初始化项目，由ModelHub XC社区提供模型

Model: AI-ModelScope/R-4B
Source: Original Platform

config.json

@@ -0,0 +1,94 @@
+{
+  "auto_map": {
+    "AutoConfig": "configuration_r.RConfig",
+    "AutoModel": "modeling_r.RForConditionalGeneration",
+    "AutoModelForCausalLM": "modeling_r.RForConditionalGeneration"
+  },
+  "architectures": [
+    "RForConditionalGeneration"
+  ],
+  "eos_token_id": 151645,
+  "image_grid_pinpoints": [
+    [
+      384,
+      768
+    ],
+    [
+      768,
+      384
+    ],
+    [
+      768,
+      768
+    ],
+    [
+      1152,
+      384
+    ],
+    [
+      384,
+      1152
+    ]
+  ],
+  "image_token_index": 151669,
+  "model_type": "R",
+  "multimodal_projector_bias": true,
+  "pad_token_id": 151643,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "Qwen/Qwen3-4B",
+    "architectures": [
+      "Qwen3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 40960,
+    "max_window_layers": 36,
+    "model_type": "qwen3",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "torch_dtype": "float32",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 152000
+  },
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.0",
+  "use_image_newline_parameter": true,
+  "video_token_index": 151670,
+  "vision_aspect_ratio": "anyres",
+  "vision_config": {
+    "auto_map": {
+      "AutoConfig": "configuration_r.RConfig"  
+    },   
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 384,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 26,
+    "patch_size": 14,
+    "torch_dtype": "float32",
+    "vision_use_head": false
+  },
+  "vision_feature_layer": -1,
+  "vision_feature_select_strategy": "full"
+}