初始化项目，由ModelHub XC社区提供模型

Model: TIGER-Lab/Mantis-8B-siglip-llama3
Source: Original Platform

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "MFuyu/llava_siglip_llama3_8b_pretrain_8192",
+  "architectures": [
+    "LlavaForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_token_index": 128256,
+  "model_type": "llava",
+  "pad_token_id": 128257,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "bos_token_id": 128000,
+    "eos_token_id": 128001,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 8192,
+    "model_type": "llama",
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 500000.0,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 128258
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.2",
+  "vision_config": {
+    "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_hidden_layers": 27,
+    "patch_size": 14
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 128258
+}