ModelPrésentéExterne

Qwen Mlp

This model detects 4 emotion states (Boredom, Engagement, Confusion, Frustration) from educational videos.

Sourcehuggingface.co/mapotofu40/qwen-mlp/tree/4845d75a02e314016d070a626984e52c98b7bde4

TypeOtherModèle de baseQwen/Qwen2.5-7B-InstructVersionMlp Boredom bestCClasse

Source du modèle

Type: Other
Taille du fichier: 22,5 MB
Modèle de base: Qwen/Qwen2.5-7B-Instruct
Version: vMlp Boredom best
Mis à jour: 24 oct. 2026
Source: Hugging Face

Description de la source

DAiSEE Emotion Detection Model

This model detects 4 emotion states (Boredom, Engagement, Confusion, Frustration) from educational videos.

Architecture

Stage 1: Qwen2.5-VL-7B-Instruct (embedding extraction)
Stage 2: MLP classifiers (4 separate models)

Usage

Via Inference Endpoint

import requests
import base64

# Encode video
with open("student_video.avi", "rb") as f:
    video_b64 = base64.b64encode(f.read()).decode()

# Send request
response = requests.post(
    "https://YOUR-ENDPOINT.aws.endpoints.huggingface.cloud",
    headers={"Authorization": f"Bearer {YOUR_HF_TOKEN}"},
    json={"inputs": video_b64}
)

predictions = response.json()
print(predictions)

Sources

1 source

Hugging FacePrincipalVersion 4845d75a02e314016d070a626984e52c98b7bde4

huggingface.co/mapotofu40/qwen-mlp/tree/4845d75a02e314016d070a626984e52c98b7bde4

Vérifié 24 oct.

Download files

Artefacts du modèle

4 artefacts

classifiers/mlp_Boredom_best.pth

pth · 22,5 MB · SHA-256 f28bdf950119…49cd · Hugging Face

Download file

classifiers/mlp_Confusion_best.pth

pth · 22,5 MB · SHA-256 84a944d8374b…ccb7 · Hugging Face

Download file

classifiers/mlp_Engagement_best.pth

pth · 22,5 MB · SHA-256 30f6d4ba31c7…cd34 · Hugging Face

Download file

classifiers/mlp_Frustration_best.pth

pth · 22,5 MB · SHA-256 c453f23c03bf…522f · Hugging Face

Download file

Extraits de sources

2 extraits

Readme6 aoûthuggingface.co/mapotofu40/qwen-mlp

--- license: apache-2.0 tags: - video-classification - emotion-detection - education - qwen2.5-vl library_name: transformers base_model: - Qwen/Qwen2.5-7B-Instruct --- # DAiSEE Emotion Detection Model This model detects 4 emotion states (Boredom, Engagement, Confusion, Frustration) from educational videos. ## Architecture - **Stage 1**: Qwen2.5-VL-7B-Instruct (embedding extraction) - **Stage 2**: MLP classifiers (4 separate models) ## Usage ### Via Inference Endpoint ```python import requests import base64 # Encode video with open("student_video.avi", "rb") as f: video_b64 = base64.b64encode(f.read()).decode() # Send request response = requests.post( "https://YOUR-ENDPOINT.aws.endpoints.huggingface.cloud", headers={"Authorization": f"Bearer {YOUR_HF_TOKEN}"}, json={"inputs": video_b64} ) predictions = response.json() print(predictions)

Note6 aoûthuggingface.co/mapotofu40/qwen-mlp

Source context: 0 downloads · 1 likes · Pipeline video-classification · Library transformers · Repo mapotofu40/qwen-mlp