[Model] Ultravox Model: Support v0.5 Release (#12912)

Signed-off-by: Farzad Abdolhosseini <farzad@fixie.ai>

examples/offline_inference/audio_language.py

@@ -24,9 +24,9 @@ question_per_audio_count = {
 # Unless specified, these settings have been tested to work on a single L4.
 
 
-# Ultravox 0.3
+# Ultravox 0.5-1B
 def run_ultravox(question: str, audio_count: int):
-    model_name = "fixie-ai/ultravox-v0_3"
+    model_name = "fixie-ai/ultravox-v0_5-llama-3_2-1b"
 
     tokenizer = AutoTokenizer.from_pretrained(model_name)
     messages = [{

examples/online_serving/openai_chat_completion_client_for_multimodal.py

@@ -12,7 +12,7 @@ vllm serve microsoft/Phi-3.5-vision-instruct --task generate \
     --trust-remote-code --max-model-len 4096 --limit-mm-per-prompt image=2
 
 (audio inference with Ultravox)
-vllm serve fixie-ai/ultravox-v0_3 --max-model-len 4096
+vllm serve fixie-ai/ultravox-v0_5-llama-3_2-1b --max-model-len 4096
 """
 import base64