Upload CXRMate2ForConditionalGeneration

config.json

@@ -0,0 +1,115 @@
+{
+  "architectures": [
+    "CXRMate2ForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_cxrmate2.CXRMate2Config",
+    "AutoModelForCausalLM": "modelling_cxrmate2.CXRMate2ForConditionalGeneration"
+  },
+  "bos_token_id": 128000,
+  "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",
+  "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"
+}

generation_config.json

@@ -1,7 +1,6 @@
 {
+  "_from_model_config": true,
   "bos_token_id": 128000,
   "eos_token_id": 128001,
-  "max_new_tokens": 320,
-  "pad_token_id": 128073,
   "transformers_version": "4.57.1"
 }