# Clashbot d1-ft-joint-tac decision model by Jyler > Clashbot d1 selects among up to 4 candidate plays from text game states. Read its course-project scope, held-out play-choice results and licence. Updated 2026-11-12 (Australia/Adelaide) ## Quick answers ### What is Clashbot d1-ft-joint-tac by Jyler? [Clashbot d1-ft-joint-tac](): A fine-tune of Liquid AI’s d1-omni-600M for a Clash Royale course project. [Clashbot d1-ft-joint-tac facts]() [Source]() ### Who makes Clashbot d1-ft-joint-tac? [Clashbot d1-ft-joint-tac](): Jyler [Clashbot d1-ft-joint-tac facts]() [Source]() By Jyler · Hugging Face weight package release: 2026-11-09 · OPEN A fine-tune of Liquid AI’s d1-omni-600M for a Clash Royale course project. It reads a text game state and up to four candidate plays, including tactical notes, retrieval and knowledge-graph context. The package selects a play; the surrounding agent uses iPhone Mirroring on a Mac. Intended for research and the course demo in Training Camp or friendly battles. ## Facts - Base: LiquidAI/d1-omni-600M; 587,161,089 stored parameters - Inputs: Text game descriptions and up to 4 candidate plays - Training: 3,641 four-option questions from 197 recorded professional games; splits by video - Access: FP16 weights and bundled custom loader; CPU loading uses FP32 - Licence: LFM Open License v1.0; file included ## Claims and sources - **VENDOR-REPORTED**: The maker reports four-way accuracy 0.507 on 766 test lines from 27 held-out games, against chance 0.25 and a placement prior 0.384. The reported 95% interval is 0.473 to 0.540. FP16 and FP32 choose the same option on 100 check lines. These are offline play-choice results, not a measured live-game win rate. [source]() ## Links - [Source: Card, weights and code]() - [Source: Licence]() ## Related projects No related projects are listed in the registry.