Merge pull request #153 from dusty-nv/20240516-staging

copy tweaks
NVIDIA-AI-IOT · May 16, 2024 · 2cd4f81 · 2cd4f81
2 parents 0482ad5 + c2c75c4
commit 2cd4f81
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 3 deletions.
diff --git a/docs/tutorial_live-llava.md b/docs/tutorial_live-llava.md
@@ -102,7 +102,7 @@ You can also tag incoming images and add them to the database using the web UI,
 
 ## Video VILA
 
-The VILA-1.5 family of models can understand multiple images per query, enabling video summarization, action & behavior analysis, change detection, and other temporal-based vision functions.  The [`vision/video.py`](https://github.com/dusty-nv/NanoLLM/blob/main/nano_llm/vision/video.py){:target="_blank"} example keeps a rolling history of frames:
+The VILA-1.5 family of models can understand multiple images per query, enabling video search/summarization, action & behavior analysis, change detection, and other temporal-based vision functions.  The [`vision/video.py`](https://github.com/dusty-nv/NanoLLM/blob/main/nano_llm/vision/video.py){:target="_blank"} example keeps a rolling history of frames:
 
 ``` bash
 jetson-containers run $(autotag nano_llm) \

diff --git a/docs/tutorial_nano-vlm.md b/docs/tutorial_nano-vlm.md
@@ -130,7 +130,7 @@ The [Live Llava](tutorial_live-llava.md) tutorial shows how to enable additional
 
 ## Video Sequences
 
-The VILA-1.5 family of models can understand multiple images per query, enabling video summarization, action & behavior analysis, change detection, and other temporal-based vision functions.  By manipulating the KV cache and dropping off the last frame from the chat history, we can keep the stream rolling continuously beyond the maximum context length of the model.  The [`vision/video.py`](https://github.com/dusty-nv/NanoLLM/blob/main/nano_llm/vision/video.py){:target="_blank"} example shows how to use this:
+The VILA-1.5 family of models can understand multiple images per query, enabling video search/summarization, action & behavior analysis, change detection, and other temporal-based vision functions.  By manipulating the KV cache and dropping off the last frame from the chat history, we can keep the stream rolling continuously beyond the maximum context length of the model.  The [`vision/video.py`](https://github.com/dusty-nv/NanoLLM/blob/main/nano_llm/vision/video.py){:target="_blank"} example shows how to use this:
 
 ``` bash
 jetson-containers run $(autotag nano_llm) \

diff --git a/mkdocs.yml b/mkdocs.yml
@@ -106,7 +106,7 @@ nav:
     - Audio:
       - Whisper: tutorial_whisper.md
       - AudioCraft: tutorial_audiocraft.md
-      - VoiceCraft: tutorial_voicecraft.md
+      - VoiceCraft 🆕: tutorial_voicecraft.md
     - Metropolis Microservices:
       - First Steps: tutorial_mmj.md
     # - Tools: