File size: 3,056 Bytes
0ce506a 50449ef 0ce506a 50449ef 0ce506a | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 | {
"architectures": [
"CXRMate2ForConditionalGeneration"
],
"auto_map": {
"AutoConfig": "configuration_cxrmate2.CXRMate2Config",
"AutoModelForCausalLM": "modelling_cxrmate2.CXRMate2ForConditionalGeneration"
},
"bos_token_id": 128000,
"config": "cxrmate2/config/002_grpo_rev_a",
"dtype": "float32",
"findings_token_type_id": 128029,
"generate_both_sections_token_id": null,
"generate_findings_token_id": 128003,
"generate_impression_token_id": 128005,
"image_token_index": 128002,
"impression_token_type_id": 128030,
"missing_time_delta_token_id": 128012,
"model_type": "cxrmate-2",
"multimodal_projector_bias": false,
"num_q_adapter_layers": 2,
"num_q_adapter_positions": 1497,
"num_q_adapter_queries": 128,
"num_token_types": null,
"permute_encoder_last_hidden_state": true,
"projector_hidden_act": null,
"sep_token_id": 128072,
"text_config": {
"_name_or_path": "meta-llama/Llama-3.2-3B",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"dtype": "float32",
"eos_token_id": 128001,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 24,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 32.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"tie_word_embeddings": true,
"use_cache": true,
"vocab_size": 128256
},
"time_delta_encoder_intermediate_size": 2048,
"time_delta_monotonic_inversion": true,
"transformers_version": "4.57.1",
"trial": 6,
"vision_config": {
"_name_or_path": "microsoft/rad-dino-maira-2",
"apply_layernorm": true,
"architectures": [
"Dinov2Model"
],
"attention_probs_dropout_prob": 0.0,
"drop_path_rate": 0.0,
"dtype": "float32",
"hidden_act": "gelu",
"hidden_dropout_prob": 0.0,
"hidden_size": 768,
"image_size": 518,
"initializer_range": 0.02,
"layer_norm_eps": 1e-06,
"layerscale_value": 1.0,
"mlp_ratio": 4,
"model_type": "dinov2",
"num_attention_heads": 12,
"num_channels": 3,
"num_hidden_layers": 12,
"out_features": [
"stage12"
],
"out_indices": [
12
],
"patch_size": 14,
"qkv_bias": true,
"reshape_hidden_states": true,
"stage_names": [
"stem",
"stage1",
"stage2",
"stage3",
"stage4",
"stage5",
"stage6",
"stage7",
"stage8",
"stage9",
"stage10",
"stage11",
"stage12"
],
"use_mask_token": true,
"use_swiglu_ffn": false
},
"vision_feature_layer": -1,
"vision_feature_select_strategy": "full"
}
|