Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
Auditing Preference Biases and Fine-Tuning Language Models with Direct Preference Optimization on Anthropic HH-RLHF Using TRL and LoRA
33+ min ago (648+ words) This tutorial provides an end-to-end workflow for fine-tuning language models using Direct Preference Optimization (DPO). We demonstrate how to audit the Anthropic HH-RLHF dataset for structural and length-based biases, implement a robust training pipeline using TRL and LoRA, and evaluate…...
NVIDIA Releases TensorRT Model Connect in Public Preview: Hugging Face Checkpoint to Native C++ Inference in Two Commands
1+ day, 11+ hour ago (420+ words) MarkTechPost NVIDIA has released TensorRT Model Connect (TRTMC) in public preview, an open-source project that takes a supported Hugging Face or local checkpoint to end-to-end TensorRT inference in two commands. There is no intermediate ONNX export step. The build produces…...
Cartesia Ships Sonic-3.6: A Streaming TTS Model That Now Leads Both Artificial Analysis Speech Arenas
1+ day, 22+ hour ago (178+ words) YES, it is available in beta and as a hosted API. Not as self-hosted weights. Sonic is a closed, commercial model. There are no open weights and no Hugging Face repo. You rent it. Sonic runs on state space models…...
Developing an End-to-End Document Intelligence Pipeline with docTR for OCR, Layout Analysis, KIE, Benchmarking, and Searchable PDFs
2+ day, 15+ hour ago (637+ words) Develop a complete document intelligence pipeline with docTR, integrating OCR, layout analysis, and KIE for production-oriented extraction and searchable PDF creation. The post Developing an End-to-End Document Intelligence Pipeline with docTR for OCR, Layout Analysis, KIE, Benchmarking, and Searchable PDFs…...
Fine-Tuning Tool-Calling LLMs: A Complete Guide Using XYZ-Aquila-SFT and Qwen3
4+ day, 21+ hour ago (574+ words) Implement an end-to-end fine-tuning pipeline for tool-calling language models. This tutorial covers parsing trajectories, structured tool-call extraction, Qwen-compatible ChatML rendering, and efficient LoRA adaptation using PyTorch. The post Fine-Tuning Tool-Calling LLMs: A Complete Guide Using XYZ-Aquila-SFT and Qwen3 appeared first on…...
Z.ai Ships GLM-5.3 Without Retraining the Base Model: Better at Complex Coding and Long-Horizon Tasks
6+ day, 1+ hour ago (212+ words) Partially, GLM-5.3 is live through the Z.ai API, the GLM Coding Plan, and ZCode. Weights are not out. Z.ai says it will publish them roughly two weeks after launch, once safety evaluation and hardening finish. Terminal-Bench 3.0 moves from 4.6 to 28.3 against…...
Meet Needle 2: An Open 45M-Parameter Tool-Calling Model That Ships as a 14MB Binary and Runs a Full Session in 28MB of RAM
6+ day, 3+ hour ago (393+ words) Yes, Needle 2 ships as prebuilt binaries and a static library for macOS, Linux (x86-64, ARM64, ARMv7, RISC-V, MIPS32el), Windows, Android, iOS/watchOS/tvOS, and WebAssembly. Cactus says Pebble already runs Needle locally in the Index 01 app for offline voice actions. Needle 2 uses what Cactus…...
Create a Reasoning-Focused LLM: A Practical Guide to Streaming, Curating, and Fine-Tuning the SupraLabs Reasoning Corpus
6+ day, 6+ hour ago (554+ words) MarkTechPost In this tutorial, we build an end-to-end workflow for working with the SupraLabs reasoning corpus. We stream a representative subset directly from the Hugging Face Hub, inspect its source distribution, token-length patterns, task composition, and reasoning-to-answer ratios, and then…...
Liquid AI Releases LFM2.5-VL-3B: A 3B Vision-Language Model That Reads Screens, Grounds Objects, and Calls Tools On-Device
6+ day, 17+ hour ago (236+ words) Yes, the checkpoint ships in four formats: native, GGUF, ONNX, and MLX. Day-one runtimes include llama.cpp, MLX, vLLM, SGLang, and ONNX. It fits in roughly 3 GB of memory. LFM2.5-VL-3B extends LFM2-VL-3B along four axes. The language backbone is LFM2.5-2.6B. The vision tower is…...
NVIDIA AI Releases Nemotron 3.5 Lightning: A 30B Open MoE with 3B Active Parameters, and NeMo Switchyard Model Router
1+ week, 1+ day ago (278+ words) Yes. Nemotron 3.5 Lightning is generally available under the permissive OpenMDW-1.1 license, with open weights, training data, and recipes. NVIDIA states the model is ready for commercial use. Long-running agents spend most of their time on high-volume execution. Tool calls, result…...