Restore metadata.yaml
Browse filesRestores the file removed by the 13:49 sync. The AI Portal needs it to ingest this model; without it the model fails on the next re-ingest. Identical to the version at b840f3a - unchanged filename, size and provenance fields. Worth adding to the local copy the sync mirrors from, so it is not removed again.
- metadata.yaml +20 -0
metadata.yaml
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
schema_version: 1.0.0
|
| 2 |
+
report_type: llm-generative
|
| 3 |
+
task_type: text-generation
|
| 4 |
+
title: Gemma-4-E2B 8da4w — ExecuTorch
|
| 5 |
+
id: Arm/gemma-4-e2b-text-executorch
|
| 6 |
+
base_model_id: google/gemma-4-E2B
|
| 7 |
+
vendor: Google
|
| 8 |
+
base_model_url: https://huggingface.co/google/gemma-4-E2B
|
| 9 |
+
profile: Arm-Optimized
|
| 10 |
+
weight_dtype: int4
|
| 11 |
+
model_size_mb: 2563.959
|
| 12 |
+
format: executorch
|
| 13 |
+
filename: gemma4_e2b_text_8da4w_emb4.pte
|
| 14 |
+
quantization:
|
| 15 |
+
method: PTQ-dynamic
|
| 16 |
+
variant: 8da4w
|
| 17 |
+
weight_bits: 4
|
| 18 |
+
activation_bits: 8
|
| 19 |
+
mode: dynamic
|
| 20 |
+
weight_granularity: per-group
|