20250328-paraff-visionund-janus-lycc0324-l4+norm-bf16/model_77_acc_9.801e-01

config.json

@@ -1,30 +1,59 @@
 {
-  "_name_or_path": "k-l-lambda/Janus-Pro-7B-language",
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "head_dim": 128,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_position_embeddings": 16384,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 30,
-  "num_key_value_heads": 32,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
+  "aligner_config": {
+    "cls": "MlpProjector",
+    "model_type": "aligner",
+    "params": {
+      "depth": 2,
+      "input_dim": 1024,
+      "n_embed": 4096,
+      "projector_type": "mlp_gelu"
+    }
+  },
+  "gen_aligner_config": {
+    "cls": "MlpProjector",
+    "model_type": "gen_aligner",
+    "params": {
+      "depth": 2,
+      "input_dim": 8,
+      "n_embed": 4096,
+      "projector_type": "mlp_gelu"
+    }
+  },
+  "gen_head_config": {
+    "cls": "vision_head",
+    "model_type": "gen_head",
+    "params": {
+      "image_token_embed": 4096,
+      "image_token_size": 16384,
+      "n_embed": 4096
+    }
+  },
+  "gen_vision_config": {
+    "cls": "VQ-16",
+    "model_type": "gen_vision",
+    "params": {
+      "image_token_size": 16384,
+      "n_embed": 8
+    }
+  },
+  "language_config": {
+    "max_position_embeddings": 16384,
+    "model_type": "llama",
+    "num_hidden_layers": 30,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 102400
+  },
+  "model_type": "multi_modality",
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.49.0",
-  "use_cache": true,
-  "vocab_size": 102400
+  "transformers_version": "4.33.1",
+  "vision_config": {
+    "cls": "CLIPVisionTower",
+    "model_type": "vision",
+    "params": {
+      "image_size": 384,
+      "model_name": "siglip_large_patch16_384",
+      "select_feature": "same",
+      "select_layer": -1
+    }
+  }
 }

generation_config.json

@@ -1,6 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "transformers_version": "4.49.0"
-}

model-00003-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3de2258581ac55797889aa5edea7c973b5b14a2d5dc0e8714ac23b33d65e5a1c
-size 3852615520

model.safetensors.index.json

@@ -1,280 +0,0 @@
-{
-  "metadata": {
-    "total_size": 13820731392
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00003-of-00003.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.norm.weight": "model-00003-of-00003.safetensors"
-  }
-}

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "background_color": [
+    127,
+    127,
+    127
+  ],
+  "do_normalize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "VLMImageProcessor",
+  "image_size": 384,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "min_size": 14,
+  "processor_class": "VLChatProcessor",
+  "rescale_factor": 0.00392156862745098
+}

processor_config.json

@@ -0,0 +1,9 @@
+{
+  "add_special_token": false,
+  "ignore_id": -100,
+  "image_tag": "<image_placeholder>",
+  "mask_prompt": true,
+  "num_image_tokens": 576,
+  "processor_class": "VLChatProcessor",
+  "sft_format": "deepseek"
+}

model-00001-of-00003.safetensors → pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a50761fdfd96ec9e31c201b1c5811a805a708614cd62ab7f47b24335eb1b274
-size 4987202208
+oid sha256:d5b18c112db38de4bc228faed0dd5e174874caa237b409110f959cd8918a93d7
+size 9988189281

model-00002-of-00003.safetensors → pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18806a0d0c74842f3da13d6e5457b2385742a50b629cb92b9474af28c1316707
-size 4980945440
+oid sha256:0b141796443add9ed28acad31ac8335ce463fe37c011474eb57ed8e1ab7eff3d
+size 4853016432

pytorch_model.bin.index.json

@@ -0,0 +1,943 @@
+{
+  "metadata": {
+    "total_size": 14840868118
+  },
+  "weight_map": {
+    "aligner.layers.0.bias": "pytorch_model-00001-of-00002.bin",
+    "aligner.layers.0.weight": "pytorch_model-00001-of-00002.bin",
+    "aligner.layers.2.bias": "pytorch_model-00001-of-00002.bin",
+    "aligner.layers.2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_aligner.layers.0.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_aligner.layers.0.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_aligner.layers.2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_aligner.layers.2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_embed.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_head.output_mlp_projector.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_head.output_mlp_projector.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_head.vision_head.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_head.vision_head.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.0.k.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.0.k.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.0.norm.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.0.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.0.proj_out.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.0.proj_out.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.0.q.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.0.q.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.0.v.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.0.v.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.1.k.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.1.k.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.1.norm.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.1.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.1.proj_out.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.1.proj_out.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.1.q.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.1.q.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.1.v.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.1.v.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.2.k.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.2.k.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.2.norm.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.2.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.2.proj_out.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.2.proj_out.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.2.q.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.2.q.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.2.v.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.attn.2.v.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.2.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.2.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.2.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.2.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.2.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.2.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.res.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.upsample.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.0.upsample.conv.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.0.nin_shortcut.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.0.nin_shortcut.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.2.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.2.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.2.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.2.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.2.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.2.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.res.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.upsample.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.1.upsample.conv.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.2.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.2.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.2.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.2.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.2.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.2.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.res.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.upsample.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.2.upsample.conv.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.0.nin_shortcut.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.0.nin_shortcut.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.2.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.2.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.2.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.2.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.2.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.2.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.res.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.upsample.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.3.upsample.conv.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.2.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.2.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.2.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.2.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.2.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.2.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_blocks.4.res.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_in.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_in.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_out.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.conv_out.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.1.k.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.1.k.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.1.norm.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.1.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.1.proj_out.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.1.proj_out.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.1.q.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.1.q.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.1.v.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.1.v.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.2.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.2.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.2.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.2.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.2.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.2.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.mid.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.norm_out.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.decoder.norm_out.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.downsample.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.downsample.conv.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.0.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.downsample.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.downsample.conv.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.1.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.downsample.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.downsample.conv.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.0.nin_shortcut.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.0.nin_shortcut.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.2.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.downsample.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.downsample.conv.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.3.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.0.k.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.0.k.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.0.norm.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.0.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.0.proj_out.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.0.proj_out.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.0.q.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.0.q.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.0.v.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.0.v.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.1.k.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.1.k.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.1.norm.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.1.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.1.proj_out.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.1.proj_out.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.1.q.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.1.q.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.1.v.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.attn.1.v.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.0.nin_shortcut.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.0.nin_shortcut.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_blocks.4.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_in.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_in.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_out.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.conv_out.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.1.k.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.1.k.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.1.norm.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.1.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.1.proj_out.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.1.proj_out.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.1.q.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.1.q.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.1.v.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.1.v.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.2.conv1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.2.conv1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.2.conv2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.2.conv2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.2.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.2.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.mid.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.norm_out.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.encoder.norm_out.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.post_quant_conv.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.post_quant_conv.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.quant_conv.bias": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.quant_conv.weight": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.quantize.codebook_used": "pytorch_model-00001-of-00002.bin",
+    "gen_vision_model.quantize.embedding.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "language_model.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "language_model.model.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "vision_model.vision_tower.attn_pool.kv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.attn_pool.kv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.attn_pool.latent": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.attn_pool.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.attn_pool.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.attn_pool.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.attn_pool.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.attn_pool.norm.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.attn_pool.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.attn_pool.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.attn_pool.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.attn_pool.q.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.attn_pool.q.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.0.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.0.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.0.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.0.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.1.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.1.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.1.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.1.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.10.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.10.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.10.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.10.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.10.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.10.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.10.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.10.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.11.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.11.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.11.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.11.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.11.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.11.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.11.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.11.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.12.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.12.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.12.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.12.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.12.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.12.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.12.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.12.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.13.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.13.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.13.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.13.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.13.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.13.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.13.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.13.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.14.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.14.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.14.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.14.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.14.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.14.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.14.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.14.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.15.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.15.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.15.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.15.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.15.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.15.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.15.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.15.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.16.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.16.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.16.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.16.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.16.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.16.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.16.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.16.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.17.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.17.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.17.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.17.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.17.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.17.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.17.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.17.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.18.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.18.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.18.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.18.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.18.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.18.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.18.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.18.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.19.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.19.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.19.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.19.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.19.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.19.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.19.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.19.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.2.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.2.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.2.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.2.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.2.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.2.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.20.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.20.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.20.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.20.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.20.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.20.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.20.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.20.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.21.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.21.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.21.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.21.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.21.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.21.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.21.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.21.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.22.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.22.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.22.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.22.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.22.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.22.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.22.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.22.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.23.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.23.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.23.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.23.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.23.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.23.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.23.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.23.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.3.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.3.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.3.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.3.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.3.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.3.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.3.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.3.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.4.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.4.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.4.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.4.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.4.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.4.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.4.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.4.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.5.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.5.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.5.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.5.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.5.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.5.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.5.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.5.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.6.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.6.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.6.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.6.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.6.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.6.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.6.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.6.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.7.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.7.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.7.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.7.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.7.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.7.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.7.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.7.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.8.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.8.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.8.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.8.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.8.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.8.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.8.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.8.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.9.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.9.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.9.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.9.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.9.norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.9.norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.9.norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.blocks.9.norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.norm.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.norm.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.patch_embed.proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.patch_embed.proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vision_model.vision_tower.pos_embed": "pytorch_model-00001-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "additional_special_tokens": [
+    "<image_placeholder>",
+    "<patch_placeholder>",
+    "<|ref|>",
+    "<|/ref|>",
+    "<|det|>",
+    "<|/det|>",
+    "<|grounding|>",
+    "<|User|>",
+    "<|Assistant|>"
+  ],
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "pad_token": "<｜▁pad▁｜>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "model_max_length": 16384,
+  "pad_token": null,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": true
+}