Mini-Coder-v2 (15B)
Mini-Coder-v2 is build on top of upscaled Qwen3.5-9B model with Continual Pretraining (CPT), we feed ~34k high-quality curated luau raw codes to improves the luau coding tasks capability.
This model present a upscaled of Qwen3.5-9B from only 32 layers to 56 layers for a deeper reasoning capability! This model parameters is 15.07B with Vision, 14.67B without Vision.
Uploaded finetuned model
- Developed by: khtsly
- License: apache-2.0
- Finetuned from model : khtsly/Mini-Coder-v2-noft
This qwen3_5 model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 159