Apex-large / config.json
aleks-wordcab's picture Ihor's picture
Duplicate from knowledgator/gliclass-v4-9b
8c30622
Raw History Blame Contribute Delete
7.12 kB
{
"architecture_type": "decoder-kv",
"architectures": [
"GLiClassModel"
],
"calibrator_beta_max": 3.0,
"calibrator_dropout": 0.1,
"calibrator_hidden_size": 256,
"calibrator_objective": "mixed",
"calibrator_rank_preserving": true,
"calibrator_use_bias": true,
"class_token_index": 248077,
"class_token_pooling": "first",
"contrastive_loss_coef": 0.0,
"dropout": 0.3,
"dtype": "bfloat16",
"embed_class_token": true,
"encoder_config": {
"_name_or_path": "Qwen/Qwen3.5-9B",
"architectures": [
"Qwen3_5ForConditionalGeneration"
],
"image_token_id": 248056,
"model_type": "qwen3_5",
"text_config": {
"_name_or_path": "",
"architectures": null,
"attention_bias": false,
"attention_dropout": 0.0,
"attn_output_gate": true,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"dtype": "bfloat16",
"eos_token_id": 248044,
"full_attention_interval": 4,
"head_dim": 256,
"hidden_act": "silu",
"hidden_size": 4096,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 12288,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_types": [
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention"
],
"linear_conv_kernel_dim": 4,
"linear_key_head_dim": 128,
"linear_num_key_heads": 16,
"linear_num_value_heads": 32,
"linear_value_head_dim": 128,
"mamba_ssm_dtype": "float32",
"max_position_embeddings": 262144,
"mlp_only_layers": [],
"model_type": "qwen3_5_text",
"mtp_num_hidden_layers": 1,
"mtp_use_dedicated_embeddings": false,
"num_attention_heads": 16,
"num_hidden_layers": 32,
"num_key_value_heads": 4,
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": null,
"partial_rotary_factor": 0.25,
"problem_type": null,
"return_dict": true,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"mrope_interleaved": true,
"mrope_section": [
11,
11,
10
],
"partial_rotary_factor": 0.25,
"rope_theta": 10000000,
"rope_type": "default"
},
"tie_word_embeddings": false,
"use_cache": true,
"vocab_size": 248080
},
"tie_word_embeddings": false,
"video_token_id": 248057,
"vision_config": {
"_name_or_path": "",
"architectures": null,
"chunk_size_feed_forward": 0,
"deepstack_visual_indexes": [],
"depth": 27,
"dtype": null,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 4304,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"model_type": "qwen3_5_vision",
"num_heads": 16,
"num_position_embeddings": 2304,
"out_hidden_size": 4096,
"output_attentions": false,
"output_hidden_states": false,
"patch_size": 16,
"problem_type": null,
"return_dict": true,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "axial"
},
"spatial_merge_size": 2,
"temporal_patch_size": 2
},
"vision_end_token_id": 248054,
"vision_start_token_id": 248053
},
"encoder_layer_id": -1,
"encoder_model_name": "Qwen/Qwen3.5-9B",
"eos_token_id": 248046,
"example_token_index": 248079,
"extract_text_features": false,
"focal_loss_alpha": 0.7,
"focal_loss_gamma": -1,
"focal_loss_reduction": "none",
"freeze_media_encoders": true,
"hidden_size": 4096,
"ignore_index": -100,
"initializer_range": 0.03,
"label_model_config": {
"_name_or_path": "BAAI/bge-small-en-v1.5",
"add_cross_attention": false,
"architectures": [
"BertModel"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"classifier_dropout": null,
"dtype": "float32",
"eos_token_id": null,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 384,
"id2label": {
"0": "LABEL_0"
},
"initializer_range": 0.02,
"intermediate_size": 1536,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"problem_type": null,
"return_dict": true,
"tie_word_embeddings": true,
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 30522
},
"label_model_name": "BAAI/bge-small-en-v1.5",
"layer_wise": false,
"logit_scale_init_value": 2.6592,
"max_labels_alloc": "dynamic",
"max_num_classes": 25,
"model_type": "GLiClass",
"multimodal": true,
"normalize_features": false,
"pad_token_id": 248044,
"pooling_strategy": "avg",
"problem_type": "multi_label_classification",
"projector_hidden_act": "gelu",
"prompt_first": true,
"recurrent_bptt_steps": null,
"recurrent_confidence_coef": 0.0,
"recurrent_confidence_margin": 0.0,
"recurrent_confidence_mode": "relative",
"recurrent_halt_threshold": 0.01,
"recurrent_improvement_coef": 0.1,
"recurrent_improvement_margin": 0.05,
"recurrent_inference": true,
"recurrent_inference_max_steps": null,
"recurrent_min_steps": 1,
"recurrent_read_text": false,
"recurrent_steps": 3,
"scorer_attn_dropout": 0.1,
"scorer_encoder_num_layers": 2,
"scorer_full_sequence": false,
"scorer_mlp_hidden_size": 1024,
"scorer_num_heads": 16,
"scorer_type": "simple",
"sep_token_index": 248078,
"shuffle_labels": true,
"squeeze_layers": false,
"text_token_index": 248078,
"transformers_version": "5.19.0",
"use_calibrator": true,
"use_embedding_projection": false,
"use_lstm": false,
"use_segment_embeddings": false,
"vocab_size": 248080
}