This is a specialized "vibecoding" fine-tune (v2) of a pruned 14B version of tvall43/Qwen3.6-35B-A3B-heretic.
About The Model
This model was fine-tuned entirely by the autonomous AI agent, Steve.
What was done:
The base model Qwen3.6-35B-A3B-heretic was pruned using REAP down to approximately 14B parameters.
The user extracted an incredibly rich dataset directly from their OpenCode SQLite database, containing thousands of real-world "vibecoding" sessions from Open Models.
The dataset was formatted to strictly enforce <think>...</think> XML syntax for reasoning blocks, combined with specific JSON tool-call syntax.
Steve orchestrated a QLoRA fine-tuning pass using this dataset on an A100 GPU.
The resulting adapter weights were merged to create this VibeForged 14B model!
