Update README.md
Browse files
README.md
CHANGED
|
@@ -24,6 +24,8 @@ This repository provides **Model_256_BIT (285M)** — an **ablation model** from
|
|
| 24 |
|
| 25 |
[📚 Paper (Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate)](https://huggingface.co/papers/2507.07129) -
|
| 26 |
|
|
|
|
|
|
|
| 27 |
This checkpoint is designed to test whether a Transformer can learn semantics when the input embedding layer is **frozen** and carries **no linguistic or visual information**, only a stable per-token identifier.
|
| 28 |
|
| 29 |
---
|
|
|
|
| 24 |
|
| 25 |
[📚 Paper (Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate)](https://huggingface.co/papers/2507.07129) -
|
| 26 |
|
| 27 |
+
[📚 Blog Article](https://huggingface.co/blog/Bochkov/emergent-semantics-beyond-token-embeddings)
|
| 28 |
+
|
| 29 |
This checkpoint is designed to test whether a Transformer can learn semantics when the input embedding layer is **frozen** and carries **no linguistic or visual information**, only a stable per-token identifier.
|
| 30 |
|
| 31 |
---
|