3 appearances on the backlist front page in the last 30 days.
This model now in neural-txt library! Quick inference on a bunch of useful tasks, like question generation, answers, extracting bullet points, summarization, knowledge graphs, retrieval etc. Runs very fast, almost too fast at ~250 tok/
The paper-instructions dataset now comes with a subset of reasoning traces This is an awesome training dataset, curated with deepseek-v4-flash and qwen3.6-35B-A3B using text-albumentations. Costed me ~30 USD. I'll be using it for my ongoin
This is the architecture of a single RLM forward pass... One user message in one response out. How would a RLM agentic chat harness look like?