Duplicate from Qwen/Qwen3.5-4B-Base

Co-authored-by: cheng <littlebird13@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3.5-4B-Base/blob/main/LICENSE
+pipeline_tag: image-text-to-text
+---
+
+# Qwen3.5-4B-Base
+
+<img width="400px" src="https://qianwen-res.oss-accelerate.aliyuncs.com/logo_qwen3.5.png">
+
+[![Qwen Chat](https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5)](https://chat.qwen.ai)
+
+> [!Note]
+> This repository contains model weights and configuration files for the pre-trained only model in the Hugging Face Transformers format. 
+> 
+> These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, etc.
+> 
+> The intended use cases are fine-tuning, in-context learning experiments, and other research or development purposes, not direct interaction.
+> However, the control tokens, e.g., `<|im_start|>` and `<|im_end|>` were trained to allow efficient LoRA-style PEFT with the official chat template, mitigating the need to finetune embeddings, a significant optimization given Qwen3.5's larger vocabulary.
+
+
+Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency.
+
+## Qwen3.5 Highlights
+
+Qwen3.5 features the following enhancement:
+
+- **Unified Vision-Language Foundation**: Early fusion training on multimodal tokens achieves cross-generational parity with Qwen3 and outperforms Qwen3-VL models across reasoning, coding, agents, and visual understanding benchmarks.
+
+- **Efficient Hybrid Architecture**: Gated Delta Networks combined with sparse Mixture-of-Experts deliver high-throughput inference with minimal latency and cost overhead.
+
+- **Scalable RL Generalization**: Reinforcement learning scaled across million-agent environments with progressively complex task distributions for robust real-world adaptability.
+
+- **Global Linguistic Coverage**: Expanded support to 201 languages and dialects, enabling inclusive, worldwide deployment with nuanced cultural and regional understanding.
+
+- **Next-Generation Training Infrastructure**: Near-100% multimodal training efficiency compared to text-only training and asynchronous RL frameworks supporting massive-scale agent scaffolds and environment orchestration.
+
+
+For more details, please refer to our blog post [Qwen3.5](https://qwen.ai/blog?id=qwen3.5).
+
+
+## Model Overview
+
+- Type: Causal Language Model with Vision Encoder
+- Training Stage: Pre-training & Post-training
+- Language Model
+    - Number of Parameters: 4B
+    - Hidden Dimension: 2560
+    - Token Embedding: 248320 (Padded)
+    - Number of Layers: 32
+    - Hidden Layout: 8 × (3 × (Gated DeltaNet → FFN) → 1 × (Gated Attention → FFN))
+    - Gated DeltaNet:
+        - Number of Linear Attention Heads: 32 for V and 16 for QK
+        - Head Dimension: 128
+    - Gated Attention:
+        - Number of Attention Heads: 16 for Q and 4 for KV
+        - Head Dimension: 256
+        - Rotary Position Embedding Dimension: 64
+    - Feed Forward Network:
+        - Intermediate Dimension: 9216
+    - LM Output: 248320 (Tied to token embedding)
+    - MTP: trained with multi-steps  
+- Context Length: 262,144 natively and extensible up to 1,010,000 tokens.
+
+### Citation
+
+If you find our work helpful, feel free to give us a cite.
+
+```bibtex
+@misc{qwen3.5,
+    title  = {{Qwen3.5}: Towards Native Multimodal Agents},
+    author = {{Qwen Team}},
+    month  = {February},
+    year   = {2026},
+    url    = {https://qwen.ai/blog?id=qwen3.5}
+}
+```

config.json

@@ -0,0 +1,104 @@
+{
+    "architectures": [
+        "Qwen3_5ForConditionalGeneration"
+    ],
+    "image_token_id": 248056,
+    "model_type": "qwen3_5",
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attn_output_gate": true,
+        "dtype": "bfloat16",
+        "eos_token_id": 248044,
+        "full_attention_interval": 4,
+        "head_dim": 256,
+        "hidden_act": "silu",
+        "hidden_size": 2560,
+        "initializer_range": 0.02,
+        "intermediate_size": 9216,
+        "layer_types": [
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention"
+        ],
+        "linear_conv_kernel_dim": 4,
+        "linear_key_head_dim": 128,
+        "linear_num_key_heads": 16,
+        "linear_num_value_heads": 32,
+        "linear_value_head_dim": 128,
+        "max_position_embeddings": 262144,
+        "mlp_only_layers": [],
+        "model_type": "qwen3_5_text",
+        "mtp_num_hidden_layers": 1,
+        "mtp_use_dedicated_embeddings": false,
+        "num_attention_heads": 16,
+        "num_hidden_layers": 32,
+        "num_key_value_heads": 4,
+        "rms_norm_eps": 1e-06,
+        "tie_word_embeddings": true,
+        "use_cache": true,
+        "vocab_size": 248320,
+        "mamba_ssm_dtype": "float32",
+        "rope_parameters": {
+            "mrope_interleaved": true,
+            "mrope_section": [
+                11,
+                11,
+                10
+            ],
+            "rope_type": "default",
+            "rope_theta": 10000000,
+            "partial_rotary_factor": 0.25
+        }
+    },
+    "tie_word_embeddings": true,
+    "transformers_version": "4.57.0.dev0",
+    "video_token_id": 248057,
+    "vision_config": {
+        "deepstack_visual_indexes": [],
+        "depth": 24,
+        "hidden_act": "gelu_pytorch_tanh",
+        "hidden_size": 1024,
+        "in_channels": 3,
+        "initializer_range": 0.02,
+        "intermediate_size": 4096,
+        "model_type": "qwen3_5",
+        "num_heads": 16,
+        "num_position_embeddings": 2304,
+        "out_hidden_size": 2560,
+        "patch_size": 16,
+        "spatial_merge_size": 2,
+        "temporal_patch_size": 2
+    },
+    "vision_end_token_id": 248054,
+    "vision_start_token_id": 248053
+}

model.safetensors-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df547074dce70532a0493e5433152bd17a65efb89088cfabc2e7e2371a93d712
+size 5329398712

model.safetensors-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:590fbaac095dd31db886c322d9d2f7df47777966391acf306ddddc3e4e3a15ef
+size 3990429344

model.safetensors.index.json

@@ -0,0 +1,745 @@
+{
+  "metadata": {
+    "total_size": 9319737856
+  },
+  "weight_map": {
+    "model.language_model.embed_tokens.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "mtp.layers.0.mlp.down_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "mtp.layers.0.mlp.gate_proj.weight": "model.safetensors-00001-of-00002.safetensors",
+    "mtp.layers.0.mlp.up_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "mtp.layers.0.self_attn.q_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "mtp.fc.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "mtp.layers.0.self_attn.o_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.out_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "mtp.layers.0.self_attn.k_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "mtp.layers.0.self_attn.v_proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.pos_embed.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.patch_embed.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.conv1d.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "mtp.layers.0.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "mtp.pre_fc_norm_embedding.weight": "model.safetensors-00002-of-00002.safetensors",
+    "mtp.pre_fc_norm_hidden.weight": "model.safetensors-00002-of-00002.safetensors",
+    "mtp.layers.0.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "mtp.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.merger.norm.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.merger.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.visual.patch_embed.proj.bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "mtp.layers.0.self_attn.k_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "mtp.layers.0.self_attn.q_norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.norm.weight": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.A_log": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.1.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.17.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.22.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.10.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.24.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.12.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.13.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.18.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.2.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.16.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.21.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.20.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.14.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.29.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.8.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.4.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.25.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.28.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.26.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.6.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.30.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.5.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.9.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors",
+    "model.language_model.layers.0.linear_attn.dt_bias": "model.safetensors-00002-of-00002.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe000e3ed39ed12b8d2481d527d44f93c65d37e87645d2dcc80d1bf9d50d2927
+size 12807196

tokenizer_config.json

@@ -0,0 +1,305 @@
+{
+    "add_prefix_space": false,
+    "added_tokens_decoder": {
+        "248044": {
+            "content": "<|endoftext|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248045": {
+            "content": "<|im_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248046": {
+            "content": "<|im_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248047": {
+            "content": "<|object_ref_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248048": {
+            "content": "<|object_ref_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248049": {
+            "content": "<|box_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248050": {
+            "content": "<|box_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248051": {
+            "content": "<|quad_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248052": {
+            "content": "<|quad_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248053": {
+            "content": "<|vision_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248054": {
+            "content": "<|vision_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248055": {
+            "content": "<|vision_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248056": {
+            "content": "<|image_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248057": {
+            "content": "<|video_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248058": {
+            "content": "<tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248059": {
+            "content": "</tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248060": {
+            "content": "<|fim_prefix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248061": {
+            "content": "<|fim_middle|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248062": {
+            "content": "<|fim_suffix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248063": {
+            "content": "<|fim_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248064": {
+            "content": "<|repo_name|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248065": {
+            "content": "<|file_sep|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248066": {
+            "content": "<tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248067": {
+            "content": "</tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248068": {
+            "content": "<think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248069": {
+            "content": "</think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248070": {
+            "content": "<|audio_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248071": {
+            "content": "<|audio_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248072": {
+            "content": "<tts_pad>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248073": {
+            "content": "<tts_text_bos>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248074": {
+            "content": "<tts_text_eod>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248075": {
+            "content": "<tts_text_bos_single>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248076": {
+            "content": "<|audio_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        }
+    },
+    "additional_special_tokens": [
+        "<|im_start|>",
+        "<|im_end|>",
+        "<|object_ref_start|>",
+        "<|object_ref_end|>",
+        "<|box_start|>",
+        "<|box_end|>",
+        "<|quad_start|>",
+        "<|quad_end|>",
+        "<|vision_start|>",
+        "<|vision_end|>",
+        "<|vision_pad|>",
+        "<|image_pad|>",
+        "<|video_pad|>"
+    ],
+    "bos_token": null,
+    "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping %}\n        {%- for item in content %}\n            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain images.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Picture ' ~ image_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n            {%- elif 'video' in item or item.type == 'video' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain videos.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Video ' ~ video_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n            {%- elif 'text' in item %}\n                {{- item.text }}\n            {%- else %}\n                {{- raise_exception('Unexpected item type in content.') }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif content is none or content is undefined %}\n        {{- '' }}\n    {%- else %}\n        {{- raise_exception('Unexpected content type.') }}\n    {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n    {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n    {{- '<|im_start|>system\\n' }}\n    {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\" }}\n    {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- '\\n\\n' + content }}\n        {%- endif %}\n    {%- endif %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false)|trim %}\n        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n    {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, true)|trim %}\n    {%- if message.role == \"system\" %}\n        {%- if not loop.first %}\n            {{- raise_exception('System message must be at the beginning.') }}\n        {%- endif %}\n    {%- elif message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content|trim %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if tool_call.function is defined %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {%- if loop.first %}\n                    {%- if content|trim %}\n                        {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- else %}\n                        {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- endif %}\n                {%- else %}\n                    {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                {%- endif %}\n                {%- if tool_call.arguments is defined %}\n                    {%- for args_name, args_value in tool_call.arguments|items %}\n                        {{- '<parameter=' + args_name + '>\\n' }}\n                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n                        {{- args_value }}\n                        {{- '\\n</parameter>\\n' }}\n                    {%- endfor %}\n                {%- endif %}\n                {{- '</function>\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>\\n' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- else %}\n        {{- raise_exception('Unexpected message role.') }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- else %}\n        {{- '<think>\\n' }}\n    {%- endif %}\n{%- endif %}",
+    "clean_up_tokenization_spaces": false,
+    "eos_token": "<|endoftext|>",
+    "errors": "replace",
+    "model_max_length": 262144,
+    "pad_token": "<|endoftext|>",
+    "split_special_tokens": false,
+    "tokenizer_class": "Qwen2Tokenizer",
+    "unk_token": null,
+    "add_bos_token": false,
+    "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+    "extra_special_tokens": {
+        "audio_bos_token": "<|audio_start|>",
+        "audio_eos_token": "<|audio_end|>",
+        "audio_token": "<|audio_pad|>",
+        "image_token": "<|image_pad|>",
+        "video_token": "<|video_pad|>",
+        "vision_bos_token": "<|vision_start|>",
+        "vision_eos_token": "<|vision_end|>"
+    }
+}

video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 234881024,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}