Real browser automation with local GLiNER2 inference and open weights. Work in progress. Contributions welcome.
-
Updated
Sep 18, 2026 - Python
Real browser automation with local GLiNER2 inference and open weights. Work in progress. Contributions welcome.
Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks
MODA: open fashion retrieval benchmark and models by Hopit AI. MODA (203M, open source), MODA Pro Lite (213M, open weights), MODA Pro (hosted). Full-corpus benchmarks vs FashionSigLIP, SigLIP-SO400M and ZooClaw — one harness, losses shown. #1 open model on LookBench.
WicaraLLM is our Indonesian Small Language Model (56M parameters), built from scratch and trained on a 1.3B-token Indonesian corpus. Engineered to run efficiently on a single laptop GPU with just 6 GB of VRAM, it combines GQA, RoPE, SwiGLU, and RMSNorm, with supervised fine-tuning for conversational capabilities
Companion code for the Manning book 'LLM Customization and Fine-Tuning.' Adapt open-weights LLMs end to end: prompting and RAG, LoRA/QLoRA, full SFT, distillation, and DPO/RLHF alignment.
One embedding space for text, image, video, audio, thermal, motion, and touch. Open weights, self-hostable.
Self-hosted, Jev-compatible decision-model API — one /v1/systemone endpoint, open weights (Laya, kev), one Docker image per engine.
Wald-Q4B: open-weight 4B decision model. Calibrated probability for every option, Jev-compatible /v1/systemone API, self-hosted. Weights on Hugging Face.
Three small 4B language models for local decisions in English, Turkish and German. Jev-compatible API, per-option probabilities and CPU GGUF builds.
Open-weight only, video-aware podcast dubbing with ASR alignment, diarization, LLM translation, and voice-cloned TTS. Local inference.
A real engineering language model running fully offline on an $8-class ESP32-S3 — open weights, native C, real-silicon benchmarks.
Did the agent actually finish? Inspectable GLiNER2.5-Decide fine-tuning on task completion and evidence spans.
Redrob Image: open-weight text-to-image model by Redrob. Free to use, free for commercial use (Apache-2.0).
Open-weight decision scorer: a probability for every candidate answer. Research preview.
每日自动更新的大模型排行榜(LLM Leaderboard):聚合 LMArena 人类盲测偏好与 OpenRouter 定价,含综合榜、按预算选型榜、价格榜、长上下文榜、开源权重榜 5 个维度。
Antalia 1: an open Turkish text-to-speech model (CrossFlow flow-matching, 24 kHz). Development discontinued; released in full.
Park and restore model KV caches for local AI agents. Open-weight models, native Hermes integration, and portable backend routing.
Typed decisions from one encoder pass. Open weights, Apache 2.0.
MODA_NER: open fashion attribute extraction — three-track benchmark suite and models by Hopit AI. Companion to hopit-ai/Moda.
VerQen: an open decision model. State in, decision out, in about 5 ms. Weights, training pipeline and the ZDS-1 benchmark harness.
To associate your repository with the open-weights topic, visit your repo's landing page and select "manage topics."