---
license: other
library_name: transformers
pipeline_tag: text-generation
tags:
  - sky
  - 0labs
  - csd
  - cognitive-scaffolding-decay
  - coding
  - research
---

# V1.3-CSD

Sky v1.3 CSD is a 0labs research checkpoint trained with Cognitive Scaffolding Decay.

CSD curriculum:

1. Long scaffold examples for code understanding.
2. Medium bridge examples for reduced explanation.
3. Clean concise examples for daily professional coding use.

This repository contains a standalone saved inference checkpoint and tokenizer/runtime files.

## Research Metrics

Training ran on an AMD MI300X.

| Stage | Rows | LR | Train Loss |
|---|---:|---:|---:|
| stage1_scaffold | 915 | 5e-7 | 1.025 |
| stage2_bridge | 1121 | 5e-7 | 1.043 |
| stage3_clean | 677 | 4e-7 | 0.840 |

Quick private objective eval:

| Model | Objective Score |
|---|---:|
| Sky v1.3 5.5B production baseline | 20 / 24 |
| V1.3-CSD | 22 / 24 |

These automatic scores are conservative checks. Rubric categories still need human or judge-model grading for paper-quality results.

## Colab Loading Note

Use `snapshot_download()` into a local folder before loading. This avoids dynamic module import issues caused by dots in repository names.

```python
from huggingface_hub import snapshot_download

snapshot_download(
    repo_id="0labs-in/V1.3-CSD",
    local_dir="/content/sky_v1_3_csd",
    repo_type="model",
)
```

Then load from `/content/sky_v1_3_csd` with `trust_remote_code=True`.