Merge pull request #96 from dusty-nv/20240308-live-llava-2

updated commands
NVIDIA-AI-IOT · Mar 10, 2024 · 14342f1 · 14342f1
2 parents 4252c2b + 48381dd
commit 14342f1
Show file tree

Hide file tree

Showing 2 changed files with 20 additions and 20 deletions.
diff --git a/docs/tutorial_live-llava.md b/docs/tutorial_live-llava.md
@@ -47,12 +47,12 @@ The [VideoQuery](https://github.com/dusty-nv/jetson-containers/blob/master/packa
 
 ```bash
 ./run.sh $(./autotag local_llm) \
-	python3 -m local_llm.agents.video_query --api=mlc --verbose \
-	  --model Efficient-Large-Model/VILA-2.7b \
-	  --max-context-len 768 \
-	  --max-new-tokens 32 \
-	  --video-input /dev/video0 \
-	  --video-output webrtc://@:8554/output
+  python3 -m local_llm.agents.video_query --api=mlc \
+    --model Efficient-Large-Model/VILA-2.7b \
+    --max-context-len 768 \
+    --max-new-tokens 32 \
+    --video-input /dev/video0 \
+    --video-output webrtc://@:8554/output
 ```
 
 <a href="https://youtu.be/dRmAGGuupuE" target="_blank"><img width="49%" style="display: inline;"  src="https://raw.githubusercontent.com/dusty-nv/jetson-containers/docs/docs/images/live_llava_horse.jpg"> <img width="49%" style="display: inline;" src="https://raw.githubusercontent.com/dusty-nv/jetson-containers/docs/docs/images/live_llava_espresso.jpg"></a>
@@ -67,12 +67,12 @@ The example above was running on a live camera, but you can also read and write
 ./run.sh \
   -v /path/to/your/videos:/mount
   $(./autotag local_llm) \
-	python3 -m local_llm.agents.video_query --api=mlc --verbose \
-	  --model Efficient-Large-Model/VILA-2.7b \
-	  --max-new-tokens 32 \
-	  --video-input /mount/my_video.mp4 \
-	  --video-output /mount/output.mp4 \
-	  --prompt "What does the weather look like?"
+    python3 -m local_llm.agents.video_query --api=mlc \
+      --model Efficient-Large-Model/VILA-2.7b \
+      --max-new-tokens 32 \
+      --video-input /mount/my_video.mp4 \
+      --video-output /mount/output.mp4 \
+      --prompt "What does the weather look like?"
 ```
 
 This example processes and pre-recorded video (in MP4, MKV, AVI, FLV formats with H.264/H.265 encoding), but it also can input/output live network streams like [RTP](https://github.com/dusty-nv/jetson-inference/blob/master/docs/aux-streaming.md#rtp), [RTSP](https://github.com/dusty-nv/jetson-inference/blob/master/docs/aux-streaming.md#rtsp), and [WebRTC](https://github.com/dusty-nv/jetson-inference/blob/master/docs/aux-streaming.md#webrtc) using Jetson's hardware-accelerated video codecs.
@@ -85,13 +85,13 @@ To enable this mode, first follow the [**NanoDB tutorial**](tutorial_nanodb.md)
 
 ```bash
 ./run.sh $(./autotag local_llm) \
-	python3 -m local_llm.agents.video_query --api=mlc --verbose \
-	  --model Efficient-Large-Model/VILA-2.7b \
-	  --max-context-len 768 \
-	  --max-new-tokens 32 \
-	  --video-input /dev/video0 \
-	  --video-output webrtc://@:8554/output \
-	  --nanodb /data/nanodb/coco/2017
+  python3 -m local_llm.agents.video_query --api=mlc \
+    --model Efficient-Large-Model/VILA-2.7b \
+    --max-context-len 768 \
+    --max-new-tokens 32 \
+    --video-input /dev/video0 \
+    --video-output webrtc://@:8554/output \
+    --nanodb /data/nanodb/coco/2017
 ```
 
 You can also tag incoming images and add them to the database using the panel in the web UI.

diff --git a/docs/tutorial_nano-vlm.md b/docs/tutorial_nano-vlm.md
@@ -116,7 +116,7 @@ These models can also be used with the [Live Llava](tutorial_live-llava.md) agen
 ``` bash
 ./run.sh $(./autotag local_llm) \
   python3 -m local_llm.agents.video_query --api=mlc \
-    --model NousResearch/Obsidian-3B-V0.5 \
+    --model Efficient-Large-Model/VILA-2.7b \
     --max-context-len 768 \
     --max-new-tokens 32 \
     --video-input /dev/video0 \