trained
12 stories and discussions about trained, aggregated from every source we track.
Fine-tunes of Qwen3.5 and Gemma 4 for zero-shot classification - firelex/jeff
Continual learning model trained from scratch on 8GB VRAM laptop with batch-1 stream of data. - volotat/mini-AGI
I trained a small JEPA-style world model on Pokémon Red.
Ask your repo "where is X?" and get the 2–3 files to open. A local model that learns from your git history, for developers and coding agents (CLI + MCP). - andreylukin/where-next
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use. - nomic-ai/gpt4all
Continual learning model trained from scratch on 8GB VRAM laptop with batch-1 stream of data. - volotat/mini-AGI
StarCraft: Brood War AI — a neural network trained by self-play RL. - tscmoo/pluto
VeriLoop E2 is now publicly available: a 27B post-trained model built on Qwen3.8-27B for verifiable code, mathematics, scientific reasoning, and long-horizon agentic problem solving. At the center of E2 is…
A 144M typed-decision model on par with Laya at one third the size, with 1.9x lower latency and 14.2x the requests per second on the same GPU. Paid API, waitlist open.
Xing4.0-29B-A4B is China Telecom's new 29B MoE model trained on Ascend NPUs, benchmarked against Gemma4-26B-A4B and Qwen3.6-35B-A3B.
Tiny chess model. Contribute to skorotkiewicz/chesslm development by creating an account on GitHub.