[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:
Kingsley
2025-04-08 18:40:10 +08:00
committed by GitHub
parent 85f95a2883
commit 0935eff188
7 changed files with 83 additions and 8 deletions

View File

@@ -66,6 +66,21 @@
"assistant_tag": "assistant"
}
},
"mllm_video_audio_demo": {
"file_name": "mllm_video_audio_demo.json",
"formatting": "sharegpt",
"columns": {
"messages": "messages",
"videos": "videos",
"audios": "audios"
},
"tags": {
"role_tag": "role",
"content_tag": "content",
"user_tag": "user",
"assistant_tag": "assistant"
}
},
"alpaca_en": {
"hf_hub_url": "llamafactory/alpaca_en",
"ms_hub_url": "llamafactory/alpaca_en",

BIN
data/mllm_demo_data/4.mp3 Normal file

Binary file not shown.

BIN
data/mllm_demo_data/4.mp4 Normal file

Binary file not shown.

View 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"
]
}
]