Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ 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
+assets/Unlimited-OCR.png filter=lfs diff=lfs merge=lfs -text
+assets/long-horizon-ocr.gif filter=lfs diff=lfs merge=lfs -text
+wheel/sglang-0.0.0.dev11416+g92e8bb79e-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,46 @@
+---
+base_model: baidu/Unlimited-OCR
+license: mit
+language:
+- multilingual
+pipeline_tag: image-text-to-text
+tags:
+- mlx
+- mlx-vlm
+- ocr
+- vision-language
+- baidu
+library_name: mlx
+---
+
+# Unlimited-OCR BF16 MLX
+
+MLX conversion of [`baidu/Unlimited-OCR`](https://huggingface.co/baidu/Unlimited-OCR).
+
+```python
+from mlx_vlm import load
+from mlx_vlm.generate import generate
+
+model, processor = load("mikoy92/Unlimited-OCR-bf16-mlx")
+result = generate(
+    model,
+    processor,
+    "<image>\ndocument parsing.",
+    image="your_image.jpg",
+    max_tokens=512,
+    temperature=0.0,
+)
+print(result.text)
+```
+
+CLI:
+
+```bash
+python -m mlx_vlm generate \
+  --model mikoy92/Unlimited-OCR-bf16-mlx \
+  --image your_image.jpg \
+  --prompt "document parsing." \
+  --temp 0
+```
+
+This repo stores MLX-layout weights in safetensors (`format=mlx`). It uses the existing `deepseekocr` MLX implementation because Unlimited-OCR shares that SAM + CLIP-L + DeepSeekV2 OCR architecture shape with different checkpoint dimensions.

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{% if message['role'] == 'user' %}{% elif message['role'] == 'assistant' %}{% endif %}{{message['content']}} {% endfor %}{% if add_generation_prompt %}{% endif %}

config.json

@@ -0,0 +1,117 @@
+{
+  "architectures": [
+    "DeepseekOCRForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "candidate_resolutions": [
+    [
+      1024,
+      1024
+    ]
+  ],
+  "eos_token_id": 1,
+  "first_k_dense_replace": 1,
+  "global_view_pos": "head",
+  "hidden_size": 1280,
+  "intermediate_size": 6848,
+  "kv_lora_rank": null,
+  "language_config": {
+    "architectures": [
+      "DeepseekOCRForCausalLM"
+    ],
+    "bos_token_id": 0,
+    "eos_token_id": 1,
+    "first_k_dense_replace": 1,
+    "hidden_size": 1280,
+    "intermediate_size": 6848,
+    "kv_lora_rank": null,
+    "lm_head": true,
+    "max_position_embeddings": 32768,
+    "moe_intermediate_size": 896,
+    "n_group": 1,
+    "n_routed_experts": 64,
+    "n_shared_experts": 2,
+    "num_attention_heads": 10,
+    "num_experts_per_tok": 6,
+    "num_hidden_layers": 12,
+    "num_key_value_heads": 10,
+    "q_lora_rank": null,
+    "qk_nope_head_dim": 0,
+    "qk_rope_head_dim": 0,
+    "rm_head": false,
+    "topk_group": 1,
+    "topk_method": "greedy",
+    "torch_dtype": "bfloat16",
+    "use_mla": false,
+    "v_head_dim": 128,
+    "vocab_size": 129280,
+    "sliding_window_size": 128
+  },
+  "lm_head": true,
+  "max_position_embeddings": 32768,
+  "model_type": "deepseekocr",
+  "moe_intermediate_size": 896,
+  "n_group": 1,
+  "n_routed_experts": 64,
+  "n_shared_experts": 2,
+  "num_attention_heads": 10,
+  "num_experts_per_tok": 6,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 10,
+  "projector_config": {
+    "input_dim": 2048,
+    "model_type": "mlp_projector",
+    "n_embed": 1280,
+    "projector_type": "linear"
+  },
+  "q_lora_rank": null,
+  "qk_nope_head_dim": 0,
+  "qk_rope_head_dim": 0,
+  "rm_head": false,
+  "sliding_window": 128,
+  "sliding_window_size": 128,
+  "tile_tag": "2D",
+  "topk_group": 1,
+  "topk_method": "greedy",
+  "transformers_version": "4.46.3",
+  "use_mla": false,
+  "v_head_dim": 128,
+  "vision_config": {
+    "image_size": 1024,
+    "mlp_ratio": 3.7362,
+    "model_name": "deeplip_b_l",
+    "model_type": "vision",
+    "width": {
+      "clip-l-14-224": {
+        "heads": 16,
+        "image_size": 224,
+        "layers": 24,
+        "patch_size": 14,
+        "width": 1024
+      },
+      "sam_vit_b": {
+        "downsample_channels": [
+          512,
+          1024
+        ],
+        "global_attn_indexes": [
+          2,
+          5,
+          8,
+          11
+        ],
+        "heads": 12,
+        "layers": 12,
+        "width": 768
+      }
+    },
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "num_attention_heads": 16,
+    "layers": 24,
+    "patch_size": 14,
+    "num_channels": 3,
+    "layer_norm_eps": 1e-05
+  },
+  "vocab_size": 129280
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4044b5fa97524c43bdb49ece58c363f21db2e1f2bfae8f081eab3d64c13dcc26
+size 5240461970

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12146c3d4a1fdbbe77d7bdcbaef645efc4f4901336868cab5e1e7558ec31ead8
+size 1431828399

model.safetensors.index.json

@@ -0,0 +1,638 @@
+{
+    "metadata": {
+        "total_size": 6672212480
+    },
+    "weight_map": {
+        "image_newline": "model-00002-of-00002.safetensors",
+        "language_model.lm_head.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.10.mlp.gate.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.10.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.10.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.11.mlp.gate.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.11.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.11.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.9.mlp.gate.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.9.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.9.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.norm.weight": "model-00002-of-00002.safetensors",
+        "projector.layers.bias": "model-00002-of-00002.safetensors",
+        "projector.layers.weight": "model-00002-of-00002.safetensors",
+        "sam_model.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.0.attn.rel_pos_h": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.0.attn.rel_pos_w": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.0.mlp.lin1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.0.mlp.lin1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.0.mlp.lin2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.0.mlp.lin2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.1.attn.rel_pos_h": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.1.attn.rel_pos_w": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.1.mlp.lin1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.1.mlp.lin1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.1.mlp.lin2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.1.mlp.lin2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.10.attn.rel_pos_h": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.10.attn.rel_pos_w": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.10.mlp.lin1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.10.mlp.lin1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.10.mlp.lin2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.10.mlp.lin2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.11.attn.rel_pos_h": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.11.attn.rel_pos_w": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.11.mlp.lin1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.11.mlp.lin1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.11.mlp.lin2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.11.mlp.lin2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.2.attn.rel_pos_h": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.2.attn.rel_pos_w": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.2.mlp.lin1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.2.mlp.lin1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.2.mlp.lin2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.2.mlp.lin2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.3.attn.rel_pos_h": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.3.attn.rel_pos_w": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.3.mlp.lin1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.3.mlp.lin1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.3.mlp.lin2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.3.mlp.lin2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.4.attn.rel_pos_h": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.4.attn.rel_pos_w": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.4.mlp.lin1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.4.mlp.lin1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.4.mlp.lin2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.4.mlp.lin2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.5.attn.rel_pos_h": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.5.attn.rel_pos_w": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.5.mlp.lin1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.5.mlp.lin1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.5.mlp.lin2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.5.mlp.lin2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.6.attn.rel_pos_h": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.6.attn.rel_pos_w": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.6.mlp.lin1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.6.mlp.lin1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.6.mlp.lin2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.6.mlp.lin2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.7.attn.rel_pos_h": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.7.attn.rel_pos_w": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.7.mlp.lin1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.7.mlp.lin1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.7.mlp.lin2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.7.mlp.lin2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.8.attn.rel_pos_h": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.8.attn.rel_pos_w": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.8.mlp.lin1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.8.mlp.lin1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.8.mlp.lin2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.8.mlp.lin2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.9.attn.rel_pos_h": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.9.attn.rel_pos_w": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.9.mlp.lin1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.9.mlp.lin1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.9.mlp.lin2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.9.mlp.lin2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+        "sam_model.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.neck.0.weight": "model-00001-of-00002.safetensors",
+        "sam_model.neck.1.bias": "model-00001-of-00002.safetensors",
+        "sam_model.neck.1.weight": "model-00001-of-00002.safetensors",
+        "sam_model.neck.2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.neck.3.bias": "model-00001-of-00002.safetensors",
+        "sam_model.neck.3.weight": "model-00001-of-00002.safetensors",
+        "sam_model.net_2.weight": "model-00001-of-00002.safetensors",
+        "sam_model.net_3.weight": "model-00001-of-00002.safetensors",
+        "sam_model.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+        "sam_model.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+        "sam_model.pos_embed": "model-00001-of-00002.safetensors",
+        "view_separator": "model-00002-of-00002.safetensors",
+        "vision_model.embeddings.class_embedding": "model-00001-of-00002.safetensors",
+        "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
+        "vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
+        "vision_model.pre_layrnorm.bias": "model-00001-of-00002.safetensors",
+        "vision_model.pre_layrnorm.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.0.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.1.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.10.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.11.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.12.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.13.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.14.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.15.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.16.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.17.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.18.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.19.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.2.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.20.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.21.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.21.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.22.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.22.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.23.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.23.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.3.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.4.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.5.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.6.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.7.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.8.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.9.self_attn.qkv_proj.bias": "model-00001-of-00002.safetensors",
+        "vision_model.transformer.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors"
+    }
+}

processor_config.json

@@ -0,0 +1,28 @@
+{
+  "add_special_token": false,
+  "candidate_resolutions": [
+    [
+      1024,
+      1024
+    ]
+  ],
+  "downsample_ratio": 4,
+  "ignore_id": -100,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_token": "<image>",
+  "mask_prompt": false,
+  "normalize": true,
+  "pad_token": "<\uff5c\u2581pad\u2581\uff5c>",
+  "patch_size": 16,
+  "processor_class": "DeepseekOCRProcessor",
+  "sft_format": "deepseek"
+}

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜▁pad▁｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": [
+    "<|User|>",
+    "<|Assistant|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<｜▁pad▁｜>",
+  "processor_class": "DeepseekOCRProcessor",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

wheel/sglang-0.0.0.dev11416+g92e8bb79e-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2644a1f349c55f0ca822e70a70679c98475754ec4722c3be1b18a72bac477cd5
+size 12450224