trl-mcsd / examples /notebooks /README.md
ihbkaiser's picture
Implement MCSD for experimental SDPO
1fa3c6c verified
# Notebooks
This directory contains a collection of Jupyter notebooks that demonstrate how to use the TRL library in different applications.
| Notebook | Description | Open in Colab |
| --- | --- | --- |
| [`grpo_trl_lora_qlora.ipynb`](https://github.com/huggingface/trl/tree/main/examples/notebooks/grpo_trl_lora_qlora.ipynb) | GRPO using QLoRA on free Colab | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_trl_lora_qlora.ipynb) |
| [`grpo_agent.ipynb`](https://github.com/huggingface/trl/tree/main/examples/notebooks/grpo_agent.ipynb) | GRPO for agent training | Not available due to OOM with Colab GPUs |
| [`grpo_rnj_1_instruct.ipynb`](https://github.com/huggingface/trl/tree/main/examples/notebooks/grpo_rnj_1_instruct.ipynb) | GRPO rnj-1-instruct with QLoRA using TRL on Colab to add reasoning capabilities | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_rnj_1_instruct.ipynb) |
| [`sft_ministral3_vl.ipynb`](https://github.com/huggingface/trl/tree/main/examples/notebooks/sft_ministral3_vl.ipynb) | Supervised Fine-Tuning (SFT) Ministral 3 with QLoRA using TRL on free Colab | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_ministral3_vl.ipynb) |
| [`grpo_ministral3_vl.ipynb`](https://github.com/huggingface/trl/tree/main/examples/notebooks/grpo_ministral3_vl.ipynb) | GRPO Ministral 3 with QLoRA using TRL on free Colab | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_ministral3_vl.ipynb) |
| [`sft_nemotron_3.ipynb`](https://github.com/huggingface/trl/tree/main/examples/notebooks/sft_nemotron_3.ipynb) | SFT with LoRA on NVIDIA Nemotron 3 models | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_nemotron_3.ipynb) |
| [`sft_trl_lora_qlora.ipynb`](https://github.com/huggingface/trl/tree/main/examples/notebooks/sft_trl_lora_qlora.ipynb) | Supervised Fine-Tuning (SFT) using QLoRA on free Colab | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_trl_lora_qlora.ipynb) |
| [`sft_qwen_vl.ipynb`](https://github.com/huggingface/trl/tree/main/examples/notebooks/sft_qwen_vl.ipynb) | Supervised Fine-Tuning (SFT) Qwen3-VL with QLoRA using TRL on free Colab | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_qwen_vl.ipynb) |
| [`sft_tool_calling.ipynb`](https://github.com/huggingface/trl/tree/main/examples/notebooks/sft_tool_calling.ipynb) | Teaching tool calling to a model without native tool-calling support using SFT with QLoRA | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_tool_calling.ipynb) |
| [`grpo_qwen3_vl.ipynb`](https://github.com/huggingface/trl/tree/main/examples/notebooks/grpo_qwen3_vl.ipynb) | GRPO Qwen3-VL with QLoRA using TRL on free Colab | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_qwen3_vl.ipynb) |
## OpenEnv Notebooks
These notebooks demonstrate GRPO training with [OpenEnv](https://github.com/meta-pytorch/OpenEnv) environments using `environment_factory`. The BrowserGym notebook uses the lower-level `rollout_func` API instead.
| Notebook | Description | Open in Colab |
| --- | --- | --- |
| [`openenv_wordle_grpo.ipynb`](https://github.com/huggingface/trl/tree/main/examples/notebooks/openenv_wordle_grpo.ipynb) | GRPO to play Wordle on an OpenEnv environment | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/openenv_wordle_grpo.ipynb) |
| [`openenv_sudoku_grpo.ipynb`](https://github.com/huggingface/trl/tree/main/examples/notebooks/openenv_sudoku_grpo.ipynb) | GRPO to play Sudoku on an OpenEnv environment | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/openenv_sudoku_grpo.ipynb) |
| [`grpo_functiongemma_browsergym_openenv.ipynb`](https://github.com/huggingface/trl/tree/main/examples/notebooks/grpo_functiongemma_browsergym_openenv.ipynb) | GRPO on FunctionGemma in the BrowserGym environment | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_functiongemma_browsergym_openenv.ipynb) |