Changes between Version 22 and Version 23 of expansion/gw16168

Timestamp:

08/13/2026 10:31:43 PM (23 hours ago)

Author:

Ryan Erb

Comment:

add more examples

expansion/gw16168

@@ -14 +14 @@
 The GW16168 needs the following:
  1. Proper cooling - A 5V fansink is mounted on the GW16168 and this needs to be connected to the fan header on the GW16FM1-C FSA adapter. 
- 1. Proper Power - The GW16168 can pull a lot of power, such as 12W. This requires a special M-Key adapter from Gateworks for Gateworks SBCs, which is the GW16FM1-C (GW16FM0-C is the basic M-Key adapter which doesn't provide enough power). 
+ 1. Proper Power - The GW16168 can pull a lot of power, such as 12W. This requires a special M-Key adapter from Gateworks for Gateworks SBCs, which is the GW16FM1-C which also has a 5V fan header (GW16FM0-C is the basic M-Key adapter which doesn't provide enough power or fan header). 
+ 1. Proper Software - The drivers and software required for this card are detailed on this page. Note, using the Gateworks SBC is recommended for development. The GW11062 ai development kit comes with drivers and software pre-loaded. 
 
 == Terminology
@@ -996 +997 @@
 Now, the demos are installed in the /root/ara2 directory. 
 
-To run a demo, see the examples above, noting the .py file will be in the respective directory. 
+To run a demo, use the run command in the ara2 directory shown in the example below:
+{{{
+root@catalina:~/# cd ara2
+root@catalina:~/ara2# ./run
+Usage: ./run [image-detect|vision-webapp|chat|webchat|webvlm]
+root@catalina:~/ara2# ./run chat
+[Config] 'Qwen2.5-7B-Instruct' is already set as enabled.
+[Service] Waiting for 'Qwen2.5-7B-Instruct' to finish loading on Ara NPU (this can take 2-3 minutes)...
+
+[Service] AAF Connector is ready and endpoint is active!
+
+--- Gateworks AI LLM Session (Model: Qwen2.5-7B-Instruct) ---
+Type 'exit' to stop.
+
+You: what is a fast animal
+AI: A fast animal is one that can move very quickly, often covering long distances in a short amount of time. Some of the fastest animals include:
+
+1. **Cheetah (Acinonyx jubatus)**: Known for its incredible speed, the cheetah can reach up to 70-75 miles per hour (112-120 kilometers per hour) in short bursts.
+
+2. **Pronghorn Antelope (Antilocapra americana)**: This North American mammal can run at speeds of up to 60 miles per hour (97 kilometers per hour).
+
+3. **Gazelle (various species)**: Gazelles are known for their agility and can run at speeds of up to 50 miles per hour (80 kilometers per hour).
+
+4. **Cassowary (Casuarius casuarius)**: Although primarily a bird, the cassowary can run at speeds of up to 31 miles per hour (50 kilometers per hour) and is one of the fastest birds on land.
+
+5. **Cheetah's cousin, the African Wild Dog (Lycaon pictus)**: These dogs can run at speeds of up to 40-45 miles per hour (64-72 kilometers per hour).
+
+6. **Greyhound (Canis familiaris)**: While not as fast as the cheetah, greyhounds can reach speeds of up to 45 miles per hour (72 kilometers per hour) in short bursts.
+
+7. **Pronghorn Antelope's relative, the Springbok (Antidorcas marsupialis)**: This African antelope can run at speeds of up to 50 miles per hour (80 kilometers per hour).
+
+These animals have evolved to run fast for various reasons, such as escaping predators, catching prey, or covering large distances efficiently.
+
+--- Stats ---
+Time taken: 91.78 seconds
+Throughput: 2.59 tokens/sec
+-------------
+
+You: 
+
+
+}}}
+
+All of the demos can also be seen the examples above on this page, noting the .py file will be in the respective directory. 
 
 For example: