event

Model Training Announcement

3 items · started 2026-10-04 · closed 2026-10-08

  1. I couldn't find a concrete answer anywhere, do you just distill the instruct model back? If that is the case, what is a quality european language question set to turn it back into a chatbot/agentic, can a model at that size even be agentic?

  2. Meet Bev. She is a decision model (the Jev / Nimble kind: you give her a situation and a question, she gives a probability for each answer), fine-tuned on Qwen3.5-9B to pick the worst answer on purpose.

  3. llm.vhdl Full-fabric VHDL LLM inference engine. Runs Qwen3.5-class transformer inference (9B on a single card, 27B targeted across two) entirely in FPGA fabric: INT4 streaming matvec, Gated DeltaNet, gated attention, and a transformer sequ…

← all threads