principled-intelligence
/

gemma-4-E2B-it-text-only

Feature Extraction

Model card Files Files and versions

edobobo commited on 17 days ago

Commit

9023a24

·

verified ·

1 Parent(s): 36b4a1f

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -39,9 +39,9 @@ We compared the text-only checkpoint against the original Gemma 4 E2B-it across
 | Metric | Gemma 4 E2B-it | Text-Only | Reduction |
 | --- | --- | --- | --- |
-| VRAM (MiB) | 12,390 | 10,195 | ~18% |
 | Parameters (B) | 5.12 | 4.65 | ~9% |
-| File size (GB) | 9.29 | 10.20 | ~9% |
 > **Note:** The "E" in E2B stands for "effective" parameters. The Gemma 4 E2B architecture uses Per-Layer Embeddings (PLE) to maximize parameter efficiency on-device — the total parameter count is higher than the effective size.
 > The text-only variant removes the vision and audio encoder weights while preserving the full language model, including all PLE parameters.

 | Metric | Gemma 4 E2B-it | Text-Only | Reduction |
 | --- | --- | --- | --- |
+| VRAM (MiB) | 10,504 | 9,596 | ~9% |
 | Parameters (B) | 5.12 | 4.65 | ~9% |
+| File size (GB) | 10.20 | 9.29 | ~9% |
 > **Note:** The "E" in E2B stands for "effective" parameters. The Gemma 4 E2B architecture uses Per-Layer Embeddings (PLE) to maximize parameter efficiency on-device — the total parameter count is higher than the effective size.
 > The text-only variant removes the vision and audio encoder weights while preserving the full language model, including all PLE parameters.