Add dedicated Tool Calling README section (#236)

Group tool-calling and function-calling notebooks into a new priority
section placed immediately after GRPO & Reinforcement Learning:

  * FunctionGemma (270M) Tool Calling
  * FunctionGemma (270M) Mobile Actions
  * FunctionGemma (270M) Inference (LMStudio)
  * FunctionGemma (270M) Conversational
  * Qwen2.5 Coder (1.5B) Tool Calling

Routing: a notebook is force-routed to "Tool Calling" when any of the
following hold:

  * classified model_type contains "Tool Calling"
  * filename contains "functiongemma" (FunctionGemma is purpose-built
    for function calling so every variant belongs here, even the ones
    whose subtype in the filename is Mobile-Actions / LMStudio / bare)
  * filename contains "tool_calling" or "tool-calling"

Previously these notebooks fell into the Gemma and Qwen architecture
sections. After this change the Gemma section no longer contains
FunctionGemma rows and the Qwen section no longer contains the
Qwen2.5 Coder Tool Calling row.

Routing precedence in the primary-section decision stays:
  GRPO > Tool Calling > Text Completion / CPT > architecture > Other

Author: danielhanchen

README.md

@@ -74,6 +74,15 @@ Below are Colab notebooks, organized by model. You can also view all [notebooks
 | **(OpenEnv) gpt oss** **(20B)** | 2048 Game | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/OpenEnv_gpt_oss_(20B)_Reinforcement_Learning_2048_Game.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 | **(DGX Spark) gpt oss** **(20B)** | 2048 Game | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/gpt_oss_(20B)_Reinforcement_Learning_2048_Game_DGX_Spark.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 
+### Tool Calling Notebooks
+| Model | Type | Notebook Link |
+| --- | --- | --- |
+| **Qwen2.5 Coder** **(1.5B)** | Tool Calling | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2.5_Coder_(1.5B)-Tool_Calling.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
+| **FunctionGemma** **(270M)** | Tool Calling | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/FunctionGemma_(270M)-Multi-Turn-Tool-Calling.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
+| **FunctionGemma** **(270M)** | Mobile Actions | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/FunctionGemma_(270M)-Mobile-Actions.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
+| **FunctionGemma** **(270M)** | Inference | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/FunctionGemma_(270M)-LMStudio.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
+| **FunctionGemma** **(270M)** | Conversational | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/FunctionGemma_(270M).ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
+
 ### Text-to-Speech (TTS) Notebooks
 | Model | Type | Notebook Link |
 | --- | --- | --- |
@@ -175,8 +184,8 @@ Below are Colab notebooks, organized by model. You can also view all [notebooks
 | **Gemma4** **(E4B)** | Conversational | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(E4B)-Text.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 | **Gemma4** **(E4B)** | Audio | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(E4B)-Audio.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 | **Gemma4** **(E2B)** | Vision | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(E2B)-Vision.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
-| **Gemma4** **(E2B)** | Conversational | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(E2B)-Text.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 | **Gemma4** **(E2B)** | Audio | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(E2B)-Audio.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
+| **Gemma4** **(E2B)** | Conversational | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(E2B)-Text.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 | **Gemma4** **(26B A4B)** | Conversational | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(26B_A4B)-Text.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 | **Gemma4** **(26B A4B)** | Vision | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(26B_A4B)-Vision.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 | **Gemma4** **(31B)** | Vision | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(31B)-Vision.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
@@ -189,10 +198,6 @@ Below are Colab notebooks, organized by model. You can also view all [notebooks
 | **(A100) Gemma3** **(27B)** | Conversational | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma3_(27B)_A100-Conversational.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 | **Gemma3** **(270M)** | Conversational | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma3_(270M).ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 | **Gemma3** **(270M)** |  | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma3_(270M)_Phone_Deployment.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
-| **FunctionGemma** **(270M)** | Tool Calling | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/FunctionGemma_(270M)-Multi-Turn-Tool-Calling.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
-| **FunctionGemma** **(270M)** | Mobile Actions | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/FunctionGemma_(270M)-Mobile-Actions.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
-| **FunctionGemma** **(270M)** | Inference | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/FunctionGemma_(270M)-LMStudio.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
-| **FunctionGemma** **(270M)** | Conversational | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/FunctionGemma_(270M).ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 | **Gemma3N** **(4B)** | Multimodal | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma3N_(4B)-Conversational.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 | **Gemma3N** **(4B)** | Audio | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma3N_(4B)-Audio.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 | **Gemma3N** **(2B)** | Inference | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma3N_(2B)-Inference.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
@@ -284,7 +289,6 @@ Below are Colab notebooks, organized by model. You can also view all [notebooks
 | **Qwen3 MoE**  |  | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen3_MoE.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 | **Qwen3 5** **(2B)** | Vision | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen3_5_(2B)_Vision.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 | **Qwen2.5** **(7B)** | Alpaca | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2.5_(7B)-Alpaca.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
-| **Qwen2.5 Coder** **(1.5B)** | Tool Calling | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2.5_Coder_(1.5B)-Tool_Calling.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 | **Qwen2.5 Coder** **(14B)** | Conversational | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2.5_Coder_(14B)-Conversational.ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 | **Qwen3 Embedding** **(4B)** |  | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen3_Embedding_(4B).ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
 | **Qwen3 Embedding** **(0 6B)** |  | <a href="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen3_Embedding_(0_6B).ipynb" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> |
@@ -346,6 +350,11 @@ Below are Colab notebooks, organized by model. You can also view all [notebooks
 | **Gemma3** **(4B)** | Vision Math | <a href="https://www.kaggle.com/notebooks/welcome?src=https://github.com/unslothai/notebooks/blob/main/nb/Kaggle-Gemma3_(4B)-Vision-GRPO.ipynb&accelerator=nvidiaTeslaT4" target="_blank" rel="noopener noreferrer"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open in Kaggle"></a> |
 | **(A100) gpt oss** **(20B)** | Auto Kernel Creation | <a href="https://www.kaggle.com/notebooks/welcome?src=https://github.com/unslothai/notebooks/blob/main/nb/Kaggle-gpt-oss-(20B)_A100-GRPO.ipynb&accelerator=nvidiaTeslaT4" target="_blank" rel="noopener noreferrer"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open in Kaggle"></a> |
 
+### Tool Calling Notebooks
+| Model | Type | Notebook Link |
+| --- | --- | --- |
+| **Qwen2.5 Coder** **(1.5B)** | Tool Calling | <a href="https://www.kaggle.com/notebooks/welcome?src=https://github.com/unslothai/notebooks/blob/main/nb/Kaggle-Qwen2.5_Coder_(1.5B)-Tool_Calling.ipynb&accelerator=nvidiaTeslaT4" target="_blank" rel="noopener noreferrer"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open in Kaggle"></a> |
+
 ### Text-to-Speech (TTS) Notebooks
 | Model | Type | Notebook Link |
 | --- | --- | --- |
@@ -510,7 +519,6 @@ Below are Colab notebooks, organized by model. You can also view all [notebooks
 | **Qwen2 VL** **(7B)** | Vision | <a href="https://www.kaggle.com/notebooks/welcome?src=https://github.com/unslothai/notebooks/blob/main/nb/Kaggle-Qwen2_VL_(7B)-Vision.ipynb&accelerator=nvidiaTeslaT4" target="_blank" rel="noopener noreferrer"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open in Kaggle"></a> |
 | **Qwen3** **(4B)** | Thinking | <a href="https://www.kaggle.com/notebooks/welcome?src=https://github.com/unslothai/notebooks/blob/main/nb/Kaggle-Qwen3_(4B)-Thinking.ipynb&accelerator=nvidiaTeslaT4" target="_blank" rel="noopener noreferrer"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open in Kaggle"></a> |
 | **Qwen2.5** **(7B)** | Alpaca | <a href="https://www.kaggle.com/notebooks/welcome?src=https://github.com/unslothai/notebooks/blob/main/nb/Kaggle-Qwen2.5_(7B)-Alpaca.ipynb&accelerator=nvidiaTeslaT4" target="_blank" rel="noopener noreferrer"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open in Kaggle"></a> |
-| **Qwen2.5 Coder** **(1.5B)** | Tool Calling | <a href="https://www.kaggle.com/notebooks/welcome?src=https://github.com/unslothai/notebooks/blob/main/nb/Kaggle-Qwen2.5_Coder_(1.5B)-Tool_Calling.ipynb&accelerator=nvidiaTeslaT4" target="_blank" rel="noopener noreferrer"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open in Kaggle"></a> |
 | **Qwen2.5 Coder** **(14B)** | Conversational | <a href="https://www.kaggle.com/notebooks/welcome?src=https://github.com/unslothai/notebooks/blob/main/nb/Kaggle-Qwen2.5_Coder_(14B)-Conversational.ipynb&accelerator=nvidiaTeslaT4" target="_blank" rel="noopener noreferrer"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open in Kaggle"></a> |
 | **Qwen3 Embedding** **(4B)** |  | <a href="https://www.kaggle.com/notebooks/welcome?src=https://github.com/unslothai/notebooks/blob/main/nb/Kaggle-Qwen3_Embedding_(4B).ipynb&accelerator=nvidiaTeslaT4" target="_blank" rel="noopener noreferrer"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open in Kaggle"></a> |
 | **Qwen3 Embedding** **(0 6B)** |  | <a href="https://www.kaggle.com/notebooks/welcome?src=https://github.com/unslothai/notebooks/blob/main/nb/Kaggle-Qwen3_Embedding_(0_6B).ipynb&accelerator=nvidiaTeslaT4" target="_blank" rel="noopener noreferrer"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open in Kaggle"></a> |

update_all_notebooks.py

@@ -3661,6 +3661,7 @@ def update_readme(
     # Priority sections appear first in the README, in this order
     priority_sections = [
         "GRPO & Reinforcement Learning",
+        "Tool Calling",
         "Text-to-Speech (TTS)",
         "Vision (Multimodal)",
         "Embedding",
@@ -3827,12 +3828,25 @@ def update_readme(
             or "-cpt" in basename_lower
             or "_cpt" in basename_lower
         )
+        # Force-route tool-calling notebooks to the dedicated Tool Calling
+        # section. All FunctionGemma notebooks belong here regardless of
+        # their filename subtype (Multi-Turn-Tool-Calling, LMStudio,
+        # Mobile-Actions, etc.) since FunctionGemma is purpose-built for
+        # function calling. Other notebooks match on type or filename.
+        is_tool_calling = (
+            "tool calling" in model_type.lower()
+            or "functiongemma" in basename_lower
+            or "tool_calling" in basename_lower
+            or "tool-calling" in basename_lower
+        )
         # Use the precomputed is_in_grpo_section flag instead of checking
         # model_type here -- by this point the RL classifier may have
         # already renamed model_type to "GSM8K Math", "Wordle", etc. which
         # would no longer start with "GRPO".
         if is_in_grpo_section or is_forced_grpo:
             section_name = 'GRPO & Reinforcement Learning'
+        elif is_tool_calling:
+            section_name = 'Tool Calling'
         elif is_text_completion:
             section_name = _TEXT_COMPLETION_SECTION
         elif architecture and architecture in list_models: