docs: remove trl docs

docs/index.md

@@ -140,12 +140,12 @@ Learn how to set up NeMo Gym and NeMo RL training environments, run tests, prepa
 {bdg-primary}`training` {bdg-secondary}`rl` {bdg-secondary}`grpo` {bdg-secondary}`multi-step`
 :::
 
-:::{grid-item-card} {octicon}`zap;1.5em;sd-mr-1` Unsloth and TRL
-:link: training-unsloth-trl
+:::{grid-item-card} {octicon}`zap;1.5em;sd-mr-1` Unsloth
+:link: training-unsloth
 :link-type: ref
 Fast, memory-efficient fine-tuning for single-step tasks: math, structured outputs, instruction following, reasoning gym and more.
 +++
-{bdg-primary}`training` {bdg-secondary}`unsloth` {bdg-secondary}`trl` {bdg-secondary}`single-step`
+{bdg-primary}`training` {bdg-secondary}`unsloth` {bdg-secondary}`single-step`
 :::
 
 ::::
@@ -211,7 +211,7 @@ tutorials/index.md
 tutorials/creating-resource-server
 tutorials/offline-training-w-rollouts
 tutorials/nemo-rl-grpo/index.md
-tutorials/unsloth-trl-training
+tutorials/unsloth-training
 ```
 
 ```{toctree}

docs/tutorials/index.md

@@ -60,12 +60,12 @@ Learn how to set up NeMo Gym and NeMo RL training environments, run tests, prepa
 {bdg-primary}`training` {bdg-secondary}`rl` {bdg-secondary}`grpo` {bdg-secondary}`multi-step`
 :::
 
-:::{grid-item-card} {octicon}`zap;1.5em;sd-mr-1` Unsloth and TRL
-:link: training-unsloth-trl
+:::{grid-item-card} {octicon}`zap;1.5em;sd-mr-1` Unsloth
+:link: training-unsloth
 :link-type: ref
 Fast, memory-efficient fine-tuning for single-step tasks: math, structured outputs, instruction following, reasoning gym and more.
 +++
-{bdg-primary}`training` {bdg-secondary}`unsloth` {bdg-secondary}`trl` {bdg-secondary}`single-step`
+{bdg-primary}`training` {bdg-secondary}`unsloth` {bdg-secondary}`single-step`
 :::
 
 ::::

docs/tutorials/unsloth-trl-training.md → docs/tutorials/unsloth-training.md

@@ -1,19 +1,16 @@
-(training-unsloth-trl)=
+(training-unsloth)=
 
-# RL Training with Unsloth and TRL
+# RL Training with Unsloth
 
-This tutorial demonstrates how to use [Unsloth](https://github.com/unslothai/unsloth) and [TRL (Transformer Reinforcement Learning)](https://github.com/huggingface/trl) to fine-tune models for single-step tasks with NeMo Gym verifiers and datasets.
+This tutorial demonstrates how to use [Unsloth](https://github.com/unslothai/unsloth) to fine-tune models for single-step tasks with NeMo Gym verifiers and datasets.
 
 **Unsloth** is a fast, memory-efficient library for fine-tuning large language models. It provides optimized implementations that significantly reduce memory usage and training time, making it possible to fine-tune larger models on consumer hardware.
 
-**TRL** is a library from HuggingFace for post-training models using techniques like SFT, GRPO, and DPO. It is built on top of [Transformers](https://github.com/huggingface/transformers) and supports a variety of model architectures and modalities. 
-
-
-Both Unsloth and TRL can be used with NeMo Gym single-step verifiers including math tasks, structured outputs, instruction following, reasoning gym, and more. 
+Unsloth can be used with NeMo Gym single-step verifiers including math tasks, structured outputs, instruction following, reasoning gym, and more. 
 
 :::{card}
 
-**Goal**: Fine-tune a model for single-step tasks using Unsloth and TRL with NeMo Gym verifiers.
+**Goal**: Fine-tune a model for single-step tasks using Unsloth with NeMo Gym verifiers.
 
 ^^^
 
@@ -28,7 +25,7 @@ Both Unsloth and TRL can be used with NeMo Gym single-step verifiers including m
 
 ## Getting Started
 
-Follow this interactive notebook to train your first model with Unsloth or TRL and NeMo Gym:
+Follow this interactive notebook to train your first model with Unsloth and NeMo Gym:
 
 :::{button-link} https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/nemo_gym_sudoku.ipynb
 :color: primary
@@ -37,7 +34,9 @@ Follow this interactive notebook to train your first model with Unsloth or TRL a
 Unsloth GRPO notebook
 :::
 
-> **Note:** This notebook supports **single-step tasks** including math, structured outputs, instruction following, reasoning gym, and more. For multi-step tool calling scenarios, see the {doc}`GRPO with NeMo RL <nemo-rl-grpo/index>` tutorial. A complete multi-step and multi-turn integration with Unsloth and TRL is under construction! 
+Check out [Unsloth's documentation](https://docs.unsloth.ai/models/nemotron-3#reinforcement-learning--nemo-gym) for more details.
+
+> **Note:** This notebook supports **single-step tasks** including math, structured outputs, instruction following, reasoning gym, and more. For multi-step tool calling scenarios, see the {doc}`GRPO with NeMo RL <nemo-rl-grpo/index>` tutorial. A multi-step integration with Unsloth is under construction! 
 
 ---