World Wire

In this tutorial, we implement an end-to-end supervised fine-tuning pipeline for the XYZ-Aquila-SFT dataset, Hugging Face Transformers, PyTorch, and PEFT. We stream and inspect the dataset, parse multi-turn tool-use trajectories, extract structured tool calls, analyze corpus characteristics, and preserve embedded reasoning and observation patterns. We then convert tool schemas between message-embedded and structured formats, render Qwen-compatible ChatML with assistant-only loss masking, prepare a custom PyTorch dataset and collator, and fine-tune Qwen3-0.6B with LoRA. Finally, we evaluate tool-call prediction before and after training and export both the transformed dataset and corpus statistics for further experimentation. Copy Code Copied Use a different Browser import os, sys, subprocess CFG = dict( REPO = "XYZAILab/XYZ-Aquila-SFT", LANG = "en", N_STREAM = 400, N_EVAL = 40, MODEL_ID = "Qwen/...

Z.ai just released GLM-5.3 . GLM-5.3 runs on the same 743B base model as GLM-5.2 . Every reported gain comes from scaled post-training: more task environments, more environment types, longer training. The results land in two places. Coding jumps most on the longest-horizon benchmarks, with Terminal-Bench 3.0 moving from 4.6 to 28.3. Cybersecurity moved further than Z.ai says it expected, with CyberGym reaching 84.5%. Weights are not public yet. Is It Deployable? 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. Which companies can move now : Startups and mid-market engineering orgs can adopt it today via the Coding Plan or API. Enterprises with data-residency or vendor-review rules should wait for weights. Security vendors and MSSPs get the most signal, and the most policy exposure. Industries : Developer too...

Cactus Compute has released Needle 2 , an open 45M-parameter model for tool calling, device use, and structured extraction. The entire model ships as a single 14MB binary that runs a full session in about 28MB of RAM. Weights are trained and deployed at CQ2-bit using Cactus Quants, and the model is sealed inside the company’s own C++ engine, so there is no runtime to install and no download at inference time. Reported decode throughput is 500 tokens/sec on a Raspberry Pi 5, 400–1,500 tokens/sec on Meta Quest 3S and Apple Vision Pro, and 300–700 tokens/sec on sub-$200 phones. The design premise is narrow and stated plainly by the team: mapping a messy sentence onto a typed function signature needs no world knowledge and no open-ended prose. That framing is why 45M parameters are enough here, and why the model targets hardware with no GPU and no NPU. Is it deployable? Yes, Needle 2 ships as prebuilt binaries and a static library for macOS, Linux (x86-64, ARM64, ARMv7, RIS...