FastVLM-0.5B / config.json
pcuenq's picture
pcuenq HF Staff
Explicit vision_config
3bdf25c
raw
history blame
2.05 kB
{
"architectures": [
"LlavaQwen2ForCausalLM"
],
"auto_map": {
"AutoConfig": "llava_qwen.LlavaConfig",
"AutoModelForCausalLM": "llava_qwen.LlavaQwen2ForCausalLM",
"AutoProcessor": "processing_fastvlm.FastVLMProcessor"
},
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 896,
"image_aspect_ratio": "pad",
"image_grid_pinpoints": null,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 32768,
"max_window_layers": 24,
"mm_hidden_size": 3072,
"mm_patch_merge_type": "flat",
"mm_projector_lr": null,
"mm_projector_type": "mlp2x_gelu",
"mm_use_im_patch_token": false,
"mm_use_im_start_end": false,
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -2,
"mm_vision_tower": "mobileclip_l_1024",
"model_type": "llava_qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": true,
"tokenizer_model_max_length": 8192,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.39.3",
"tune_mm_mlp_adapter": false,
"unfreeze_mm_vision_tower": true,
"use_cache": true,
"use_mm_proj": true,
"use_sliding_window": false,
"vision_config": {
"cls_ratio": 2.0,
"down_patch_size": 7,
"down_stride": 2,
"downsamples": [true, true, true, true, true],
"embed_dims": [96, 192, 384, 768, 1536],
"hidden_size": 1024,
"image_size": 1024,
"intermediate_size": 3072,
"layer_scale_init_value": 1e-5,
"layers": [2, 12, 24, 4, 2],
"mlp_ratios": [4, 4, 4, 4, 4],
"num_classes": 1000,
"patch_size": 64,
"pos_embs_shapes": [null, null, null, [7, 7], [7, 7]],
"projection_dim": 768,
"repmixer_kernel_size": 3,
"token_mixers": ["repmixer", "repmixer", "repmixer", "attention", "attention"]
},
"vocab_size": 151936
}