diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index c9e13957c..6c7e248bf 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -26,6 +26,11 @@ jobs:
             pytorch: 2.5.1
             axolotl_extras:
             is_latest: true
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.6.0
+            axolotl_extras:
     runs-on: axolotl-gpu-runner
     steps:
       - name: Checkout
diff --git a/.nojekyll b/.nojekyll
index 228f83be3..b496fe423 100644
--- a/.nojekyll
+++ b/.nojekyll
@@ -1 +1 @@
-a169bae6
\ No newline at end of file
+347765d0
\ No newline at end of file
diff --git a/docs/dataset-formats/index.html b/docs/dataset-formats/index.html
index 886ea17d7..109efaffd 100644
--- a/docs/dataset-formats/index.html
+++ b/docs/dataset-formats/index.html
@@ -399,7 +399,7 @@ Description
 </tr>
 </thead>
 <tbody class="list">
-<tr data-index="0" data-listing-file-modified-sort="1738765455897" data-listing-reading-time-sort="1" data-listing-word-count-sort="92" data-listing-title-sort="Pre-training" data-listing-filename-sort="pretraining.qmd">
+<tr data-index="0" data-listing-file-modified-sort="1738931346554" data-listing-reading-time-sort="1" data-listing-word-count-sort="92" data-listing-title-sort="Pre-training" data-listing-filename-sort="pretraining.qmd">
 <td>
 <a href="../../docs/dataset-formats/pretraining.html" class="title listing-title">Pre-training</a>
 </td>
@@ -407,7 +407,7 @@ Description
 <span class="listing-description">Data format for a pre-training completion task.</span>
 </td>
 </tr>
-<tr data-index="1" data-listing-file-modified-sort="1738765455897" data-listing-reading-time-sort="2" data-listing-word-count-sort="308" data-listing-title-sort="Instruction Tuning" data-listing-filename-sort="inst_tune.qmd">
+<tr data-index="1" data-listing-file-modified-sort="1738931346554" data-listing-reading-time-sort="2" data-listing-word-count-sort="308" data-listing-title-sort="Instruction Tuning" data-listing-filename-sort="inst_tune.qmd">
 <td>
 <a href="../../docs/dataset-formats/inst_tune.html" class="title listing-title">Instruction Tuning</a>
 </td>
@@ -415,7 +415,7 @@ Description
 <span class="listing-description">Instruction tuning formats for supervised fine-tuning.</span>
 </td>
 </tr>
-<tr data-index="2" data-listing-file-modified-sort="1738765455897" data-listing-reading-time-sort="4" data-listing-word-count-sort="625" data-listing-title-sort="Conversation" data-listing-filename-sort="conversation.qmd">
+<tr data-index="2" data-listing-file-modified-sort="1738931346554" data-listing-reading-time-sort="4" data-listing-word-count-sort="625" data-listing-title-sort="Conversation" data-listing-filename-sort="conversation.qmd">
 <td>
 <a href="../../docs/dataset-formats/conversation.html" class="title listing-title">Conversation</a>
 </td>
@@ -423,7 +423,7 @@ Description
 <span class="listing-description">Conversation format for supervised fine-tuning.</span>
 </td>
 </tr>
-<tr data-index="3" data-listing-file-modified-sort="1738765455897" data-listing-reading-time-sort="1" data-listing-word-count-sort="85" data-listing-title-sort="Stepwise Supervised Format" data-listing-filename-sort="stepwise_supervised.qmd">
+<tr data-index="3" data-listing-file-modified-sort="1738931346554" data-listing-reading-time-sort="1" data-listing-word-count-sort="85" data-listing-title-sort="Stepwise Supervised Format" data-listing-filename-sort="stepwise_supervised.qmd">
 <td>
 <a href="../../docs/dataset-formats/stepwise_supervised.html" class="title listing-title">Stepwise Supervised Format</a>
 </td>
@@ -431,7 +431,7 @@ Description
 <span class="listing-description">Format for datasets with stepwise completions and labels</span>
 </td>
 </tr>
-<tr data-index="4" data-listing-file-modified-sort="1738765455897" data-listing-reading-time-sort="1" data-listing-word-count-sort="3" data-listing-title-sort="Template-Free" data-listing-filename-sort="template_free.qmd">
+<tr data-index="4" data-listing-file-modified-sort="1738931346554" data-listing-reading-time-sort="1" data-listing-word-count-sort="3" data-listing-title-sort="Template-Free" data-listing-filename-sort="template_free.qmd">
 <td>
 <a href="../../docs/dataset-formats/template_free.html" class="title listing-title">Template-Free</a>
 </td>
@@ -439,7 +439,7 @@ Description
 <span class="listing-description">Construct prompts without a template.</span>
 </td>
 </tr>
-<tr data-index="5" data-listing-file-modified-sort="1738765455897" data-listing-reading-time-sort="1" data-listing-word-count-sort="92" data-listing-title-sort="Custom Pre-Tokenized Dataset" data-listing-filename-sort="tokenized.qmd">
+<tr data-index="5" data-listing-file-modified-sort="1738931346554" data-listing-reading-time-sort="1" data-listing-word-count-sort="92" data-listing-title-sort="Custom Pre-Tokenized Dataset" data-listing-filename-sort="tokenized.qmd">
 <td>
 <a href="../../docs/dataset-formats/tokenized.html" class="title listing-title">Custom Pre-Tokenized Dataset</a>
 </td>
diff --git a/sitemap.xml b/sitemap.xml
index 8e79cc5f2..d6d39f3dd 100644
--- a/sitemap.xml
+++ b/sitemap.xml
@@ -2,154 +2,154 @@
 <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/FAQS.html</loc>
-    <lastmod>2025-02-05T14:24:15.895Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.553Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/conversation.html</loc>
-    <lastmod>2025-02-05T14:24:15.897Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.554Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/index.html</loc>
-    <lastmod>2025-02-05T14:24:15.897Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.554Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/inst_tune.html</loc>
-    <lastmod>2025-02-05T14:24:15.897Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.554Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/template_free.html</loc>
-    <lastmod>2025-02-05T14:24:15.897Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.554Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/amd_hpc.html</loc>
-    <lastmod>2025-02-05T14:24:15.896Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.554Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/nccl.html</loc>
-    <lastmod>2025-02-05T14:24:15.900Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.557Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/installation.html</loc>
-    <lastmod>2025-02-05T14:24:15.900Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.557Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/config.html</loc>
-    <lastmod>2025-02-05T14:24:15.897Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.554Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/lr_groups.html</loc>
-    <lastmod>2025-02-05T14:24:15.900Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.557Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/debugging.html</loc>
-    <lastmod>2025-02-05T14:24:15.897Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.554Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset_preprocessing.html</loc>
-    <lastmod>2025-02-05T14:24:15.897Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.554Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/getting-started.html</loc>
-    <lastmod>2025-02-05T14:24:15.897Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.554Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/multi-node.html</loc>
-    <lastmod>2025-02-05T14:24:15.900Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.557Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/multimodal.html</loc>
-    <lastmod>2025-02-05T14:24:15.900Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.557Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/mac.html</loc>
-    <lastmod>2025-02-05T14:24:15.900Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.557Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/examples/colab-notebooks/colab-axolotl-example.html</loc>
-    <lastmod>2025-02-05T14:24:15.901Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.558Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/TODO.html</loc>
-    <lastmod>2025-02-05T14:24:15.896Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.553Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html</loc>
-    <lastmod>2025-02-05T14:24:15.915Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.572Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/src/axolotl/integrations/kd/topk_logprob/LICENSE.html</loc>
-    <lastmod>2025-02-05T14:24:15.916Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.573Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/src/axolotl/integrations/LICENSE.html</loc>
-    <lastmod>2025-02-05T14:24:15.915Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.572Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/index.html</loc>
-    <lastmod>2025-02-05T14:24:15.912Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.569Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/multi-gpu.html</loc>
-    <lastmod>2025-02-05T14:24:15.900Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.557Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/unsloth.html</loc>
-    <lastmod>2025-02-05T14:24:15.900Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.558Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/inference.html</loc>
-    <lastmod>2025-02-05T14:24:15.900Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.557Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/batch_vs_grad.html</loc>
-    <lastmod>2025-02-05T14:24:15.897Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.554Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/faq.html</loc>
-    <lastmod>2025-02-05T14:24:15.897Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.554Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/ray-integration.html</loc>
-    <lastmod>2025-02-05T14:24:15.900Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.557Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/fsdp_qlora.html</loc>
-    <lastmod>2025-02-05T14:24:15.897Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.554Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/rlhf.html</loc>
-    <lastmod>2025-02-05T14:24:15.900Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.558Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/multipack.html</loc>
-    <lastmod>2025-02-05T14:24:15.900Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.557Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/input_output.html</loc>
-    <lastmod>2025-02-05T14:24:15.900Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.557Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/reward_modelling.html</loc>
-    <lastmod>2025-02-05T14:24:15.900Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.557Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/torchao.html</loc>
-    <lastmod>2025-02-05T14:24:15.900Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.558Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/tokenized.html</loc>
-    <lastmod>2025-02-05T14:24:15.897Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.554Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/pretraining.html</loc>
-    <lastmod>2025-02-05T14:24:15.897Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.554Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/stepwise_supervised.html</loc>
-    <lastmod>2025-02-05T14:24:15.897Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.554Z</lastmod>
   </url>
   <url>
     <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/cli.html</loc>
-    <lastmod>2025-02-05T14:24:15.897Z</lastmod>
+    <lastmod>2025-02-07T12:29:06.554Z</lastmod>
   </url>
 </urlset>