You need to agree to share your Hugging Face information to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
Access is granted manually by the owner. State your name, affiliation and intended use.
Log in or Sign Up to review the conditions and access this model content.
VideoFace-X-LLM — ViT + LLM-LoRA fine-tune (step 3200 of 3406)
InternVideo2.5-Chat-8B fine-tuned on the ExplainFace corpus (Gemini descriptions of CelebV-HQ videos) for the ACCV 2026 paper "When, Where, and Why: Hierarchical Causal Explainability for Video Face Understanding with MLLMs". This is the "Ours (ViT+LLM LoRA)" row of the results table and the model all H-TCC explainability results were computed on.
Contents
- Root: the merged full checkpoint (LoRA folded into the LLM weights,
W += α/r · B·A), loadable withtrust_remote_code=True. lora_adapter/: the trainable-only checkpoint as saved during training (trainable.safetensors: vision encoder, connector and LoRA weights;trainable_config.json).merge_lora_ckpt.py: the script that produced the merged checkpoint from the base model andlora_adapter/.
Training
- Trainable: vision encoder (lr 1e-5) + connector
mlp1(lr 4e-5) + LoRA on the frozen language model (rank 64, α 128, dropout 0.05, targetswqkv, wo, w1, w2, w3, lr 1e-4). - 1 epoch = 3,406 steps over the 27,304-clip identity-independent training split
(
Aak579/CelebV-HQ-identity-split20), micro-batch 1, global batch 8, AdamW, weight decay 0.01, 3 % linear warm-up then cosine decay, gradient clip 1.0, 8–32 frames per clip, seed 42, FSDP full sharding, 2 × NVIDIA L40S. Full args:train_run_config.json. Checkpoints were saved every 400 steps; this is step 3,200.
Test results (6,923-clip identity-independent test split)
| Appearance mA / F1mac | Action mA / F1mac | Emotion video Acc / F1mac | Emotion temporal Acc / F1mac | Deepfake (FF++) Acc / F1mac | AU (DISFA) mA / frame F1 / clip F1 |
|---|---|---|---|---|---|
| 86.36 / 32.87 | 94.80 / 20.82 | 60.57 / 25.68 | 74.84 / 26.81 | 56.32 / 45.80 | 79.2 / 31.6 / 32.2 |
For the JSON tasks the model was decoded with the training-style prompt prefix and a { prefill,
as in the paper's inference scripts.
- Downloads last month
- -
Model tree for Aak579/VideoFace-X-LLM-ViT-LLM-LoRA-3200
Base model
OpenGVLab/InternVideo2_5_Chat_8B