Update README.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,15 @@ A learnable per-layer scale λ (`post_feedforward_layernorm_2`) gates the routed
|
|
| 19 |
contribution — setting λ=0 exactly recovers the original dense model, which makes
|
| 20 |
λ both a safety knob and a diagnostic tool.
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
| | |
|
| 23 |
|---|---|
|
| 24 |
| Base model | google/gemma4-12b-it |
|
|
|
|
| 19 |
contribution — setting λ=0 exactly recovers the original dense model, which makes
|
| 20 |
λ both a safety knob and a diagnostic tool.
|
| 21 |
|
| 22 |
+
|
| 23 |
+
<a href="https://hfviewer.com/TOTORONG/Solon_MOE_p4?utm_source=huggingface&utm_medium=embedded_model_card&utm_campaign=TOTORONG__Solon_MOE_p4_card&utm_content=embedded_card_open_viewer&from=embedded-model-card" target="_blank" rel="noopener">
|
| 24 |
+
<img
|
| 25 |
+
src="https://hfviewer.com/api/card.svg?source=TOTORONG%2FSolon_MOE_p4&granularity=auto&v=20260516-title-pills-card"
|
| 26 |
+
alt="Architecture graph for TOTORONG/Solon_MOE_p4. Open in hfviewer"
|
| 27 |
+
width="100%"
|
| 28 |
+
/>
|
| 29 |
+
</a>
|
| 30 |
+
|
| 31 |
| | |
|
| 32 |
|---|---|
|
| 33 |
| Base model | google/gemma4-12b-it |
|