Update README (#4)

- Update README (d906d4555894900049015fd8e72d11c59c06d170)

README.md

@@ -29,6 +29,7 @@ base_model:
 > * **GGUF** (Q4_0): Ready-to-deploy formats for broad ecosystem compatibility. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B.
 > * **Mobile-optimized** (wNa8o8): A custom schema engineered explicitly for mobile hardware efficiency. It features targeted 2-bit decoding layers, optimized KV caches, and static activations to maximize VRAM savings. Available for Gemma 4 E2B and E4B.
 > * **Compressed Tensors** (w4a16): QAT checkpoints serialized in the compressed-tensors format for native, optimized inference with vLLM. Available for Gemma 4 E2B, E4B, 12B, and 31B. 
+> * **Assistant Compatibility**: When using multi-token prediction (speculative decoding) with an assistant model alongside a QAT target model, the assistant model must also be a QAT checkpoint with the same precision to ensure compatibility.
 
 Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages. 
 
@@ -144,7 +145,7 @@ Once you have everything installed, you can proceed to load the model with the c
 ```python
 from transformers import AutoProcessor, AutoModelForMultimodalLM
 
-MODEL_ID = "google/gemma-4-12B-it"
+MODEL_ID = "google/gemma-4-E2B-it"
 
 # Load model
 processor = AutoProcessor.from_pretrained(MODEL_ID)
@@ -199,7 +200,7 @@ You can then load the model with the code below:
 ```python
 from transformers import AutoProcessor, AutoModelForMultimodalLM
 
-MODEL_ID = "google/gemma-4-12B-it"
+MODEL_ID = "google/gemma-4-E2B-it"
 
 # Load model
 processor = AutoProcessor.from_pretrained(MODEL_ID)
@@ -258,7 +259,7 @@ You can then load the model with the code below:
 ```python
 from transformers import AutoProcessor, AutoModelForMultimodalLM
 
-MODEL_ID = "google/gemma-4-12B-it"
+MODEL_ID = "google/gemma-4-E2B-it"
 
 # Load model
 processor = AutoProcessor.from_pretrained(MODEL_ID)
@@ -316,7 +317,7 @@ You can then load the model with the code below:
 ```python
 from transformers import AutoProcessor, AutoModelForMultimodalLM
 
-MODEL_ID = "google/gemma-4-12B-it"
+MODEL_ID = "google/gemma-4-E2B-it"
 
 # Load model
 processor = AutoProcessor.from_pretrained(MODEL_ID)
@@ -391,7 +392,7 @@ Compared to Gemma 3, the models use standard `system`, `assistant`, and `user` r
 
 ### 3. Multi-Turn Conversations
 
-* **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.
+* **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.
 
 ### 4. Modality order