Belle-VLM-Base / config.json
beyoru's picture
Upload Belle-VLM (epoch-based training)
ec93f53 verified
{
"architectures": [
"LlavaQwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"dtype": "bfloat16",
"eos_token_id": 151645,
"freeze_mm_mlp_adapter": false,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 1024,
"image_aspect_ratio": "pad",
"image_grid_pinpoints": null,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 40960,
"max_window_layers": 28,
"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_384",
"model_type": "llava_qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"tokenizer_model_max_length": 4096,
"tokenizer_padding_side": "right",
"transformers_version": "4.57.1",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mm_proj": true,
"use_sliding_window": false,
"vocab_size": 151936,
"auto_map": {
"AutoConfig": "configuration_llava_qwen.LlavaQwen3Config",
"AutoModelForCausalLM": "modeling_llava_qwen.LlavaQwen3ForCausalLM"
}
}