vasanth009's picture
Add MLX fp16 V-JEPA2 ViT-g encoder (from facebook/vjepa2-vitg-fpc64-256)
fa5afa4 verified
Raw
History Blame Contribute Delete
531 Bytes
{
"hidden_size": 1408,
"num_hidden_layers": 40,
"num_attention_heads": 22,
"mlp_ratio": 4.363636363636363,
"patch_size": 16,
"tubelet_size": 2,
"crop_size": 256,
"frames_per_clip": 64,
"in_chans": 3,
"hidden_act": "gelu",
"layer_norm_eps": 1e-06,
"qkv_bias": true,
"pred_hidden_size": 384,
"pred_num_hidden_layers": 12,
"pred_num_attention_heads": 12,
"pred_mlp_ratio": 4.0,
"pred_num_mask_tokens": 10,
"num_pooler_layers": 3,
"num_labels": 174,
"hf_repo": "facebook/vjepa2-vitg-fpc64-256"
}