Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- checkpoint
|
| 7 |
+
- training-artifact
|
| 8 |
+
---
|
| 9 |
+
# DeepBrainz-R1-0.6B-16K-ckpt
|
| 10 |
+
|
| 11 |
+
⚠️ **Checkpoint Repository — Not an Inference-Ready Model**
|
| 12 |
+
|
| 13 |
+
This repository contains **raw training checkpoints** produced during the
|
| 14 |
+
DeepBrainz-R1 model development process.
|
| 15 |
+
|
| 16 |
+
These files are intended for:
|
| 17 |
+
- Training lineage and reproducibility
|
| 18 |
+
- Research inspection
|
| 19 |
+
- Internal experimentation
|
| 20 |
+
- Conversion into finalized inference artifacts
|
| 21 |
+
|
| 22 |
+
---
|
| 23 |
+
|
| 24 |
+
## Important Notes
|
| 25 |
+
|
| 26 |
+
- ❌ This repository is **NOT** intended for direct use with
|
| 27 |
+
`AutoModelForCausalLM.from_pretrained`
|
| 28 |
+
- ❌ Weights may be **sharded** and require merging
|
| 29 |
+
- ❌ Inference configuration may be incomplete
|
| 30 |
+
- ❌ No guarantees are provided regarding inference behavior
|
| 31 |
+
|
| 32 |
+
---
|
| 33 |
+
|
| 34 |
+
## For Inference / Usage
|
| 35 |
+
|
| 36 |
+
Please use a **finalized DeepBrainz-R1 model**.
|
| 37 |
+
Checkpoint repositories are not intended for direct consumption.
|
| 38 |
+
|
| 39 |
+
---
|
| 40 |
+
|
| 41 |
+
## License
|
| 42 |
+
|
| 43 |
+
Apache 2.0
|
| 44 |
+
|
| 45 |
+
---
|
| 46 |
+
|
| 47 |
+
## About DeepBrainz
|
| 48 |
+
|
| 49 |
+
DeepBrainz builds reasoning-first AI systems focused on efficiency, structure,
|
| 50 |
+
and real-world problem solving.
|