mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-12-20 05:40:34 +08:00
[data] Fix bugs of use_audio_in_video in Qwen2.5 Omni (#7638)
* cache _mm_inputs * nit * support for use_audio_in_video * remove cache * fix data * Update mllm_video_audio_demo.json
This commit is contained in:
57
data/mllm_video_audio_demo.json
Normal file
57
data/mllm_video_audio_demo.json
Normal file
@@ -0,0 +1,57 @@
|
||||
[
|
||||
{
|
||||
"messages": [
|
||||
{
|
||||
"content": "<video><audio>What is the video describing?",
|
||||
"role": "user"
|
||||
},
|
||||
{
|
||||
"content": "A girl who is drawing a picture of a guitar and feel nervous.",
|
||||
"role": "assistant"
|
||||
}
|
||||
],
|
||||
"videos": [
|
||||
"mllm_demo_data/4.mp4"
|
||||
],
|
||||
"audios": [
|
||||
"mllm_demo_data/4.mp3"
|
||||
]
|
||||
},
|
||||
{
|
||||
"messages": [
|
||||
{
|
||||
"content": "<video><audio>What does this girl say?",
|
||||
"role": "user"
|
||||
},
|
||||
{
|
||||
"content": "She says: 'Hello! Take a look at what am I drawing!'",
|
||||
"role": "assistant"
|
||||
}
|
||||
],
|
||||
"videos": [
|
||||
"mllm_demo_data/4.mp4"
|
||||
],
|
||||
"audios": [
|
||||
"mllm_demo_data/4.mp3"
|
||||
]
|
||||
},
|
||||
{
|
||||
"messages": [
|
||||
{
|
||||
"content": "<video><audio>What is this girl drawing with?",
|
||||
"role": "user"
|
||||
},
|
||||
{
|
||||
"content": "She is drawing with an iPad.",
|
||||
"role": "assistant"
|
||||
}
|
||||
],
|
||||
"videos": [
|
||||
"mllm_demo_data/4.mp4"
|
||||
],
|
||||
"audios": [
|
||||
"mllm_demo_data/4.mp3"
|
||||
]
|
||||
}
|
||||
|
||||
]
|
||||
Reference in New Issue
Block a user