| license: apache-2.0 | |
| tags: | |
| - polly | |
| - scbe | |
| - qwen2 | |
| - text-generation | |
| - sft | |
| - merged | |
| - superseded | |
| <!-- scbe-status --> | |
| > **Status: superseded.** Research artifact, not a production candidate. Canonical model: [scbe-coding-agent-vtc-qwen15-v1-gguf](https://hf.co/issdandavis/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](https://hf.co/issdandavis/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. | |