Instructions to use google/gemma-4-12B-it-assistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-4-12B-it-assistant with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("google/gemma-4-12B-it-assistant") model = AutoModelForCausalLM.from_pretrained("google/gemma-4-12B-it-assistant", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README
#6
by MaartenGr - opened
README.md
CHANGED
|
@@ -432,7 +432,7 @@ Compared to Gemma 3, the models use standard `system`, `assistant`, and `user` r
|
|
| 432 |
|
| 433 |
### 3. Multi-Turn Conversations
|
| 434 |
|
| 435 |
-
* **No Thinking Content in History**: In multi-turn conversations, the historical model output should only include the final response. Thoughts from previous model turns must *not be added* before the next user turn begins.
|
| 436 |
|
| 437 |
### 4. Modality order
|
| 438 |
|
|
|
|
| 432 |
|
| 433 |
### 3. Multi-Turn Conversations
|
| 434 |
|
| 435 |
+
* **No Thinking Content in History**: In multi-turn conversations, the historical model output should only include the final response. Thoughts from previous model turns must *not be added* before the next user turn begins, with the exception of tool call turns where thinking content should be preserved.
|
| 436 |
|
| 437 |
### 4. Modality order
|
| 438 |
|