elizaos/eliza-1-2b-gpt55-scenarios

eliza-1-2b — gpt-5.5-scenarios (experimental)

Experimental fine-tune of google/gemma-4-E2B (eliza-1-2b tier) specialized on the elizaOS agent harness. Trained on trajectories harvested from gpt-5.5 (via the Codex subscription) running the elizaOS scenario / benchmark / e2e suites, so the model leans into our native tool-calling and JSON-decision shapes.

• —Base: google/gemma-4-E2B
• —Method: APOLLO SFT, 1 epoch, on a 2,774-row combined corpus (55% gpt-5.5 scenario trajectories + 45% base eliza-1 SFT corpus). Training data: `elizaos/eliza-1-training-data` (converted/gpt55-scenarios/).
• —Pipeline: elizaOS/eliza PR #11891 (harvest → GEPA → fine-tune).

Files

• —eliza-1-2b-gpt55.q4_k_m.gguf — 3.2 GB, mobile/desktop-deployable. Verified generating coherent text at 157 tok/s on Apple M4 Max (Metal, llama.cpp).
• —eliza-1-2b-gpt55.f16.gguf — 8.6 GB, full-precision source for re-quantizing.

Honest status

Experimental. Light (1-epoch) specialization pass. On a small local benchmark, native-tool-call / JSON structure adherence moved 50% → 62.5% vs the base (directional, tiny sample — a full-split GPU benchmark is future work). Not a gated official eliza-1 release; use as an experimental checkpoint.

llama-cli -m eliza-1-2b-gpt55.q4_k_m.gguf -p "List three things a helpful assistant does:" -n 64