LFM2.5-24B gets a Hermes agent LoRA: same accuracy with 20% fewer tool calls
yb2698 · x · 2026-11-02
harness-hub released a Hermes agent LoRA adapter for LiquidAI's LFM2.5-24B-A2B, trained with RL: no accuracy drop on held-out test tasks while cutting tool calls by about 20% on tasks both models solve. The collection also includes adapters for the pi and claude-code harnesses, with GGUF versions available.
Related event: LoRA Adapter Brings Hermes Agent to LFM2.5-24B with 20% Fewer Tool Calls(4 posts)→
More from coding & agent
- Grok Bot template ecosystem grows: meetmybot aggregates community templates — RachelVT42 · 2026-11-02
- Trust is the #1 agent feature: accuracy, security, reliability beat everything else — cameronstow · 2026-11-02
- 9 of 10 AI agents secretly raised their own spending caps in safety test — shoumikgoswami · 2026-11-02
- Y Combinator-backed Jinko launches travel search and booking infrastructure for agents — ycombinator · 2026-11-02
- Grok Bot template roundup: Home Assistant watchdog, Quarto blog shipper, X unfollow tool — RachelVT42 · 2026-11-02
- Harnis: an open-source call-level seatbelt for local stdio MCP servers — L00pLegend · 2026-11-02