---
license: apache-2.0
base_model: Qwen/Qwen2.5-14B-Instruct
library_name: transformers
pipeline_tag: text-generation
tags:
- geometry-dash
- gguf
- llama-cpp
- ollama
- tool-use
- geode
- qwen2.5
language:
- en
---

# EditorAI v4 — 14B GD Level Designer (EAS-native)

The flagship EditorAI model. Fine-tune of **Qwen/Qwen2.5-14B-Instruct** trained directly on the EAS (EditorAI Script) output format.

| | v3 (7B) | **v4 (14B)** |
|---|---|---|
| Base model | Qwen2.5-7B-Instruct | **Qwen2.5-14B-Instruct** |
| Native context | 32 K | **32 K** |
| Q4_K_M size | 4.46 GB | **8.4 GB** |
| Q5_K_M size | — | 9.8 GB |
| Output format | EAS + JSON fallback | **EAS-native** (trained on EAS verbs directly) |
| Training data | 3,700 mixed | 4,173 mixed (level-gen rows pre-converted to EAS w/ auto FLOOR / SPIKE-TRAIN / PILLAR detection) |

## Files

- `editorai-v4-Q4_K_M.gguf` (8.4 GB) — ship target, recommended for ≥12 GB GPUs
- `editorai-v4-Q5_K_M.gguf` (9.8 GB) — quality bump if you have 16 GB+
- `Modelfile.v4` — Ollama Modelfile, 32K ctx, Qwen2.5 tool template

## Quick start

```bash
ollama pull entity12208/editorai:v4-14b
ollama create entity12208/editorai:v4-14b -f Modelfile.v4   # alternative
./llama-server -m editorai-v4-Q4_K_M.gguf -c 32768 --jinja  # llama.cpp
```

## Speed (Q4_K_M)

- RTX 3060 12 GB / 4060 Ti 16 GB: ~30–40 t/s
- RTX 4070 / 3090: ~50–70 t/s
- RTX 4090: ~80–120 t/s
- Apple M3 Max (Metal): ~25–35 t/s

## Training

- QLoRA 4-bit NF4, rank 32, alpha 64, lr 2e-4 cosine, adamw_8bit
- H100 80 GB (Lightning.ai), ~1h training (260 steps × 14.6 s/step, 2 epochs)
- Gradient checkpointing on, max_len 1024, batch 4 × grad_accum 8 (effective 32)
- 4,173 rows: 2,473 EAS-native level-gen (parsed from 150 real .gmd files with smart structural macro detection) + 1,200 multi-turn tool-use + 500 Alpaca
- System prompt at training time mirrors the mod's runtime system prompt

## License

Apache-2.0, inherited from the base model.