trainable parameters, it requires substantial activation memory to update the low-rank weights. LoRA-FA (FA stands for Frozen-A) freezes matrix A and only updates matrix B. 3) VeRA - In LoRA, low-rank matrices A and B are unique for each layer. - In VeRA, A and B are frozen, random, and shared across all layers. - Instead, it learns layer-specific scaling VECTORS (b and d) instead. 4) Delta-LoRA - It tunes the matrix W as well, but not in the traditional way. - Here, the difference (or delta) between the product of matrices A and B in two consecutive training steps is added to W. 5) LoRA+ - In LoRA, both matrices A and B are updated with the same learning rate. - Authors of LoRA+ found that setting a higher learning rate for matrix B results in better convergence. ____ Find me → @_avichawla Every day, I share tutorials and insights on DS, ML, LLMs, and RAGs.

DeepSeek V4.1-Flash-1017 can now run locally! 🐳 We made 1-bit retain ~88.2% accuracy while shrinking size from 508GB to 250GB (−52%). Run on a 128GB+ RAM device. V4.1 Flash 1017 is the strongest open model to date Guide: unsloth.ai/docs/models/deeps… GGUF: huggingface.co/unsloth/DeepS…

We launched OSS Scanner, which gives critical open source projects free, periodic vulnerability scans from our strongest models. Each finding includes a proof-of-concept, and a patch where possible. red.anthropic.com/oss-scanne…

Turn notebook experiments into managed model workflows. Track runs with MLflow, version models in Model Registry, and deploy them as REST APIs. trk.udemy.com/c/6457882/3227… #AD #MLOps #MLflow

Aloha!🌺 Meet Ornith-1.5-122B: No Tradeoff Between Strong and Fast Stronger. Faster. Leaner. Ornith-1.5-122B delivers frontier-level capabilities with exceptional inference efficiency. With superior instruction following, stronger task decomposition, and deeper understanding of real-world workflows, it achieves state-of-the-art performance among open-source models of comparable size, while running on a single NVIDIA DGX card!! Open weights under the MIT license. Coding ✅SWE-bench Verified: 0.845 ✅TB2.1: 0.813 ✅CyberGym: 0.800 ✅NL2Repo: 0.512 Agentic ✅HLE: 0.446 ✅BrowseComp: 0.785 ✅MCP-Atlas: 0.746 ✅Toolathlon: 0.708 🤗Hugging Face: huggingface.co/ornith-ai/Orn… We can’t wait to see what you build with Ornith-1.5-122B.

🚀 Introducing DeepInfer, our in-house inference framework, now fully open source! Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable. 🔗 github.com/deepseek-ai/DeepI… 1/4

Here's a course to explore: Generative Pre-trained Transformers (GPT). Experiment with text generation in hands-on Python labs. aiflx.xyz/courses/generative… #AD #NLP