Upload 8 files

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "./output_llava/checkpoints/pretrain-conv-llava-jp-1.3b-stage2-1280",
+  "activation_function": "gelu",
+  "architectures": [
+    "LlavaGpt2ForCausalLM"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 7,
+  "drop_path_rates": [
+    0.085,
+    0.088,
+    0.091,
+    0.094,
+    0.097,
+    0.1
+  ],
+  "embd_pdrop": 0.1,
+  "eos_token_id": 7,
+  "gradient_checkpointing": false,
+  "image_aspect_ratio": "square",
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "mm_dense_connector_type": null,
+  "mm_hidden_size": 3072,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_vision_resolution": 1280,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "convnext_large",
+  "model_type": "llava-jp",
+  "n_ctx": 1024,
+  "n_embd": 2048,
+  "n_head": 16,
+  "n_inner": 8192,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "scales": null,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "tokenizer_model_max_length": 1532,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vision_add_five_stage": 6,
+  "vision_encoder_type": "ConvNeXt",
+  "vision_five_stage_width": 3072,
+  "vocab_size": 50688
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 7,
+  "eos_token_id": 7,
+  "transformers_version": "4.41.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f9d7f34ad88e7b37d1dd493817decda61720bfadb07d8ed48772649879fb576
+size 4997886200

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a325101c74550f438c4e325c968c49d2e71202cc81bcc78607ff3f518d8e9877
+size 2064141360

model.safetensors.index.json

@@ -0,0 +1,702 @@
+{
+  "metadata": {
+    "total_size": 7061942656
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.0.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.0.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.0.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.0.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.0.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.1.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.1.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.1.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.1.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.2.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.2.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.2.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.2.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.0.blocks.2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.0.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.0.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.0.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.0.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.0.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.1.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.1.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.1.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.1.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.2.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.2.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.2.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.2.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.blocks.2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.downsample.0.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.downsample.0.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.downsample.1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.1.downsample.1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.0.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.0.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.0.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.0.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.0.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.1.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.1.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.1.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.1.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.10.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.10.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.10.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.10.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.10.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.11.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.11.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.11.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.11.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.11.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.12.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.12.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.12.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.12.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.12.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.13.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.13.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.13.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.13.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.13.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.14.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.14.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.14.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.14.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.14.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.15.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.15.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.15.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.15.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.15.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.16.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.16.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.16.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.16.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.16.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.17.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.17.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.17.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.17.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.17.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.18.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.18.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.18.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.18.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.18.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.19.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.19.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.19.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.19.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.19.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.2.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.2.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.2.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.2.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.20.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.20.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.20.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.20.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.20.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.21.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.21.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.21.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.21.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.21.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.22.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.22.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.22.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.22.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.22.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.23.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.23.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.23.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.23.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.23.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.24.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.24.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.24.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.24.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.24.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.24.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.24.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.24.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.24.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.25.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.25.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.25.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.25.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.25.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.25.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.25.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.25.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.25.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.26.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.26.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.26.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.26.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.26.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.26.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.26.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.26.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.26.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.3.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.3.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.3.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.3.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.3.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.4.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.4.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.4.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.4.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.4.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.5.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.5.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.5.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.5.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.5.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.6.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.6.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.6.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.6.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.6.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.7.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.7.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.7.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.7.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.7.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.8.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.8.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.8.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.8.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.8.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.9.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.9.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.9.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.9.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.blocks.9.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.downsample.0.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.downsample.0.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.downsample.1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.2.downsample.1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.0.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.0.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.0.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.0.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.0.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.1.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.1.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.1.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.1.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.2.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.2.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.2.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.2.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.blocks.2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.downsample.0.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.downsample.0.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.downsample.1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.3.downsample.1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.0.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.0.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.0.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.0.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.0.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.1.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.1.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.1.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.1.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.2.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.2.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.2.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.2.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.3.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.3.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.3.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.3.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.3.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.4.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.4.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.4.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.4.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.4.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.5.conv_dw.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.5.conv_dw.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.5.norm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.5.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.blocks.5.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.downsample.0.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.downsample.0.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.downsample.1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stages.4.downsample.1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stem.0.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stem.0.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stem.1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.stem.1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.0.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.c_attn.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.c_attn.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.c_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.c_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_2.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.3.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
+    "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
+    "transformer.wpe.weight": "model-00001-of-00002.safetensors",
+    "transformer.wte.weight": "model-00001-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,48 @@
+{
+  "additional_special_tokens": [
+    "</s|LLM-jp>"
+  ],
+  "bos_token": {
+    "content": "<s|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<CLS|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<EOD|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk|LLM-jp>",
+  "sep_token": {
+    "content": "<SEP|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,85 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<mask|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<pad|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<CLS|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<SEP|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "</s|LLM-jp>"
+  ],
+  "bos_token": "<s|LLM-jp>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS|LLM-jp>",
+  "eod_token": "<EOD|LLM-jp>",
+  "eos_token": "<EOD|LLM-jp>",
+  "extra_ids": 0,
+  "mask_token": "<mask|LLM-jp>",
+  "model_max_length": 1532,
+  "pad_token": "<unk|LLM-jp>",
+  "padding_side": "right",
+  "sep_token": "<SEP|LLM-jp>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk|LLM-jp>"
+}