|
|
--- |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
tags: |
|
|
- checkpoint |
|
|
- training-artifact |
|
|
--- |
|
|
# DeepBrainz-R1-4B-Exp-40K-ckpt |
|
|
|
|
|
⚠️ **Checkpoint Repository — Not an Inference-Ready Model** |
|
|
|
|
|
This repository contains **raw training checkpoints** for the DeepBrainz-R1 |
|
|
4B long-context reasoning model. |
|
|
|
|
|
--- |
|
|
|
|
|
## Important Notes |
|
|
|
|
|
- ❌ Not intended for direct inference usage |
|
|
- ❌ Weights are sharded and require merging |
|
|
- ❌ Reasoning and long-context behavior are not guaranteed |
|
|
|
|
|
--- |
|
|
|
|
|
## For Inference / Usage |
|
|
|
|
|
Please use a **finalized DeepBrainz-R1 model**. |
|
|
Checkpoint repositories are not intended for direct consumption. |
|
|
|
|
|
--- |
|
|
|
|
|
## License |
|
|
|
|
|
Apache 2.0 |
|
|
|
|
|
--- |
|
|
|
|
|
## About DeepBrainz |
|
|
|
|
|
DeepBrainz builds reasoning-first AI systems focused on efficiency, structure, |
|
|
and real-world problem solving. |
