link the published week-in-review article (Geometric Memory FT5)
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ model, 768-d L2-normalized output.
|
|
| 16 |
|
| 17 |
12 layers, 512-d, 8 heads, FFN 2048, 8192 position capacity. **0.53x bert-base.**
|
| 18 |
|
| 19 |
-
> 📄 **Technical companion:** [TECHNICAL.md](https://huggingface.co/AbstractPhil/captionbert-8192-v2/blob/main/TECHNICAL.md) — the full training recipe, per-task tables, geometry gauges, adapter-library numerics, and the laws this family earned.
|
| 20 |
|
| 21 |
```python
|
| 22 |
from transformers import AutoModel, AutoTokenizer
|
|
|
|
| 16 |
|
| 17 |
12 layers, 512-d, 8 heads, FFN 2048, 8192 position capacity. **0.53x bert-base.**
|
| 18 |
|
| 19 |
+
> 📄 **Technical companion:** [TECHNICAL.md](https://huggingface.co/AbstractPhil/captionbert-8192-v2/blob/main/TECHNICAL.md) — the full training recipe, per-task tables, geometry gauges, adapter-library numerics, and the laws this family earned. Week-in-review article: [Geometric Memory FT5 — Agreement, Anchors, Addresses](https://huggingface.co/blog/AbstractPhil/geometric-memory-ft5).
|
| 20 |
|
| 21 |
```python
|
| 22 |
from transformers import AutoModel, AutoTokenizer
|