Instructions to use google/gemma-4-12B-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-4-12B-it with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("google/gemma-4-12B-it") model = AutoModelForImageTextToText.from_pretrained("google/gemma-4-12B-it") - Notebooks
- Google Colab
- Kaggle
Add AIME 2026 evaluation result
#6
by SaylorTwift HF Staff - opened
- .eval_results/aime_2026.yaml +9 -0
- config.json +1 -1
- model.safetensors +1 -1
.eval_results/aime_2026.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: MathArena/aime_2026
|
| 3 |
+
task_id: MathArena/aime_2026
|
| 4 |
+
value: 77.5
|
| 5 |
+
date: '2026-05-23'
|
| 6 |
+
notes: No tools
|
| 7 |
+
source:
|
| 8 |
+
url: https://huggingface.co/google/gemma-4-12B-it
|
| 9 |
+
name: Model Card
|
config.json
CHANGED
|
@@ -106,7 +106,7 @@
|
|
| 106 |
"sliding_attention",
|
| 107 |
"full_attention"
|
| 108 |
],
|
| 109 |
-
"max_position_embeddings":
|
| 110 |
"model_type": "gemma4_unified_text",
|
| 111 |
"moe_intermediate_size": null,
|
| 112 |
"num_attention_heads": 16,
|
|
|
|
| 106 |
"sliding_attention",
|
| 107 |
"full_attention"
|
| 108 |
],
|
| 109 |
+
"max_position_embeddings": 131072,
|
| 110 |
"model_type": "gemma4_unified_text",
|
| 111 |
"moe_intermediate_size": null,
|
| 112 |
"num_attention_heads": 16,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 23919549408
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:366b79fc7e2ea81106d45e2b3ca10e144925f93dd9d456396692825ddb7bb788
|
| 3 |
size 23919549408
|