Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,182 @@
+{
+  "_name_or_path": "checkpoints/qwen2-5-7b/",
+  "architectures": [
+    "LlavaQwen2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "freeze_mm_mlp_adapter": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "mlp_bias": false,
+  "mm_hidden_size": 2048,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 1e-05,
+  "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/monovev2",
+  "model_type": "llava_llama",
+  "new_img_size": null,
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "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": "4.45.1",
+  "tune_mm_mlp_adapter": false,
+  "unfreeze_mm_vision_tower": true,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_sliding_window": false,
+  "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": 151665
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.45.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54cb594eb6d1e38856803a74acb3df1d95dace43c3a0a2ad2b327a057c0e8def
+size 4874800640

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29628f308a2ffdd8e5cdd3479f899c25ccfb1a46209d423075029ba69c5c8dc4
+size 4932750888

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:923b965893cfa65352769308e2e5dd141e083b5915a9628e60bdc74d95f32177
+size 4985060088

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b90eb63f6a4492a52d9843ac0fec766f8c4046f1672025facac76d61358da75c
+size 1477856144

model.safetensors.index.json

@@ -0,0 +1,755 @@
+{
+  "metadata": {
+    "total_size": 16270367744
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.mm_projector.layers.0.linear_proj.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+    "model.mm_projector.layers.0.linear_proj.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+    "model.mm_projector.layers.0.linear_proj.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.mm_projector.layers.0.linear_proj.linear_proj.weight": "model-00004-of-00004.safetensors",
+    "model.mm_projector.layers.0.linear_proj.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.layers.0.linear_proj.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.image_pos_embed.column_embeddings.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.image_pos_embed.row_embeddings.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.conv1.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.conv1.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.conv2.fn.dw.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.conv2.fn.dw.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.fn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.fn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.fn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.fn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.convs.0.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.convs.0.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.convs.0.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.convs.0.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.convs.1.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.convs.1.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.convs.1.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.convs.1.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.convs.2.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.convs.2.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.convs.2.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.convs.2.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.convs.3.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.convs.3.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.convs.3.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.convs.3.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.visual_temporal_embed.pos_idx_to_embed": "model-00004-of-00004.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
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}