Modelpublic

EditorAI-Geode/editorai-1p5b-v2

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face

0likes20downloads

Model Card

EditorAI v2 — 1.5B GD Level Designer with Tool Use

The first practical EditorAI model. Fine-tune of Qwen/Qwen2.5-1.5B-Instruct for the EditorAI Geode mod.

	v2
Base model	Qwen2.5-1.5B-Instruct
Context	8 K
Q4KM size	941 MB
Training	QLoRA 4-bit, 2 epochs, 3,700-row mixed dataset
Tool use	works (with mod fallback parser)
Format	JSON

Files

—editorai-v2-Q4_K_M.gguf (941 MB) — primary ship target
—editorai-v2-fp16.gguf (2.9 GB) — full-precision
—Modelfile.v2 — Ollama Modelfile with tool-capable Qwen2.5 template

Quick start

bash

# Pull from registry:
ollama pull entity12208/editorai:v2

# Or build locally:
ollama create entity12208/editorai:v2 -f Modelfile.v2

Speed

—GTX 1050 4 GB: ~21 t/s
—RTX 3050 6 GB: ~50 t/s
—RTX 4090: ~150+ t/s

Note

v2 emits JSON levels. The companion mod (≥v2.2.0) accepts JSON and includes a parser fallback that handles small format quirks. For new installs prefer [v3](../editorai-7b-v3) or [v4](../editorai-14b-v4) — they emit the more compact EAS format which is what the mod prefers.

License

Apache-2.0, inherited from the base model.