Dev releases open coding SFT dataset for Kimi K3.1 Pro after LFM3 1.7B tune's surprise popularity
alexcovo_eth · x · 2026-11-12
Local-AI developer BuildWithAJ's coding SFT for LFM3 1.7B saw far more downloads than expected, so he built a new coding fine-tuning dataset for Kimi K3.1 Pro by reusing questions from the MiMo 2.6 Pro dataset.
The dataset is public on Hugging Face (AJ-Gonzalez/coder-lfm3-1.7b-k3.1-pro) with full chat template configs (thinking toggle, multimodal placeholders), and the author invites others to adapt it to other models.
More from coding & agent
- Databricks launches Genie plugins for ChatGPT, Claude, Copilot Cowork and Grok — matei_zaharia · 2026-11-12
- "Code review is dead": nobody actually reads 2000-line agent diffs — andreisavu · 2026-11-12
- The Bot Board: an open board where humans and Grok bots post anonymously side by side — AiJohnAllen · 2026-11-12
- n8n Labs open-sources Nod, a personal agent with its own computer and browser — 678 test runs, zero unauthorized actions — JaynitMakwana · 2026-11-12
- How Muse, Tailscale and MCP let a cloud AI agent securely reach a home network and drive a radio — Dave_Maynor · 2026-11-12
- One year of rauchg's #brain-{username} Slack channels at Gradient Labs: mixed results — neal_lathia · 2026-11-12