Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

all_results.json

@@ -0,0 +1,9 @@
+{
+    "cpu_available_memory": 81.32,
+    "cpu_used_memory": 13.07,
+    "progress_or_epoch": 1.0,
+    "train_loss": 0.02089503208717809,
+    "train_runtime": 17741.4214,
+    "train_samples_per_second": 2.313,
+    "train_steps_per_second": 2.313
+}

chat_template.jinja

@@ -0,0 +1,43 @@
+{%- if not add_generation_prompt is defined -%}
+    {%- set add_generation_prompt = true -%}
+{%- endif -%}
+{%- if not cls_token is defined -%}
+    {%- set cls_token = "<|begin_of_sentence|>" -%}
+{%- endif -%}
+{%- if not eos_token is defined -%}
+    {%- set eos_token = "</s>" -%}
+{%- endif -%}
+{{- cls_token -}}
+{%- for message in messages -%}
+    {%- if message["role"] == "user" -%}
+        {{- "User: " -}}
+        {%- for content in message["content"] -%}
+            {%- if content["type"] == "image" -%}
+                {{ "<|IMAGE_START|><|IMAGE_PLACEHOLDER|><|IMAGE_END|>" }}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- for content in message["content"] -%}
+            {%- if content["type"] == "text" -%}
+                {{ content["text"] }}
+            {%- endif -%}
+        {%- endfor -%}
+        {{ "\n" -}}
+    {%- elif message["role"] == "assistant" -%}
+        {{- "Assistant:\n" -}}
+        {%- for content in message["content"] -%}
+            {%- if content["type"] == "text" -%}
+                {{ content["text"] }}
+            {%- endif -%}
+        {%- endfor -%}
+        {{ eos_token -}}
+    {%- elif message["role"] == "system" -%}
+        {%- for content in message["content"] -%}
+            {%- if content["type"] == "text" -%}
+                {{ content["text"] + "\n" }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- "Assistant:\n" -}}
+{%- endif -%}

config.json

@@ -0,0 +1,95 @@
+{
+  "architectures": [
+    "PaddleOCRVLForConditionalGeneration"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_paddleocr_vl.PaddleOCRVLConfig",
+    "AutoModel": "modeling_paddleocr_vl.PaddleOCRVLForConditionalGeneration",
+    "AutoModelForCausalLM": "modeling_paddleocr_vl.PaddleOCRVLForConditionalGeneration"
+  },
+  "compression_ratio": 1.0,
+  "enable_auto_parallel": false,
+  "freq_allocation": 20,
+  "fuse_ln": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "ignored_index": -100,
+  "image_token_id": 100295,
+  "intermediate_size": 3072,
+  "is_lora": false,
+  "max_position_embeddings": 131072,
+  "model_type": "paddleocr_vl",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 2,
+  "paddleformers_version": "1.1.0.post20260418",
+  "pp_seg_method": "layer:DecoderLayer|EmptyLayer",
+  "rms_norm_eps": 1e-05,
+  "rope_is_neox_style": true,
+  "rope_parameters": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_theta": 500000,
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_theta": 500000,
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 500000,
+  "scale_qk_coeff": 1.0,
+  "seq_length": 8192,
+  "sliding_window": null,
+  "tensor_model_parallel_size": -1,
+  "tie_word_embeddings": false,
+  "token_balance_seqlen": false,
+  "torch_dtype": "bfloat16",
+  "use_3d_rope": true,
+  "use_bias": false,
+  "use_cache": false,
+  "use_fast_layer_norm": false,
+  "use_flash_attention": false,
+  "video_token_id": 101307,
+  "vision_config": {
+    "architectures": [
+      "PaddleOCRVisionModel"
+    ],
+    "attention_dropout": 0.0,
+    "auto_map": {
+      "AutoConfig": "configuration_paddleocr_vl.PaddleOCRVLConfig",
+      "AutoModel": "modeling_paddleocr_vl.PaddleOCRVisionModel"
+    },
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 384,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "paddleocr_vl",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "pad_token_id": 0,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "bfloat16"
+  },
+  "vision_end_token_id": 101306,
+  "vision_start_token_id": 101305,
+  "vocab_size": 103424,
+  "weight_share_add_bias": true
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "max_length": 20,
+  "no_repeat_ngram_size": 0,
+  "use_cache": false
+}

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5100210ed354cf88ab5965f2ec878e5219e71dfeb2f390d01f74bf717f550f68
+size 1886777936

model.safetensors.index.json

@@ -0,0 +1,616 @@
+{
+    "metadata": {
+        "total_size": 1886700768
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00001-of-00001.safetensors",
+        "mlp_AR.linear_1.bias": "model-00001-of-00001.safetensors",
+        "mlp_AR.linear_1.weight": "model-00001-of-00001.safetensors",
+        "mlp_AR.linear_2.bias": "model-00001-of-00001.safetensors",
+        "mlp_AR.linear_2.weight": "model-00001-of-00001.safetensors",
+        "mlp_AR.pre_norm.bias": "model-00001-of-00001.safetensors",
+        "mlp_AR.pre_norm.weight": "model-00001-of-00001.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00001.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "model.norm.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.embeddings.packing_position_embedding.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.embeddings.position_embedding.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+        "visual.vision_model.post_layernorm.bias": "model-00001-of-00001.safetensors",
+        "visual.vision_model.post_layernorm.weight": "model-00001-of-00001.safetensors"
+    }
+}

preprocessor_config.json

@@ -0,0 +1,33 @@
+{
+  "auto_map": {
+    "AutoImageProcessor": "image_processing_paddleocr_vl.PaddleOCRVLImageProcessor",
+    "AutoProcessor": "processing_paddleocr_vl.PaddleOCRVLProcessor"
+  },
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "PaddleOCRVLImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_pixels": 1003520,
+  "merge_size": 2,
+  "min_pixels": 112896,
+  "patch_size": 14,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_pixels": 1003520,
+    "min_pixels": 112896
+  },
+  "temporal_conv_size": 1,
+  "temporal_patch_size": 1
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a215a59183d0d0781adc33bacd3ce6162716f7fd568fb30234a74d69803a7d
+size 11189060

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ef7db83df785924fb83d7b887b6e822a031c56e15cff40aaf9b982988180df
+size 1614363

tokenizer_config.json

@@ -0,0 +1,28 @@
+{
+  "_from_auto": true,
+  "add_prefix_space": false,
+  "auto_map": {
+    "AutoProcessor": "processing_paddleocr_vl.PaddleOCRVLProcessor"
+  },
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<|begin_of_sentence|>",
+  "download_hub": "huggingface",
+  "eos_token": "</s>",
+  "image_token": "<|IMAGE_PLACEHOLDER|>",
+  "is_local": false,
+  "mask_token": "<mask:1>",
+  "model_max_length": 131072,
+  "model_specific_special_tokens": {
+    "image_token": "<|IMAGE_PLACEHOLDER|>"
+  },
+  "pad_token": "<unk>",
+  "processor_class": "PaddleOCRVLProcessor",
+  "sep_token": "<|end_of_sentence|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "cpu_available_memory": 81.32,
+    "cpu_used_memory": 13.07,
+    "progress_or_epoch": 1.0,
+    "train_loss": 0.02089503208717809,
+    "train_runtime": 17741.4214,
+    "train_samples_per_second": 2.313,
+    "train_steps_per_second": 2.313
+}

trainer_state.json

@@ -0,0 +1,15 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "consumed_samples": 41036,
+  "epoch": 1.0,
+  "global_step": 41036,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "max_steps": 41036,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 0,
+  "trial_name": null,
+  "trial_params": null
+}