Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,37 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,180 @@
+{
+  "_name_or_path": "checkpoints/mistral-nemo-instruct",
+  "architectures": [
+    "LlavaMistralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "mlp_bias": false,
+  "mm_hidden_size": 2048,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 7e-06,
+  "mm_projector_type": "glu",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "checkpoints/ve-ft-mine-4e-v2.0",
+  "model_type": "llava_llama",
+  "new_img_size": null,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "s2": false,
+  "s2_max_split_size": 384,
+  "s2_scales": "384,768",
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "float16",
+  "transformers_version": "4.43.0.dev0",
+  "tune_mm_mlp_adapter": false,
+  "unfreeze_mm_vision_tower": true,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "video_fps": 1,
+  "video_frames_num": 16,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": [
+      1,
+      1,
+      9,
+      1
+    ],
+    "dim_embed": [
+      256,
+      512,
+      1024,
+      2048
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.1,
+    "early_stopping": false,
+    "enable_checkpoint": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_feature_source": [
+      "spatial_avg_pool",
+      "temporal_avg_pool"
+    ],
+    "image_pos_embed": {
+      "max_pos_embeddings": 50,
+      "type": "learned_abs_2d"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_groups": [
+      8,
+      16,
+      32,
+      64
+    ],
+    "num_heads": [
+      8,
+      16,
+      32,
+      64
+    ],
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_padding": [
+      3,
+      1,
+      1,
+      1
+    ],
+    "patch_prenorm": [
+      false,
+      true,
+      true,
+      true
+    ],
+    "patch_size": [
+      7,
+      3,
+      3,
+      3
+    ],
+    "patch_stride": [
+      4,
+      2,
+      2,
+      2
+    ],
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 1024,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "visual_temporal_embedding": {
+      "max_temporal_embeddings": 100,
+      "type": "COSINE"
+    },
+    "window_size": 12
+  },
+  "vocab_size": 131072
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Tensorflow","task":"image-object-detection"}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.43.0.dev0"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8efa5826f7eb8696ee1321b9ee9c0d7f903ed4def3242405131183d4b4def2d
+size 4865522432

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86db2bb97c33c81b90fd7fff87f84a0326a220306d78de459733c41f16ee32ca
+size 4907529344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb913f588ede35a843463bf50f61e20bf0e5999b8efb206a18202330a31ad24
+size 4907529376

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba31a68624657c204dc15e399fd2dcf13a4b0f17ddf63dd7fd4a57d6b324936
+size 4907529376

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97829a137d06e338671e8a8894f4cbee04779d9ea9f488e180983c2ee7faa747
+size 4937396952

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8896d267237793f3a98d15dc0defe541b51a228dee51d1d66b05ac27a5b279ea
+size 1342177408

model.safetensors.index.json

@@ -0,0 +1,779 @@
+{
+  "metadata": {
+    "total_size": 25867581440
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.mm_projector.layers.0.linear_proj.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "model.mm_projector.layers.0.linear_proj.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "model.mm_projector.layers.0.linear_proj.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.mm_projector.layers.0.linear_proj.linear_proj.weight": "model-00005-of-00006.safetensors",
+    "model.mm_projector.layers.0.linear_proj.norm1.bias": "model-00005-of-00006.safetensors",
+    "model.mm_projector.layers.0.linear_proj.norm1.weight": "model-00005-of-00006.safetensors",
+    "model.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.image_pos_embed.column_embeddings.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.image_pos_embed.row_embeddings.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.conv1.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.conv1.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.conv2.fn.dw.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.conv2.fn.dw.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc1.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc1.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc2.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc2.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.fn.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.fn.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.fn.qkv.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.fn.qkv.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.convs.0.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.convs.0.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.convs.0.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.convs.0.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.convs.1.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.convs.1.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.convs.1.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.convs.1.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.convs.2.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.convs.2.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.convs.2.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.convs.2.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.convs.3.norm.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.convs.3.norm.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.convs.3.proj.bias": "model-00005-of-00006.safetensors",
+    "model.vision_tower.vision_tower.convs.3.proj.weight": "model-00005-of-00006.safetensors",
+    "model.vision_tower.visual_temporal_embed.pos_idx_to_embed": "model-00005-of-00006.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,33 @@
+{
+  "auto_map": {
+    "AutoProcessor": "processing_florence2.Florence2Processor"
+  },
+  "crop_size": {
+    "height": 768,
+    "width": 768
+  },
+  "do_center_crop": false,
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_seq_length": 577,
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "processor_class": "Florence2Processor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 768,
+    "width": 768
+  }
+}

readme_ms.md

@@ -0,0 +1,33 @@
+---
+frameworks:
+- Tensorflow
+license: Apache License 2.0
+tasks:
+- image-object-detection
+
+#model-type:
+##如 gpt、phi、llama、chatglm、baichuan 等
+#- gpt
+
+#domain:
+##如 nlp、cv、audio、multi-modal
+#- nlp
+
+#language:
+##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
+#- cn 
+
+#metrics:
+##如 CIDEr、Blue、ROUGE 等
+#- CIDEr
+
+#tags:
+##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
+#- pretrained
+
+#tools:
+##如 vllm、fastchat、llamacpp、AdaSeq 等
+#- vllm
+---
+### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
+#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}