Transfer model via script

.gitattributes

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

README.md

@@ -0,0 +1,290 @@
+---
+base_model:
+- DeepGlint-AI/rice-vit-large-patch14-560
+- Qwen/Qwen3-4B-Instruct-2507
+datasets:
+- lmms-lab/LLaVA-One-Vision-1.5-Mid-Training-85M
+- lmms-lab/LLaVA-OneVision-1.5-Insturct-Data
+- HuggingFaceM4/FineVision
+library_name: transformers
+license: apache-2.0
+pipeline_tag: image-text-to-text
+---
+
+<div align="center">
+
+<h1>LLaVA-OneVision-1.5: Fully Open-Source State-of-the-Art VLM Model</h1>
+
+
+<p>
+  <a href="https://huggingface.co/papers/2509.23661">
+    <img alt="Paper" src="https://img.shields.io/badge/Paper-b31b1b?style=for-the-badge&logo=arXiv&logoColor=white">
+  </a>
+  <a href="https://github.com/EvolvingLMMs-Lab/LLaVA-OneVision-1.5">
+    <img alt="Code" src="https://img.shields.io/badge/Code-181717?style=for-the-badge&logo=github&logoColor=white">
+  </a>
+  <a href="https://huggingface.co/datasets/mvp-lab/LLaVA-OneVision-1.5-Mid-Training-85M">
+    <img alt="Mid-Training Dataset" src="https://img.shields.io/badge/Mid--Training%20Dataset-f59e0b?style=for-the-badge&logo=huggingface&logoColor=white">
+  </a>
+  <a href="https://huggingface.co/datasets/mvp-lab/LLaVA-OneVision-1.5-Instruct-Data">
+    <img alt="Instruct Dataset" src="https://img.shields.io/badge/Instruct%20Dataset-3fb950?style=for-the-badge&logo=huggingface&logoColor=white">
+  </a>
+  <a href="https://huggingface.co/spaces/lmms-lab/LLaVA-OneVision-1.5">
+    <img alt="Demo" src="https://img.shields.io/badge/Demo-1f6feb?style=for-the-badge&logo=huggingface&logoColor=white">
+  </a>
+  <a href="https://huggingface.co/lmms-lab/LLaVA-OneVision-1.5-4B-Instruct/tensorboard">
+    <img alt="TensorBoard" src="https://img.shields.io/badge/TensorBoard-FF6F00?style=for-the-badge&logo=tensorflow&logoColor=white">
+  </a>
+</p>
+
+</div>
+
+
+
+## Introduction
+
+LLaVA-OneVision-1.5 is a fully open-source family of large multimodal models (LMMs) built to democratize multimodal training. Trained on native‑resolution images, it delivers state‑of‑the‑art performance at substantially lower cost. The project also releases high‑quality pretraining and SFT data, a complete and efficient training framework with recipes and configs, and comprehensive logs to support transparent, reproducible research.
+#### **Superior Performance**
+  - The model leads on multiple multimodal benchmarks and generally surpasses Qwen2.5-VL.
+  - Training on native-resolution images significantly improves its visual understanding.
+
+#### **High-Quality Data at Scale**
+  - The pretraining corpus comprises large-scale, concept-balanced, diverse, and high-quality captions curated with strict filtering and quality control.
+  - The instruction-tuning dataset is comprehensive and covers a wide range of tasks.
+
+#### **Ultra-Efficient Training Framework**
+  - The end-to-end training cost is about $16,000 on A100 GPUs at roughly $0.60 per GPU-hour.
+  - The system is built on Megatron-LM with support for MoE, FP8, and long-sequence parallelism, and the codebase is optimized for cost-effective scaling.
+
+#### **Fully Open Framework**
+  - The project releases high-quality pretraining and SFT datasets along with the complete training framework, configurations, and recipes.
+  - It also provides detailed training logs and metrics to enable reproducibility and community adoption.
+
+
+## Models
+
+| Model | HF Link | Training Log |
+|---|---|---|
+| LLaVA-OV-1.5-4B-Instruct | [🤗 HF / 4B-Instruct](https://huggingface.co/lmms-lab/LLaVA-OneVision-1.5-4B-Instruct) | [📈 Tensorboard](https://huggingface.co/lmms-lab/LLaVA-OneVision-1.5-4B-Instruct/tensorboard) |
+| LLaVA-OV-1.5-8B-Instruct | [🤗 HF / 8B-Instruct](https://huggingface.co/lmms-lab/LLaVA-OneVision-1.5-8B-Instruct) | [📈 Tensorboard](https://huggingface.co/lmms-lab/LLaVA-OneVision-1.5-8B-Instruct/tensorboard) |
+
+## Dataset
+
+| Description        | Link                                                                                                   | Status      |
+|--------------------|--------------------------------------------------------------------------------------------------------|-------------|
+| LLaVA-OneVision-1.5-Mid-Training-85M   | [🤗HF / Mid-Training 85M](https://huggingface.co/datasets/mvp-lab/LLaVA-OneVision-1.5-Mid-Training-85M) | Uploading…  |
+| LLaVA-OneVision-1.5-Instruct           | [🤗HF / Instruct-Data](https://huggingface.co/datasets/mvp-lab/LLaVA-OneVision-1.5-Instruct-Data)        | Available  |
+
+## Evaluation Results
+All evaluations were conducted using [lmms_eval](https://github.com/EvolvingLMMs-Lab/lmms-eval).
+
+![image](https://cdn-uploads.huggingface.co/production/uploads/655c70d331c4978366d4b2e6/J8oBYmQkTOC6pBNLgJn9d.png)
+
+## Quick Start with HuggingFace
+
+Here we show a code snippet to show you how to use the chat model with `transformers` and `qwen_vl_utils`:
+
+```python
+from transformers import AutoTokenizer, AutoProcessor, AutoModelForCausalLM
+from qwen_vl_utils import process_vision_info
+model_path = "lmms-lab/LLaVA-One-Vision-1.5-8B-Instruct"
+
+# default: Load the model on the available device(s)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path, torch_dtype="auto", device_map="auto", trust_remote_code=True
+)
+
+# default processer
+processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
+            },
+            {"type": "text", "text": "Describe this image."},
+        ],
+    }
+]
+
+# Preparation for inference
+text = processor.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True
+)
+image_inputs, video_inputs = process_vision_info(messages)
+inputs = processor(
+    text=[text],
+    images=image_inputs,
+    videos=video_inputs,
+    padding=True,
+    return_tensors="pt",
+)
+inputs = inputs.to("cuda")
+
+# Inference: Generation of the output
+generated_ids = model.generate(**inputs, max_new_tokens=1024)
+generated_ids_trimmed = [
+    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+]
+output_text = processor.batch_decode(
+    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+)
+print(output_text)
+```
+
+## Evaluation
+```
+# pip install git+https://github.com/EvolvingLMMs-Lab/lmms-eval.git  
+
+accelerate launch --num_processes=8 --main_process_port 12399 -m lmms_eval \
+    --model=llava_onevision1_5 \
+    --model_args=pretrained=lmms-lab/LLaVA-OneVision-1.5-8B-Instruct,attn_implementation=flash_attention_2,max_pixels=3240000 \
+    --tasks=mmmu_val,mmmu_pro_standard,mmbench_en_test,mmerealworld,mmerealworld_cn,ai2d,ai2d_no_mask,vstar_bench,chartqa,charxiv,docvqa_test,mathvista_testmini,mmstar,scienceqa \
+    --batch_size=1
+```
+
+
+
+### Mid-Training
+
+To improve model training efficiency, we implement offline sample packing:
+
+1.  Download the [**Mid-Training-85M Dataset**](https://huggingface.co/datasets/lmms-lab/LLaVA-One-Vision-1.5-Mid-Training-85M)
+2.  Pack the data into webdataset format, refer to [**Examples offlinepacking**](examples_offline_packing) and [**Offline Padding-Free Data Packing**](examples/llava_ov_1_5/sample_packing/README.md)
+
+
+### Instruct
+1.  Download the [**LLaVA-OneVision-1.5-Insturct-Data**](https://huggingface.co/datasets/lmms-lab/LLaVA-OneVision-1.5-Insturct-Data)
+2.  Convert the data into webdataset format, refer to [**Conversion for Mixed Instruction Data**](docs/sft_data_preprocessing.md)
+
+## Roadmaps
+
+Q4 2025 Key Deliverables:
+
+1.  **Ultra-efficient MoE Training**  
+2.  **Full Video Input LLM**  
+
+
+## Contributors
+Thanks so much to all of our amazing contributors!
+
+<!-- readme: collaborators,contributors,jiankangdeng/- -start -->
+<table>
+	<tbody>
+		<tr>
+            <td align="center">
+                <a href="https://github.com/fdcp">
+                    <img src="https://avatars.githubusercontent.com/u/15667917?v=4" width="80;" alt="fdcp"/>
+                    <br />
+                    <sub><b>fdcp</b></sub>
+                </a>
+            </td>
+            <td align="center">
+                <a href="https://github.com/anxiangsir">
+                    <img src="https://avatars.githubusercontent.com/u/31175974?v=4" width="80;" alt="anxiangsir"/>
+                    <br />
+                    <sub><b>anxiangsir</b></sub>
+                </a>
+            </td>
+            <td align="center">
+                <a href="https://github.com/yiyexy">
+                    <img src="https://avatars.githubusercontent.com/u/35927125?v=4" width="80;" alt="yiyexy"/>
+                    <br />
+                    <sub><b>yiyexy</b></sub>
+                </a>
+            </td>
+            <td align="center">
+                <a href="https://github.com/wideyard">
+                    <img src="https://avatars.githubusercontent.com/u/101321826?v=4" width="80;" alt="wideyard"/>
+                    <br />
+                    <sub><b>wideyard</b></sub>
+                </a>
+            </td>
+            <td align="center">
+                <a href="https://github.com/chengzheng345">
+                    <img src="https://avatars.githubusercontent.com/u/209475443?v=4" width="80;" alt="chengzheng345"/>
+                    <br />
+                    <sub><b>chengzheng345</b></sub>
+                </a>
+            </td>
+            <td align="center">
+                <a href="https://github.com/killTheHostage">
+                    <img src="https://avatars.githubusercontent.com/u/16442720?v=4" width="80;" alt="killTheHostage"/>
+                    <br />
+                    <sub><b>killTheHostage</b></sub>
+                </a>
+            </td>
+            <td align="center">
+                <a href="https://github.com/mathCrazyy">
+                    <img src="https://avatars.githubusercontent.com/u/20607153?v=4" width="80;" alt="mathCrazyy"/>
+                    <br />
+                    <sub><b>mathCrazyy</b></sub>
+                </a>
+            </td>
+            <td align="center">
+                <a href="https://github.com/yunglechao">
+                    <img src="https://avatars.githubusercontent.com/u/7631185?v=4" width="80;" alt="yunglechao"/>
+                    <br />
+                    <sub><b>yunglechao</b></sub>
+                </a>
+            </td>
+		</tr>
+		<tr>
+            <td align="center">
+                <a href="https://github.com/RobitYadda">
+                    <img src="https://avatars.githubusercontent.com/u/6811311?v=4" width="80;" alt="RobitYadda"/>
+                    <br />
+                    <sub><b>RobitYadda</b></sub>
+                </a>
+            </td>
+		</tr>
+	<tbody>
+</table>
+<!-- readme: collaborators,contributors,jiankangdeng/- -end -->
+
+## Citation
+
+If you find *LLaVA-OneVision-1.5* useful in your research, please consider to cite the following related papers:
+
+```
+@inproceedings{LLaVA-OneVision-1.5,
+  title={LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training},
+  author={An, Xiang and Xie, Yin and Yang, Kaicheng and Zhang, Wenkang and Zhao, Xiuwei and Cheng, Zheng and Wang, Yirui and Xu, Songcen and Chen, Changrui and Wu, Chunsheng and Tan, Huajie and Li, Chunyuan and Yang, Jing and Yu, Jie and Wang, Xiyao and Qin, Bin and Wang, Yumeng and Yan, Zizhen and Feng, Ziyong and Liu, Ziwei and Li, Bo and Deng, Jiankang},
+  booktitle={arxiv},  
+  year={2025}
+ }
+
+@inproceedings{xie2025region,
+  title={Region-based Cluster Discrimination for Visual Representation Learning},
+  author={Xie, Yin and Yang, Kaicheng and An, Xiang and Wu, Kun and Zhao, Yongle and Deng, Weimo and Ran, Zimin and Wang, Yumeng and Feng, Ziyong and Miles, Roy and Elezi, Ismail and Deng, Jiankang},
+  booktitle={ICCV},
+  year={2025}
+}
+
+@article{lillava,
+  title={LLaVA-OneVision: Easy Visual Task Transfer},
+  author={Li, Bo and Zhang, Yuanhan and Guo, Dong and Zhang, Renrui and Li, Feng and Zhang, Hao and Zhang, Kaichen and Zhang, Peiyuan and Li, Yanwei and Liu, Ziwei and Li, Chunyuan},
+  journal={Transactions on Machine Learning Research}
+  year={2024}
+}
+```
+
+## Acknowledgement
+
+We extend our sincere gratitude to **AIAK team of the** [**Baige AI computing platform**](https://cloud.baidu.com/product/aihc.html) **from Baidu AI Cloud** for providing the exceptional training framework. The outstanding capabilities of AIAK-Training-LLM and AIAK-Megatron have significantly accelerated our training process with remarkable efficiency. These cutting-edge frameworks have been instrumental in achieving our research goals. `To get full AIAK support, you can contact Baidu Cloud.`
+
+
+We also thank the maintainers and contributors of the following open-source projects, whose work greatly inspired and supported our research:
+
+- LLaVA: Large Language-and-Vision Assistant — [LLaVA](https://github.com/haotian-liu/LLaVA)
+- LLaVA-NeXT: Next-generation multi-modal assistant — [LLaVA-NeXT](https://github.com/LLaVA-VL/LLaVA-NeXT)
+- lmms-eval: A standardized evaluation framework for Large Multimodal Models — [lmms-eval](https://github.com/EvolvingLMMs-Lab/lmms-eval)
+- Megatron-LM: Efficient, scalable training for large language models — [Megatron-LM](https://github.com/NVIDIA/Megatron-LM)
+- Qwen2.5-VL: Strong vision-language foundation model — [Qwen2.5-VL](https://github.com/QwenLM/Qwen2.5-VL)
+- InternVL: Open-source large-scale vision-language foundation model — [InternVL](https://github.com/OpenGVLab/InternVL)
+- Qwen3: Next-generation Qwen LLM — [Qwen](https://github.com/QwenLM/Qwen)
+- MetaCLIP: Scalable contrastive pretraining — [MetaCLIP](https://github.com/facebookresearch/MetaCLIP)
+- FineVision: Open Data Is All You Need — [FineVision](https://huggingface.co/spaces/HuggingFaceM4/FineVision)

added_tokens.json

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

chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

config.json

@@ -0,0 +1,89 @@
+{
+  "architectures": [
+    "LLaVAOneVision1_5_ForConditionalGeneration"
+  ],
+  "image_token_id": 151655,
+  "model_type": "llavaonevision1_5",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "image_token_id": null,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 262144,
+    "max_window_layers": 36,
+    "model_type": "LLaVAOneVision1_5_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 5000000.0,
+    "sliding_window": null,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "video_token_id": null,
+    "vocab_size": 151936
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 24,
+    "embed_dim": 1024,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "layer_norm_eps": 1e-05,
+    "model_type": "rice_vit",
+    "num_heads": 16,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 1,
+    "text_hidden_size": 2560
+  },
+  "vocab_size": 151936
+}

configuration_llavaonevision1_5.py

@@ -0,0 +1,288 @@
+# coding=utf-8
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from transformers.configuration_utils import PretrainedConfig, layer_type_validation
+from transformers.modeling_rope_utils import rope_config_validation
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+class RiceConfig(PretrainedConfig):
+    model_type = "rice_vit"
+    base_config_key = "vision_config"
+
+    def __init__(
+        self,
+        depth=24,
+        embed_dim=1024,
+        hidden_size=1024,
+        hidden_act="gelu",
+        intermediate_size=4096,
+        num_heads=16,
+        in_channels=3,
+        patch_size=14,
+        spatial_merge_size=2,
+        temporal_patch_size=1,
+        initializer_range=0.02,
+        layer_norm_eps=1e-05,
+        text_hidden_size=2560,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        self.depth = depth
+        self.embed_dim = embed_dim
+        self.hidden_size = hidden_size
+        self.hidden_act = hidden_act
+        self.intermediate_size = intermediate_size
+        self.num_heads = num_heads
+        self.in_channels = in_channels
+        self.patch_size = patch_size
+        self.spatial_merge_size = spatial_merge_size
+        self.temporal_patch_size = temporal_patch_size
+        self.initializer_range = initializer_range
+        self.layer_norm_eps = layer_norm_eps
+        self.text_hidden_size = text_hidden_size
+
+
+class LLaVAOneVision1_5_TextConfig(PretrainedConfig):
+    r"""
+    Args:
+        vocab_size (`int`, *optional*, defaults to 152064):
+            Vocabulary size of the Qwen2VL model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`Qwen2VLModel`]
+        hidden_size (`int`, *optional*, defaults to 8192):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 29568):
+            Dimension of the MLP representations.
+        num_hidden_layers (`int`, *optional*, defaults to 80):
+            Number of hidden layers in the Transformer encoder.
+        num_attention_heads (`int`, *optional*, defaults to 64):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        num_key_value_heads (`int`, *optional*, defaults to 8):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `32`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 32768):
+            The maximum sequence length that this model might ever be used with.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-05):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether the model's input and output word embeddings should be tied.
+        rope_theta (`float`, *optional*, defaults to 1000000.0):
+            The base period of the RoPE embeddings.
+        use_sliding_window (`bool`, *optional*, defaults to `False`):
+            Whether to use sliding window attention.
+        sliding_window (`int`, *optional*, defaults to 4096):
+            Sliding window attention (SWA) window size. If not specified, will default to `4096`.
+        max_window_layers (`int`, *optional*, defaults to 80):
+            The number of layers that use SWA (Sliding Window Attention). The bottom layers use SWA while the top use full attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
+            and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
+            accordingly.
+            Expected contents:
+                `rope_type` (`str`):
+                    The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
+                    'llama3'], with 'default' being the original RoPE implementation.
+                `factor` (`float`, *optional*):
+                    Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
+                    most scaling types, a `factor` of x will enable the model to handle sequences of length x *
+                    original maximum pre-trained length.
+                `original_max_position_embeddings` (`int`, *optional*):
+                    Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
+                    pretraining.
+                `attention_factor` (`float`, *optional*):
+                    Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
+                    computation. If unspecified, it defaults to value recommended by the implementation, using the
+                    `factor` field to infer the suggested value.
+                `beta_fast` (`float`, *optional*):
+                    Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
+                    ramp function. If unspecified, it defaults to 32.
+                `beta_slow` (`float`, *optional*):
+                    Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
+                    ramp function. If unspecified, it defaults to 1.
+                `short_factor` (`List[float]`, *optional*):
+                    Only used with 'longrope'. The scaling factor to be applied to short contexts (<
+                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
+                    size divided by the number of attention heads divided by 2
+                `long_factor` (`List[float]`, *optional*):
+                    Only used with 'longrope'. The scaling factor to be applied to long contexts (<
+                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
+                    size divided by the number of attention heads divided by 2
+                `low_freq_factor` (`float`, *optional*):
+                    Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
+                `high_freq_factor` (`float`, *optional*):
+                    Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
+        image_token_id (`int`, *optional*):
+            Token index used as placeholder for image embeddings.
+        video_token_id (`int`, *optional*):
+            Token index used as placeholder for video embeddings.
+
+    """
+
+    model_type = "LLaVAOneVision1_5_text"
+    base_config_key = "text_config"
+    keys_to_ignore_at_inference = ["past_key_values"]
+    # Default tensor parallel plan for base model `Qwen2VL`
+    base_model_tp_plan = {
+        "layers.*.self_attn.q_proj": "colwise",
+        "layers.*.self_attn.k_proj": "colwise",
+        "layers.*.self_attn.v_proj": "colwise",
+        "layers.*.self_attn.o_proj": "rowwise",
+        "layers.*.mlp.gate_proj": "colwise",
+        "layers.*.mlp.up_proj": "colwise",
+        "layers.*.mlp.down_proj": "rowwise",
+    }
+    base_model_pp_plan = {
+        "embed_tokens": (["input_ids"], ["inputs_embeds"]),
+        "layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
+        "norm": (["hidden_states"], ["hidden_states"]),
+    }
+
+    def __init__(
+        self,
+        vocab_size=151936,
+        hidden_size=4096,
+        intermediate_size=12288,
+        num_hidden_layers=36,
+        num_attention_heads=32,
+        num_key_value_heads=8,
+        head_dim=128,
+        hidden_act="silu",
+        max_position_embeddings=32768,
+        initializer_range=0.02,
+        rms_norm_eps=1e-06,
+        use_cache=True,
+        tie_word_embeddings=False,
+        rope_theta=1000000.0,
+        attention_bias=False,
+        use_sliding_window=False,
+        sliding_window=None,
+        max_window_layers=36,
+        attention_dropout=0.0,
+        rope_scaling=None,
+        layer_types=None,
+        image_token_id=None,
+        video_token_id=None,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.use_sliding_window = use_sliding_window
+        self.sliding_window = sliding_window
+        self.max_window_layers = max_window_layers
+
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.head_dim = head_dim
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.attention_dropout = attention_dropout
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.tie_word_embeddings = tie_word_embeddings
+
+        # Validate the correctness of rotary position embeddings parameters
+        # BC: if there is a 'type' field, move it to 'rope_type'.
+        # and change type from 'mrope' to 'default' because `mrope` does default RoPE calculations
+        # one can set it to "linear"/"dynamic" etc. to have scaled RoPE
+        # TODO: @raushan update config in the hub
+        if self.rope_scaling is not None and "type" in self.rope_scaling:
+            if self.rope_scaling["type"] == "mrope":
+                self.rope_scaling["type"] = "default"
+            self.rope_scaling["rope_type"] = self.rope_scaling["type"]
+        rope_config_validation(self, ignore_keys={"mrope_section"})
+        self.image_token_id = image_token_id
+        self.video_token_id = video_token_id
+
+        self.layer_types = layer_types
+        if self.layer_types is None:
+            self.layer_types = [
+                "sliding_attention"
+                if self.sliding_window is not None and i >= self.max_window_layers
+                else "full_attention"
+                for i in range(self.num_hidden_layers)
+            ]
+        layer_type_validation(self.layer_types)
+
+        super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs)
+
+
+class Llavaonevision1_5Config(PretrainedConfig):
+    r"""
+    Args:
+        text_config (`Union[PreTrainedConfig, dict]`, *optional*, defaults to `LLaVAOneVision1_5_TextConfig`):
+            The config object or dictionary of the text backbone.
+        vision_config (`Union[PreTrainedConfig, dict]`,  *optional*, defaults to `LLaVAOneVision1_5_VisionConfig`):
+            The config object or dictionary of the vision backbone.
+        image_token_id (`int`, *optional*, defaults to 151655):
+            The image token index to encode the image prompt.
+        video_token_id (`int`, *optional*, defaults to 151656):
+            The video token index to encode the image prompt.
+    """
+
+    model_type = "llavaonevision1_5"
+    sub_configs = {"vision_config": RiceConfig, "text_config": LLaVAOneVision1_5_TextConfig}
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        text_config=None,
+        vision_config=None,
+        image_token_id=151655,
+        video_token_id=151656,
+        vocab_size=152064,
+        **kwargs,
+    ):
+        if isinstance(vision_config, dict):
+            self.vision_config = self.sub_configs["vision_config"](**vision_config)
+        elif vision_config is None:
+            self.vision_config = self.sub_configs["vision_config"]()
+
+        if isinstance(text_config, dict):
+            self.text_config = self.sub_configs["text_config"](**text_config)
+        elif text_config is None:
+            # For BC use all kwargs to init `TextConfig`
+            self.text_config = self.sub_configs["text_config"](**kwargs)
+
+        self.image_token_id = image_token_id
+        self.video_token_id = video_token_id
+        self.vocab_size = vocab_size
+
+        super().__init__(**kwargs)
+
+__all__ = ["Llavaonevision1_5Config", "LLaVAOneVision1_5_TextConfig"]

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151645,
+  "repetition_penalty": 1.05,
+  "temperature": 0.000001,
+  "_from_model_config": true,
+  "transformers_version": "4.53.0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f82cd85dce1f7a8438ff40d84a269a0fa99a0e34a848c7353e18aabd462fcdec
+size 4563695792

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d61103678768e54825eb35862e8b98e25db536bb1b4528e1822a50e5491cd286
+size 4919602640

model.safetensors.index.json

@@ -0,0 +1,705 @@
+{
+  "metadata": {
+    "total_size": 9483221056
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+    "visual.class_embedding": "model-00002-of-00002.safetensors",
+    "visual.class_pos_emb": "model-00002-of-00002.safetensors",
+    "visual.merger.ln_q.bias": "model-00002-of-00002.safetensors",
+    "visual.merger.ln_q.weight": "model-00002-of-00002.safetensors",
+    "visual.merger.mlp.0.bias": "model-00002-of-00002.safetensors",
+    "visual.merger.mlp.0.weight": "model-00002-of-00002.safetensors",
+    "visual.merger.mlp.2.bias": "model-00002-of-00002.safetensors",
+    "visual.merger.mlp.2.weight": "model-00002-of-00002.safetensors",
+    "visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
+    "visual.pre_layernorm.bias": "model-00002-of-00002.safetensors",
+    "visual.pre_layernorm.weight": "model-00002-of-00002.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 2560000,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 1
+}

special_tokens_map.json

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

tensorboard/instruct/events.out.tfevents.1758101239.109436.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543ddda0e04e35a6bb2e488bfdd641b2f84cbb814bacc29e0936ae780d0b0ab1
+size 92983372

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}