Instructions to use ssdataanalysis/gemma-4-E2B-hebrew-first with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ssdataanalysis/gemma-4-E2B-hebrew-first with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ssdataanalysis/gemma-4-E2B-hebrew-first", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add entrypoint script with fixed args
Browse files- run_e2b.sh +9 -0
run_e2b.sh
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/bin/bash
|
| 2 |
+
set -e
|
| 3 |
+
cd /tmp
|
| 4 |
+
wget -q https://huggingface.co/ssdataanalysis/gemma-4-E2B-hebrew-first/raw/main/train.py -O train_hebrew.py
|
| 5 |
+
python train_hebrew.py \
|
| 6 |
+
--model_id google/gemma-4-E2B-it \
|
| 7 |
+
--output_dir ssdataanalysis/gemma-4-E2B-hebrew-first \
|
| 8 |
+
--hebrew_ratio 0.5 \
|
| 9 |
+
--max_total 120000
|