You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Run update_all_notebooks.py after PR #217 Minesweeper merge (#237)
PR #217 added gpt_oss_(20B)_Reinforcement_Learning_GRPO_Minesweeper_Game_BF16.ipynb
but the README regeneration and derivative files were not part of that
merge. Running the script pulls in:
* HuggingFace Course- and Kaggle- sibling notebooks for Minesweeper
(generated by copy_and_update_notebooks from the original_template/
source during normal script runs)
* Regenerated python_scripts/ exports for the three Minesweeper notebooks
* A new README row in the GRPO & Reinforcement Learning section
* Cache entries in scripts/model_created_at.csv for the new HF refs
Script change: detect_rl_task() now recognizes "minesweeper" in markdown
headers or filenames and returns "Minesweeper Game", so the new notebook
renders with Type "Minesweeper Game" instead of the generic "GRPO"
fallback. Slotted alongside 2048 Game and Auto Kernel Creation in the
interleaved non-vLLM bucket.
Copy file name to clipboardExpand all lines: README.md
+4-2Lines changed: 4 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -58,6 +58,7 @@ Below are Colab notebooks, organized by model. You can also view all [notebooks
58
58
|**NeMo Gym Sudoku**| Sudoku | <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/NeMo-Gym-Sudoku.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
59
59
|**NeMo Gym Multi Environment**| Multi Environment | <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/NeMo-Gym-Multi-Environment.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
60
60
|**gpt oss BF16****(20B)**| 2048 Game | <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/gpt_oss_(20B)_Reinforcement_Learning_2048_Game_BF16.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
61
+
|**gpt oss****(20B)**| Minesweeper Game | <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/gpt_oss_(20B)_Reinforcement_Learning_GRPO_Minesweeper_Game_BF16.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
61
62
|**gpt oss****(20B)**| Auto Kernel Creation | <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/gpt_oss_(20B)_GRPO_BF16.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
62
63
|**Llama3****(8B)**| ORPO | <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3_(8B)-ORPO.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
63
64
|**Qwen3 VL****(8B)**| Vision Math | <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen3_VL_(8B)-Vision-GRPO.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
@@ -184,10 +185,10 @@ Below are Colab notebooks, organized by model. You can also view all [notebooks
184
185
|**Gemma4****(E4B)**| Conversational | <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(E4B)-Text.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
185
186
|**Gemma4****(E4B)**| Audio | <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(E4B)-Audio.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
186
187
|**Gemma4****(E2B)**| Vision | <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(E2B)-Vision.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
187
-
|**Gemma4****(E2B)**| Audio | <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(E2B)-Audio.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
188
188
|**Gemma4****(E2B)**| Conversational | <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(E2B)-Text.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
189
-
|**Gemma4****(26B A4B)**|Conversational| <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(26B_A4B)-Text.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
189
+
|**Gemma4****(E2B)**|Audio| <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(E2B)-Audio.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
190
190
|**Gemma4****(26B A4B)**| Vision | <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(26B_A4B)-Vision.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
191
+
|**Gemma4****(26B A4B)**| Conversational | <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(26B_A4B)-Text.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
191
192
|**Gemma4****(31B)**| Vision | <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(31B)-Vision.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
192
193
|**Gemma4****(31B)**| Conversational | <ahref="https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(31B)-Text.ipynb"target="_blank"rel="noopener noreferrer"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a> |
193
194
@@ -340,6 +341,7 @@ Below are Colab notebooks, organized by model. You can also view all [notebooks
340
341
|**DeepSeek R1 0528 Qwen3****(8B)**| DAPO Math + vLLM | <ahref="https://www.kaggle.com/notebooks/welcome?src=https://github.com/unslothai/notebooks/blob/main/nb/Kaggle-DeepSeek_R1_0528_Qwen3_(8B)_GRPO.ipynb&accelerator=nvidiaTeslaT4"target="_blank"rel="noopener noreferrer"><imgsrc="https://kaggle.com/static/images/open-in-kaggle.svg"alt="Open in Kaggle"></a> |
341
342
|**Phi 4****(14B)**| GSM8K Math + vLLM | <ahref="https://www.kaggle.com/notebooks/welcome?src=https://github.com/unslothai/notebooks/blob/main/nb/Kaggle-Phi_4_(14B)-GRPO.ipynb&accelerator=nvidiaTeslaT4"target="_blank"rel="noopener noreferrer"><imgsrc="https://kaggle.com/static/images/open-in-kaggle.svg"alt="Open in Kaggle"></a> |
342
343
|**Qwen3****(4B)**| DAPO Math + vLLM | <ahref="https://www.kaggle.com/notebooks/welcome?src=https://github.com/unslothai/notebooks/blob/main/nb/Kaggle-Qwen3_(4B)-GRPO.ipynb&accelerator=nvidiaTeslaT4"target="_blank"rel="noopener noreferrer"><imgsrc="https://kaggle.com/static/images/open-in-kaggle.svg"alt="Open in Kaggle"></a> |
344
+
|**gpt oss****(20B)**| Minesweeper Game | <ahref="https://www.kaggle.com/notebooks/welcome?src=https://github.com/unslothai/notebooks/blob/main/nb/Kaggle-gpt_oss_(20B)_Reinforcement_Learning_GRPO_Minesweeper_Game_BF16.ipynb&accelerator=nvidiaTeslaT4"target="_blank"rel="noopener noreferrer"><imgsrc="https://kaggle.com/static/images/open-in-kaggle.svg"alt="Open in Kaggle"></a> |
343
345
|**gpt oss****(20B)**| Auto Kernel Creation | <ahref="https://www.kaggle.com/notebooks/welcome?src=https://github.com/unslothai/notebooks/blob/main/nb/Kaggle-gpt_oss_(20B)_GRPO_BF16.ipynb&accelerator=nvidiaTeslaT4"target="_blank"rel="noopener noreferrer"><imgsrc="https://kaggle.com/static/images/open-in-kaggle.svg"alt="Open in Kaggle"></a> |
344
346
|**Llama3****(8B)**| ORPO | <ahref="https://www.kaggle.com/notebooks/welcome?src=https://github.com/unslothai/notebooks/blob/main/nb/Kaggle-Llama3_(8B)-ORPO.ipynb&accelerator=nvidiaTeslaT4"target="_blank"rel="noopener noreferrer"><imgsrc="https://kaggle.com/static/images/open-in-kaggle.svg"alt="Open in Kaggle"></a> |
345
347
|**Qwen3 VL****(8B)**| Vision Math | <ahref="https://www.kaggle.com/notebooks/welcome?src=https://github.com/unslothai/notebooks/blob/main/nb/Kaggle-Qwen3_VL_(8B)-Vision-GRPO.ipynb&accelerator=nvidiaTeslaT4"target="_blank"rel="noopener noreferrer"><imgsrc="https://kaggle.com/static/images/open-in-kaggle.svg"alt="Open in Kaggle"></a> |
0 commit comments