Status: superseded. Research artifact, not a production candidate. Canonical model: scbe-coding-agent-vtc-qwen15-v1-gguf.

Polly r8 - Qwen2.5-Coder-1.5B (merged)

Full-weight merge. Facts below are from MERGE_INFO.txt in this repo.

  • Base: Qwen/Qwen2.5-Coder-1.5B-Instruct
  • Adapter: training/runs/local_1.5b_r8_20260415T202900/checkpoint-500
  • Round: r8 - 137K coding examples + tokenizer + spiral seal
  • Method: merge_and_unload (LoRA baked into base weights)

Important

The Kaggle 0.5B adapter at polly-r8-qwen-0.5b is a different base model. The two cannot be averaged or merged together.

Not published here

No eval numbers are included in this repo, so none are claimed. Treat this as a training artifact from round r8, not a benchmarked release.

Downloads last month
9
Safetensors
Model size
2B params
Tensor type
BF16
·
F16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support