Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,8 @@ 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
+processor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+processor/.ipynb_checkpoints/tokenizer-checkpoint.json filter=lfs diff=lfs merge=lfs -text
+assets/boogu-infinity-teaser.png filter=lfs diff=lfs merge=lfs -text
+assets/dual_single_layers.pdf filter=lfs diff=lfs merge=lfs -text
+assets/dual_single_layers.png filter=lfs diff=lfs merge=lfs -text

mllm/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

mllm/README.md

@@ -0,0 +1,291 @@
+---
+license: apache-2.0
+pipeline_tag: image-text-to-text
+library_name: transformers
+base_model:
+- Qwen/Qwen3-VL-8B-Instruct
+base_model_relation: quantized
+---
+<a href="https://chat.qwenlm.ai/" target="_blank" style="margin: 2px;">
+    <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
+</a>
+
+# Qwen3-VL-8B-Instruct-FP8
+
+> This repository contains an FP8 quantized version of the [Qwen3-VL-8B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct) model. The quantization method is fine-grained fp8 quantization with block size of 128, and its performance metrics are nearly identical to those of the original BF16 model. Enjoy!
+
+
+Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
+
+This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.
+
+Available in Dense and MoE architectures that scale from edge to cloud, with Instruct and reasoning‑enhanced Thinking editions for flexible, on‑demand deployment.
+
+
+#### Key Enhancements:
+
+* **Visual Agent**: Operates PC/mobile GUIs—recognizes elements, understands functions, invokes tools, completes tasks.
+
+* **Visual Coding Boost**: Generates Draw.io/HTML/CSS/JS from images/videos.
+
+* **Advanced Spatial Perception**: Judges object positions, viewpoints, and occlusions; provides stronger 2D grounding and enables 3D grounding for spatial reasoning and embodied AI.
+
+* **Long Context & Video Understanding**: Native 256K context, expandable to 1M; handles books and hours-long video with full recall and second-level indexing.
+
+* **Enhanced Multimodal Reasoning**: Excels in STEM/Math—causal analysis and logical, evidence-based answers.
+
+* **Upgraded Visual Recognition**: Broader, higher-quality pretraining is able to “recognize everything”—celebrities, anime, products, landmarks, flora/fauna, etc.
+
+* **Expanded OCR**: Supports 32 languages (up from 19); robust in low light, blur, and tilt; better with rare/ancient characters and jargon; improved long-document structure parsing.
+
+* **Text Understanding on par with pure LLMs**: Seamless text–vision fusion for lossless, unified comprehension.
+
+
+#### Model Architecture Updates:
+
+<p align="center">
+    <img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/qwen3vl_arc.jpg" width="80%"/>
+<p>
+
+
+1. **Interleaved-MRoPE**: Full‑frequency allocation over time, width, and height via robust positional embeddings, enhancing long‑horizon video reasoning.
+
+2. **DeepStack**: Fuses multi‑level ViT features to capture fine‑grained details and sharpen image–text alignment.
+
+3. **Text–Timestamp Alignment:** Moves beyond T‑RoPE to precise, timestamp‑grounded event localization for stronger video temporal modeling.
+
+
+This is the weight repository for Qwen3-VL-8B-Instruct-FP8.
+
+
+---
+
+## Model Performance
+
+**Multimodal performance**
+
+![](https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/qwen3vl_4b_8b_vl_instruct.jpg)
+
+**Pure text performance**
+![](https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/qwen3vl_4b_8b_text_instruct.jpg)
+
+
+## Quickstart
+
+Currently, 🤗 Transformers does not support loading these weights directly. Stay tuned!
+
+We recommend deploying the model using vLLM or SGLang, with example launch commands provided below.  For details on the runtime environment and deployment, please refer to this [link](https://github.com/QwenLM/Qwen3-VL?tab=readme-ov-file#deployment). 
+
+### vLLM Inference
+
+Here we provide a code snippet demonstrating how to use vLLM to run inference with Qwen3-VL locally. For more details on efficient deployment with vLLM, please refer to the [community deployment guide](https://docs.vllm.ai/projects/recipes/en/latest/Qwen/Qwen3-VL.html).
+
+```python
+# -*- coding: utf-8 -*-
+import torch
+from qwen_vl_utils import process_vision_info
+from transformers import AutoProcessor
+from vllm import LLM, SamplingParams
+
+import os
+os.environ['VLLM_WORKER_MULTIPROC_METHOD'] = 'spawn'
+
+def prepare_inputs_for_vllm(messages, processor):
+    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    # qwen_vl_utils 0.0.14+ reqired
+    image_inputs, video_inputs, video_kwargs = process_vision_info(
+        messages,
+        image_patch_size=processor.image_processor.patch_size,
+        return_video_kwargs=True,
+        return_video_metadata=True
+    )
+    print(f"video_kwargs: {video_kwargs}")
+
+    mm_data = {}
+    if image_inputs is not None:
+        mm_data['image'] = image_inputs
+    if video_inputs is not None:
+        mm_data['video'] = video_inputs
+
+    return {
+        'prompt': text,
+        'multi_modal_data': mm_data,
+        'mm_processor_kwargs': video_kwargs
+    }
+
+
+if __name__ == '__main__':
+    # messages = [
+    #     {
+    #         "role": "user",
+    #         "content": [
+    #             {
+    #                 "type": "video",
+    #                 "video": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-VL/space_woaudio.mp4",
+    #             },
+    #             {"type": "text", "text": "这段视频有多长"},
+    #         ],
+    #     }
+    # ]
+
+    messages = [
+        {
+            "role": "user",
+            "content": [
+              {
+                  "type": "image",
+                  "image": "https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/receipt.png",
+              },
+              {"type": "text", "text": "Read all the text in the image."},
+            ],
+        }
+    ]
+
+    # TODO: change to your own checkpoint path
+    checkpoint_path = "Qwen/Qwen3-VL-8B-Instruct-FP8"
+    processor = AutoProcessor.from_pretrained(checkpoint_path)
+    inputs = [prepare_inputs_for_vllm(message, processor) for message in [messages]]
+
+    llm = LLM(
+        model=checkpoint_path,
+        trust_remote_code=True,
+        gpu_memory_utilization=0.70,
+        enforce_eager=False,
+        tensor_parallel_size=torch.cuda.device_count(),
+        seed=0
+    )
+
+    sampling_params = SamplingParams(
+        temperature=0,
+        max_tokens=1024,
+        top_k=-1,
+        stop_token_ids=[],
+    )
+
+    for i, input_ in enumerate(inputs):
+        print()
+        print('=' * 40)
+        print(f"Inputs[{i}]: {input_['prompt']=!r}")
+    print('\n' + '>' * 40)
+
+    outputs = llm.generate(inputs, sampling_params=sampling_params)
+    for i, output in enumerate(outputs):
+        generated_text = output.outputs[0].text
+        print()
+        print('=' * 40)
+        print(f"Generated text: {generated_text!r}")
+```
+
+###  SGLang Inference
+
+Here we provide a code snippet demonstrating how to use SGLang to run inference with Qwen3-VL locally.
+
+```python
+import time
+from PIL import Image
+from sglang import Engine
+from qwen_vl_utils import process_vision_info
+from transformers import AutoProcessor, AutoConfig
+
+if __name__ == "__main__":
+    # TODO: change to your own checkpoint path
+    checkpoint_path = "Qwen/Qwen3-VL-8B-Instruct-FP8"
+    processor = AutoProcessor.from_pretrained(checkpoint_path)
+
+    messages = [
+        {
+            "role": "user",
+            "content": [
+              {
+                  "type": "image",
+                  "image": "https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/receipt.png",
+              },
+              {"type": "text", "text": "Read all the text in the image."},
+            ],
+        }
+    ]
+
+    text = processor.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True
+    )
+
+    image_inputs, _ = process_vision_info(messages, image_patch_size=processor.image_processor.patch_size)
+
+    llm = Engine(
+        model_path=checkpoint_path,
+        enable_multimodal=True,
+        mem_fraction_static=0.8,
+        tp_size=torch.cuda.device_count(),
+        attention_backend="fa3"
+    )
+
+    start = time.time()
+    sampling_params = {"max_new_tokens": 1024}
+    response = llm.generate(prompt=text, image_data=image_inputs, sampling_params=sampling_params)
+    print(f"Response costs: {time.time() - start:.2f}s")
+    print(f"Generated text: {response['text']}")
+```
+
+### Generation Hyperparameters
+#### VL
+```bash
+export greedy='false'
+export top_p=0.8
+export top_k=20
+export temperature=0.7
+export repetition_penalty=1.0
+export presence_penalty=1.5
+export out_seq_length=16384
+```
+
+#### Text
+```bash
+export greedy='false'
+export top_p=1.0
+export top_k=40
+export repetition_penalty=1.0
+export presence_penalty=2.0
+export temperature=1.0
+export out_seq_length=32768
+```
+
+
+
+## Citation
+
+If you find our work helpful, feel free to give us a cite.
+
+```
+@misc{qwen3technicalreport,
+      title={Qwen3 Technical Report}, 
+      author={Qwen Team},
+      year={2025},
+      eprint={2505.09388},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2505.09388}, 
+}
+
+@article{Qwen2.5-VL,
+  title={Qwen2.5-VL Technical Report},
+  author={Bai, Shuai and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Song, Sibo and Dang, Kai and Wang, Peng and Wang, Shijie and Tang, Jun and Zhong, Humen and Zhu, Yuanzhi and Yang, Mingkun and Li, Zhaohai and Wan, Jianqiang and Wang, Pengfei and Ding, Wei and Fu, Zheren and Xu, Yiheng and Ye, Jiabo and Zhang, Xi and Xie, Tianbao and Cheng, Zesen and Zhang, Hang and Yang, Zhibo and Xu, Haiyang and Lin, Junyang},
+  journal={arXiv preprint arXiv:2502.13923},
+  year={2025}
+}
+
+@article{Qwen2VL,
+  title={Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution},
+  author={Wang, Peng and Bai, Shuai and Tan, Sinan and Wang, Shijie and Fan, Zhihao and Bai, Jinze and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Fan, Yang and Dang, Kai and Du, Mengfei and Ren, Xuancheng and Men, Rui and Liu, Dayiheng and Zhou, Chang and Zhou, Jingren and Lin, Junyang},
+  journal={arXiv preprint arXiv:2409.12191},
+  year={2024}
+}
+
+@article{Qwen-VL,
+  title={Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond},
+  author={Bai, Jinze and Bai, Shuai and Yang, Shusheng and Wang, Shijie and Tan, Sinan and Wang, Peng and Lin, Junyang and Zhou, Chang and Zhou, Jingren},
+  journal={arXiv preprint arXiv:2308.12966},
+  year={2023}
+}
+```

mllm/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
+}

mllm/config.json

@@ -0,0 +1,322 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0.dev0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 27,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "fmt": "e4m3",
+    "quant_method": "fp8",
+    "ignored_layers": [
+      "lm_head",
+      "model.visual.merger.linear_fc1",
+      "model.visual.merger.linear_fc2",
+      "model.visual.merger.norm",
+      "model.visual.patch_embed.proj",
+      "model.visual.pos_embed",
+      "visual.merger.linear_fc1",
+      "visual.merger.linear_fc2",
+      "visual.merger.norm",
+      "visual.patch_embed.proj",
+      "visual.pos_embed",
+      "model.visual.blocks.0.attn.proj",
+      "model.visual.blocks.0.attn.qkv",
+      "model.visual.blocks.0.mlp.linear_fc1",
+      "model.visual.blocks.0.mlp.linear_fc2",
+      "visual.blocks.0.attn.proj",
+      "visual.blocks.0.attn.qkv_proj",
+      "visual.blocks.0.mlp.linear_fc1",
+      "visual.blocks.0.mlp.linear_fc2",
+      "model.visual.blocks.1.attn.proj",
+      "model.visual.blocks.1.attn.qkv",
+      "model.visual.blocks.1.mlp.linear_fc1",
+      "model.visual.blocks.1.mlp.linear_fc2",
+      "visual.blocks.1.attn.proj",
+      "visual.blocks.1.attn.qkv_proj",
+      "visual.blocks.1.mlp.linear_fc1",
+      "visual.blocks.1.mlp.linear_fc2",
+      "model.visual.blocks.2.attn.proj",
+      "model.visual.blocks.2.attn.qkv",
+      "model.visual.blocks.2.mlp.linear_fc1",
+      "model.visual.blocks.2.mlp.linear_fc2",
+      "visual.blocks.2.attn.proj",
+      "visual.blocks.2.attn.qkv_proj",
+      "visual.blocks.2.mlp.linear_fc1",
+      "visual.blocks.2.mlp.linear_fc2",
+      "model.visual.blocks.3.attn.proj",
+      "model.visual.blocks.3.attn.qkv",
+      "model.visual.blocks.3.mlp.linear_fc1",
+      "model.visual.blocks.3.mlp.linear_fc2",
+      "visual.blocks.3.attn.proj",
+      "visual.blocks.3.attn.qkv_proj",
+      "visual.blocks.3.mlp.linear_fc1",
+      "visual.blocks.3.mlp.linear_fc2",
+      "model.visual.blocks.4.attn.proj",
+      "model.visual.blocks.4.attn.qkv",
+      "model.visual.blocks.4.mlp.linear_fc1",
+      "model.visual.blocks.4.mlp.linear_fc2",
+      "visual.blocks.4.attn.proj",
+      "visual.blocks.4.attn.qkv_proj",
+      "visual.blocks.4.mlp.linear_fc1",
+      "visual.blocks.4.mlp.linear_fc2",
+      "model.visual.blocks.5.attn.proj",
+      "model.visual.blocks.5.attn.qkv",
+      "model.visual.blocks.5.mlp.linear_fc1",
+      "model.visual.blocks.5.mlp.linear_fc2",
+      "visual.blocks.5.attn.proj",
+      "visual.blocks.5.attn.qkv_proj",
+      "visual.blocks.5.mlp.linear_fc1",
+      "visual.blocks.5.mlp.linear_fc2",
+      "model.visual.blocks.6.attn.proj",
+      "model.visual.blocks.6.attn.qkv",
+      "model.visual.blocks.6.mlp.linear_fc1",
+      "model.visual.blocks.6.mlp.linear_fc2",
+      "visual.blocks.6.attn.proj",
+      "visual.blocks.6.attn.qkv_proj",
+      "visual.blocks.6.mlp.linear_fc1",
+      "visual.blocks.6.mlp.linear_fc2",
+      "model.visual.blocks.7.attn.proj",
+      "model.visual.blocks.7.attn.qkv",
+      "model.visual.blocks.7.mlp.linear_fc1",
+      "model.visual.blocks.7.mlp.linear_fc2",
+      "visual.blocks.7.attn.proj",
+      "visual.blocks.7.attn.qkv_proj",
+      "visual.blocks.7.mlp.linear_fc1",
+      "visual.blocks.7.mlp.linear_fc2",
+      "model.visual.blocks.8.attn.proj",
+      "model.visual.blocks.8.attn.qkv",
+      "model.visual.blocks.8.mlp.linear_fc1",
+      "model.visual.blocks.8.mlp.linear_fc2",
+      "visual.blocks.8.attn.proj",
+      "visual.blocks.8.attn.qkv_proj",
+      "visual.blocks.8.mlp.linear_fc1",
+      "visual.blocks.8.mlp.linear_fc2",
+      "model.visual.blocks.9.attn.proj",
+      "model.visual.blocks.9.attn.qkv",
+      "model.visual.blocks.9.mlp.linear_fc1",
+      "model.visual.blocks.9.mlp.linear_fc2",
+      "visual.blocks.9.attn.proj",
+      "visual.blocks.9.attn.qkv_proj",
+      "visual.blocks.9.mlp.linear_fc1",
+      "visual.blocks.9.mlp.linear_fc2",
+      "model.visual.blocks.10.attn.proj",
+      "model.visual.blocks.10.attn.qkv",
+      "model.visual.blocks.10.mlp.linear_fc1",
+      "model.visual.blocks.10.mlp.linear_fc2",
+      "visual.blocks.10.attn.proj",
+      "visual.blocks.10.attn.qkv_proj",
+      "visual.blocks.10.mlp.linear_fc1",
+      "visual.blocks.10.mlp.linear_fc2",
+      "model.visual.blocks.11.attn.proj",
+      "model.visual.blocks.11.attn.qkv",
+      "model.visual.blocks.11.mlp.linear_fc1",
+      "model.visual.blocks.11.mlp.linear_fc2",
+      "visual.blocks.11.attn.proj",
+      "visual.blocks.11.attn.qkv_proj",
+      "visual.blocks.11.mlp.linear_fc1",
+      "visual.blocks.11.mlp.linear_fc2",
+      "model.visual.blocks.12.attn.proj",
+      "model.visual.blocks.12.attn.qkv",
+      "model.visual.blocks.12.mlp.linear_fc1",
+      "model.visual.blocks.12.mlp.linear_fc2",
+      "visual.blocks.12.attn.proj",
+      "visual.blocks.12.attn.qkv_proj",
+      "visual.blocks.12.mlp.linear_fc1",
+      "visual.blocks.12.mlp.linear_fc2",
+      "model.visual.blocks.13.attn.proj",
+      "model.visual.blocks.13.attn.qkv",
+      "model.visual.blocks.13.mlp.linear_fc1",
+      "model.visual.blocks.13.mlp.linear_fc2",
+      "visual.blocks.13.attn.proj",
+      "visual.blocks.13.attn.qkv_proj",
+      "visual.blocks.13.mlp.linear_fc1",
+      "visual.blocks.13.mlp.linear_fc2",
+      "model.visual.blocks.14.attn.proj",
+      "model.visual.blocks.14.attn.qkv",
+      "model.visual.blocks.14.mlp.linear_fc1",
+      "model.visual.blocks.14.mlp.linear_fc2",
+      "visual.blocks.14.attn.proj",
+      "visual.blocks.14.attn.qkv_proj",
+      "visual.blocks.14.mlp.linear_fc1",
+      "visual.blocks.14.mlp.linear_fc2",
+      "model.visual.blocks.15.attn.proj",
+      "model.visual.blocks.15.attn.qkv",
+      "model.visual.blocks.15.mlp.linear_fc1",
+      "model.visual.blocks.15.mlp.linear_fc2",
+      "visual.blocks.15.attn.proj",
+      "visual.blocks.15.attn.qkv_proj",
+      "visual.blocks.15.mlp.linear_fc1",
+      "visual.blocks.15.mlp.linear_fc2",
+      "model.visual.blocks.16.attn.proj",
+      "model.visual.blocks.16.attn.qkv",
+      "model.visual.blocks.16.mlp.linear_fc1",
+      "model.visual.blocks.16.mlp.linear_fc2",
+      "visual.blocks.16.attn.proj",
+      "visual.blocks.16.attn.qkv_proj",
+      "visual.blocks.16.mlp.linear_fc1",
+      "visual.blocks.16.mlp.linear_fc2",
+      "model.visual.blocks.17.attn.proj",
+      "model.visual.blocks.17.attn.qkv",
+      "model.visual.blocks.17.mlp.linear_fc1",
+      "model.visual.blocks.17.mlp.linear_fc2",
+      "visual.blocks.17.attn.proj",
+      "visual.blocks.17.attn.qkv_proj",
+      "visual.blocks.17.mlp.linear_fc1",
+      "visual.blocks.17.mlp.linear_fc2",
+      "model.visual.blocks.18.attn.proj",
+      "model.visual.blocks.18.attn.qkv",
+      "model.visual.blocks.18.mlp.linear_fc1",
+      "model.visual.blocks.18.mlp.linear_fc2",
+      "visual.blocks.18.attn.proj",
+      "visual.blocks.18.attn.qkv_proj",
+      "visual.blocks.18.mlp.linear_fc1",
+      "visual.blocks.18.mlp.linear_fc2",
+      "model.visual.blocks.19.attn.proj",
+      "model.visual.blocks.19.attn.qkv",
+      "model.visual.blocks.19.mlp.linear_fc1",
+      "model.visual.blocks.19.mlp.linear_fc2",
+      "visual.blocks.19.attn.proj",
+      "visual.blocks.19.attn.qkv_proj",
+      "visual.blocks.19.mlp.linear_fc1",
+      "visual.blocks.19.mlp.linear_fc2",
+      "model.visual.blocks.20.attn.proj",
+      "model.visual.blocks.20.attn.qkv",
+      "model.visual.blocks.20.mlp.linear_fc1",
+      "model.visual.blocks.20.mlp.linear_fc2",
+      "visual.blocks.20.attn.proj",
+      "visual.blocks.20.attn.qkv_proj",
+      "visual.blocks.20.mlp.linear_fc1",
+      "visual.blocks.20.mlp.linear_fc2",
+      "model.visual.blocks.21.attn.proj",
+      "model.visual.blocks.21.attn.qkv",
+      "model.visual.blocks.21.mlp.linear_fc1",
+      "model.visual.blocks.21.mlp.linear_fc2",
+      "visual.blocks.21.attn.proj",
+      "visual.blocks.21.attn.qkv_proj",
+      "visual.blocks.21.mlp.linear_fc1",
+      "visual.blocks.21.mlp.linear_fc2",
+      "model.visual.blocks.22.attn.proj",
+      "model.visual.blocks.22.attn.qkv",
+      "model.visual.blocks.22.mlp.linear_fc1",
+      "model.visual.blocks.22.mlp.linear_fc2",
+      "visual.blocks.22.attn.proj",
+      "visual.blocks.22.attn.qkv_proj",
+      "visual.blocks.22.mlp.linear_fc1",
+      "visual.blocks.22.mlp.linear_fc2",
+      "model.visual.blocks.23.attn.proj",
+      "model.visual.blocks.23.attn.qkv",
+      "model.visual.blocks.23.mlp.linear_fc1",
+      "model.visual.blocks.23.mlp.linear_fc2",
+      "visual.blocks.23.attn.proj",
+      "visual.blocks.23.attn.qkv_proj",
+      "visual.blocks.23.mlp.linear_fc1",
+      "visual.blocks.23.mlp.linear_fc2",
+      "model.visual.blocks.24.attn.proj",
+      "model.visual.blocks.24.attn.qkv",
+      "model.visual.blocks.24.mlp.linear_fc1",
+      "model.visual.blocks.24.mlp.linear_fc2",
+      "visual.blocks.24.attn.proj",
+      "visual.blocks.24.attn.qkv_proj",
+      "visual.blocks.24.mlp.linear_fc1",
+      "visual.blocks.24.mlp.linear_fc2",
+      "model.visual.blocks.25.attn.proj",
+      "model.visual.blocks.25.attn.qkv",
+      "model.visual.blocks.25.mlp.linear_fc1",
+      "model.visual.blocks.25.mlp.linear_fc2",
+      "visual.blocks.25.attn.proj",
+      "visual.blocks.25.attn.qkv_proj",
+      "visual.blocks.25.mlp.linear_fc1",
+      "visual.blocks.25.mlp.linear_fc2",
+      "model.visual.blocks.26.attn.proj",
+      "model.visual.blocks.26.attn.qkv",
+      "model.visual.blocks.26.mlp.linear_fc1",
+      "model.visual.blocks.26.mlp.linear_fc2",
+      "visual.blocks.26.attn.proj",
+      "visual.blocks.26.attn.qkv_proj",
+      "visual.blocks.26.mlp.linear_fc1",
+      "visual.blocks.26.mlp.linear_fc2",
+      "model.visual.deepstack_merger_list.0.linear_fc1",
+      "model.visual.deepstack_merger_list.0.linear_fc2",
+      "model.visual.deepstack_merger_list.0.norm",
+      "visual.deepstack_merger_list.0.linear_fc1",
+      "visual.deepstack_merger_list.0.linear_fc2",
+      "visual.deepstack_merger_list.0.norm",
+      "model.visual.deepstack_merger_list.1.linear_fc1",
+      "model.visual.deepstack_merger_list.1.linear_fc2",
+      "model.visual.deepstack_merger_list.1.norm",
+      "visual.deepstack_merger_list.1.linear_fc1",
+      "visual.deepstack_merger_list.1.linear_fc2",
+      "visual.deepstack_merger_list.1.norm",
+      "model.visual.deepstack_merger_list.2.linear_fc1",
+      "model.visual.deepstack_merger_list.2.linear_fc2",
+      "model.visual.deepstack_merger_list.2.norm",
+      "visual.deepstack_merger_list.2.linear_fc1",
+      "visual.deepstack_merger_list.2.linear_fc2",
+      "visual.deepstack_merger_list.2.norm"
+    ],
+    "modules_to_not_convert":[
+      "lm_head",
+      "model.visual"
+    ],
+    "weight_block_size": [
+      128,
+      128
+    ]
+  }
+}

mllm/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "top_k": 20,
+  "top_p": 0.8,
+  "repetition_penalty": 1.0,
+  "temperature": 0.7,
+  "transformers_version": "4.56.0"
+}

mllm/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2dea2e85e643ef7045c31a485a426631a1e0a84e463f8b2c7e9c6682a06eafd
+size 5363407552

mllm/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc64ec934af27a7007d265014e907aff9e16658d409e5cd4cf79869bf2bd8c1
+size 5226891960

mllm/model.safetensors.index.json

@@ -0,0 +1,1007 @@
+{
+  "metadata": {},
+  "weight_map": {
+    "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "lm_head.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.norm.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.24.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.24.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.24.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.24.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.24.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.24.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.24.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.24.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.25.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.25.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.25.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.25.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.25.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.25.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.25.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.25.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.26.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.26.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.26.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.26.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.26.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.26.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.26.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.26.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+    "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight_scale_inv": "model-00002-of-00002.safetensors"
+  }
+}

mllm/preprocessor_config.json

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

mllm/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

mllm/video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "patch_size": 16,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}

model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "BooguImagePipeline",
+  "_diffusers_version": "0.35.2",
+  "mllm": [
+    "transformers",
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "processor": [
+    "transformers",
+    "Qwen3VLProcessor"
+  ],
+  "scheduler": [
+    "scheduling_flow_match_euler_discrete_time_shifting",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "transformer": [
+    "boogu.models.transformers.transformer_boogu",
+    "BooguImageTransformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]    
+}

processor/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

processor/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- 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 %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- 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 %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

processor/preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_pixels": null,
+  "merge_size": 2,
+  "min_pixels": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2
+}

processor/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
+  }
+}

processor/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

processor/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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": 262144,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

processor/video_preprocessor_config.json

@@ -0,0 +1,41 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "fps": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "merge_size": 2,
+  "min_frames": 4,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}

scheduler/scheduler_config.json

@@ -0,0 +1,9 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.33.1",
+  "do_shift": true,
+  "dynamic_time_shift": false,
+  "time_shift_version": "v1",
+  "seq_len":  4096,
+  "num_train_timesteps": 1000
+}

scheduler/scheduling_flow_match_euler_discrete_time_shifting.py

@@ -0,0 +1,32 @@
+# Copyright (C) 2026 Boogu Team.
+# This repository is a fork by Boogu Team; modifications have been made.
+
+"""
+Compatibility entry point for the released Boogu base pipeline scheduler.
+
+The inference code in this repository owns the canonical scheduler
+implementation. Keeping another full copy here easily causes drift between the
+released pipeline package and the active codebase. Diffusers only needs this
+module to expose `FlowMatchEulerDiscreteScheduler` for `model_index.json`, so
+this file intentionally re-exports the repository class.
+"""
+
+try:
+    from boogu.schedulers.scheduling_flow_match_euler_discrete_time_shifting import (
+        FlowMatchEulerDiscreteScheduler,
+        FlowMatchEulerDiscreteSchedulerOutput,
+    )
+except ModuleNotFoundError as exc:
+    if exc.name != "boogu":
+        raise
+    raise ModuleNotFoundError(
+        "Failed to import the canonical Boogu scheduler implementation. "
+        "Run inference from the Boogu-Image repository root "
+        "or add that directory to PYTHONPATH before loading the pipeline."
+    ) from exc
+
+
+__all__ = [
+    "FlowMatchEulerDiscreteScheduler",
+    "FlowMatchEulerDiscreteSchedulerOutput",
+]

transformer/config.json

@@ -0,0 +1,44 @@
+{
+  "_class_name": "BooguImageTransformer2DModel",
+  "_diffusers_version": "0.38.0",
+  "axes_dim_rope": [
+    40,
+    40,
+    40
+  ],
+  "axes_lens": [
+    2048,
+    1664,
+    1664
+  ],
+  "ffn_dim_multiplier": null,
+  "hidden_size": 3360,
+  "in_channels": 16,
+  "instruction_feature_configs": {
+    "instruction_feat_dim": 4096,
+    "num_instruction_feature_layers": 1,
+    "reduce_type": "mean"
+  },
+  "multiple_of": 256,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 28,
+  "num_double_stream_layers": 8,
+  "num_kv_heads": 7,
+  "num_layers": 40,
+  "num_refiner_layers": 2,
+  "out_channels": null,
+  "patch_size": 2,
+  "prompt_tuning_configs": {
+    "ffn_dim_multiplier": null,
+    "hidden_size": 4096,
+    "multiple_of": 256,
+    "norm_eps": 1e-05,
+    "num_attention_heads": 32,
+    "num_kv_heads": 8,
+    "num_layers": 0,
+    "num_trainable_prompt_tokens": 0,
+    "use_causal_mask": true,
+    "use_prompt_tuning": false
+  },
+  "timestep_scale": 1000.0
+}

transformer/diffusion_pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8dab95addd81b9f8fc7405984ce97ff772d7615264327f1a347bec4cf8f89d7
+size 9989936201

transformer/diffusion_pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9df4894273f55ba7d6ac812ad97d206a29714734a89f0e8a3b1ec9df17421928
+size 333466293

transformer/diffusion_pytorch_model.bin.index.json

@@ -0,0 +1,949 @@
+{
+  "metadata": {
+    "total_size": 10322841088
+  },
+  "weight_map": {
+    "context_refiner.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.0.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.0.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.0.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.0.norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.0.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.1.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.1.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.1.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.1.norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "context_refiner.1.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_instruct_attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_instruct_attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_instruct_attn.processor.img_out.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_instruct_attn.processor.img_to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_instruct_attn.processor.img_to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_instruct_attn.processor.img_to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_instruct_attn.processor.instruct_out.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_instruct_attn.processor.instruct_to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_instruct_attn.processor.instruct_to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_instruct_attn.processor.instruct_to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_instruct_attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_norm2.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_norm2.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_norm2.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_norm3.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_norm3.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_norm3.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_self_attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_self_attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_self_attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.img_self_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.instruct_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.instruct_feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.instruct_feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.instruct_feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.instruct_ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.instruct_ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.instruct_norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.instruct_norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.instruct_norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.instruct_norm2.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.instruct_norm2.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.0.instruct_norm2.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_instruct_attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_instruct_attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_instruct_attn.processor.img_out.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_instruct_attn.processor.img_to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_instruct_attn.processor.img_to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_instruct_attn.processor.img_to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_instruct_attn.processor.instruct_out.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_instruct_attn.processor.instruct_to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_instruct_attn.processor.instruct_to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_instruct_attn.processor.instruct_to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_instruct_attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_norm2.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_norm2.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_norm2.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_norm3.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_norm3.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_norm3.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_self_attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_self_attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_self_attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.img_self_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.instruct_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.instruct_feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.instruct_feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.instruct_feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.instruct_ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.instruct_ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.instruct_norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.instruct_norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.instruct_norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.instruct_norm2.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.instruct_norm2.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.1.instruct_norm2.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_instruct_attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_instruct_attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_instruct_attn.processor.img_out.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_instruct_attn.processor.img_to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_instruct_attn.processor.img_to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_instruct_attn.processor.img_to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_instruct_attn.processor.instruct_out.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_instruct_attn.processor.instruct_to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_instruct_attn.processor.instruct_to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_instruct_attn.processor.instruct_to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_instruct_attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_norm2.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_norm2.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_norm2.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_norm3.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_norm3.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_norm3.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_self_attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_self_attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_self_attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.img_self_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.instruct_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.instruct_feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.instruct_feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.instruct_feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.instruct_ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.instruct_ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.instruct_norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.instruct_norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.instruct_norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.instruct_norm2.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.instruct_norm2.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.2.instruct_norm2.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_instruct_attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_instruct_attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_instruct_attn.processor.img_out.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_instruct_attn.processor.img_to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_instruct_attn.processor.img_to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_instruct_attn.processor.img_to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_instruct_attn.processor.instruct_out.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_instruct_attn.processor.instruct_to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_instruct_attn.processor.instruct_to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_instruct_attn.processor.instruct_to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_instruct_attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_norm2.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_norm2.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_norm2.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_norm3.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_norm3.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_norm3.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_self_attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_self_attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_self_attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.img_self_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.instruct_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.instruct_feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.instruct_feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.instruct_feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.instruct_ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.instruct_ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.instruct_norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.instruct_norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.instruct_norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.instruct_norm2.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.instruct_norm2.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.3.instruct_norm2.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_instruct_attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_instruct_attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_instruct_attn.processor.img_out.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_instruct_attn.processor.img_to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_instruct_attn.processor.img_to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_instruct_attn.processor.img_to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_instruct_attn.processor.instruct_out.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_instruct_attn.processor.instruct_to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_instruct_attn.processor.instruct_to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_instruct_attn.processor.instruct_to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_instruct_attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_norm2.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_norm2.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_norm2.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_norm3.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_norm3.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_norm3.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_self_attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_self_attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_self_attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.img_self_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.instruct_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.instruct_feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.instruct_feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.instruct_feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.instruct_ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.instruct_ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.instruct_norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.instruct_norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.instruct_norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.instruct_norm2.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.instruct_norm2.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.4.instruct_norm2.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_instruct_attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_instruct_attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_instruct_attn.processor.img_out.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_instruct_attn.processor.img_to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_instruct_attn.processor.img_to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_instruct_attn.processor.img_to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_instruct_attn.processor.instruct_out.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_instruct_attn.processor.instruct_to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_instruct_attn.processor.instruct_to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_instruct_attn.processor.instruct_to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_instruct_attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_norm2.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_norm2.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_norm2.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_norm3.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_norm3.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_norm3.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_self_attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_self_attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_self_attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.img_self_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.instruct_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.instruct_feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.instruct_feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.instruct_feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.instruct_ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.instruct_ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.instruct_norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.instruct_norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.instruct_norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.instruct_norm2.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.instruct_norm2.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.5.instruct_norm2.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_instruct_attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_instruct_attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_instruct_attn.processor.img_out.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_instruct_attn.processor.img_to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_instruct_attn.processor.img_to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_instruct_attn.processor.img_to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_instruct_attn.processor.instruct_out.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_instruct_attn.processor.instruct_to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_instruct_attn.processor.instruct_to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_instruct_attn.processor.instruct_to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_instruct_attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_norm2.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_norm2.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_norm2.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_norm3.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_norm3.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_norm3.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_self_attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_self_attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_self_attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.img_self_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.instruct_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.instruct_feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.instruct_feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.instruct_feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.instruct_ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.instruct_ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.instruct_norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.instruct_norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.instruct_norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.instruct_norm2.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.instruct_norm2.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.6.instruct_norm2.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_instruct_attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_instruct_attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_instruct_attn.processor.img_out.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_instruct_attn.processor.img_to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_instruct_attn.processor.img_to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_instruct_attn.processor.img_to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_instruct_attn.processor.instruct_out.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_instruct_attn.processor.instruct_to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_instruct_attn.processor.instruct_to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_instruct_attn.processor.instruct_to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_instruct_attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_norm2.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_norm2.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_norm2.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_norm3.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_norm3.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_norm3.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_self_attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_self_attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_self_attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.img_self_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.instruct_attn_norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.instruct_feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.instruct_feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.instruct_feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.instruct_ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.instruct_ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.instruct_norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.instruct_norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.instruct_norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.instruct_norm2.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.instruct_norm2.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "double_stream_layers.7.instruct_norm2.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "image_index_embedding": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.0.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.0.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.0.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.0.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.0.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.0.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.0.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.1.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.1.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.1.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.1.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.1.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.1.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "noise_refiner.1.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "norm_out.linear_1.bias": "diffusion_pytorch_model-00002-of-00002.bin",
+    "norm_out.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "norm_out.linear_2.bias": "diffusion_pytorch_model-00002-of-00002.bin",
+    "norm_out.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "ref_image_patch_embedder.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_patch_embedder.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.0.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.0.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.0.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.0.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.0.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.0.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.0.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.1.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.1.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.1.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.1.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.1.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.1.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "ref_image_refiner.1.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.0.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.0.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.0.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.0.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.0.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.0.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.0.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.1.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.1.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.1.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.1.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.1.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.1.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.1.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.10.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.10.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.10.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.10.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.10.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.10.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.10.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.10.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.10.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.10.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.10.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.10.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.10.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.10.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.10.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.11.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.11.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.11.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.11.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.11.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.11.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.11.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.11.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.11.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.11.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.11.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.11.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.11.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.11.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.11.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.12.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.12.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.12.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.12.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.12.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.12.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.12.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.12.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.12.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.12.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.12.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.12.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.12.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.12.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.12.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.13.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.13.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.13.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.13.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.13.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.13.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.13.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.13.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.13.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.13.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.13.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.13.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.13.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.13.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.13.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.14.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.14.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.14.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.14.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.14.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.14.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.14.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.14.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.14.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.14.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.14.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.14.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.14.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.14.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.14.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.15.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.15.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.15.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.15.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.15.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.15.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.15.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.15.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.15.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.15.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.15.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.15.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.15.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.15.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.15.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.16.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.16.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.16.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.16.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.16.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.16.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.16.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.16.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.16.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.16.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.16.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.16.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.16.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.16.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.16.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.17.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.17.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.17.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.17.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.17.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.17.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.17.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.17.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.17.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.17.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.17.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.17.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.17.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.17.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.17.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.18.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.18.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.18.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.18.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.18.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.18.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.18.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.18.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.18.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.18.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.18.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.18.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.18.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.18.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.18.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.19.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.19.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.19.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.19.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.19.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.19.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.19.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.19.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.19.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.19.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.19.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.19.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.19.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.19.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.19.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.2.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.2.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.2.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.2.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.2.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.2.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.2.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.2.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.2.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.20.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.20.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.20.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.20.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.20.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.20.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.20.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.20.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.20.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.20.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.20.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.20.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.20.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.20.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.20.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.21.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.21.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.21.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.21.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.21.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.21.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.21.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.21.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.21.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.21.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.21.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.21.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.21.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.21.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.21.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.22.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.22.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.22.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.22.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.22.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.22.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.22.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.22.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.22.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.22.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.22.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.22.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.22.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.22.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.22.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.23.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.23.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.23.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.23.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.23.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.23.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.23.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.23.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.23.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.23.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.23.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.23.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.23.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.23.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.23.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.24.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.24.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.24.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.24.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.24.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.24.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.24.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.24.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.24.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.24.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.24.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.24.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.24.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.24.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.24.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.25.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.25.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.25.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.25.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.25.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.25.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.25.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.25.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.25.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.25.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.25.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.25.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.25.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.25.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.25.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.26.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.26.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.26.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.26.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.26.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.26.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.26.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.26.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.26.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.26.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.26.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.26.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.26.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.26.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.26.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.27.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.27.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.27.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.27.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.27.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.27.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.27.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.27.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.27.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.27.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.27.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.27.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.27.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.27.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.27.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.28.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.28.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.28.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.28.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.28.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.28.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.28.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.28.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.28.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.28.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.28.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.28.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.28.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.28.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.28.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.29.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.29.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.29.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.29.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.29.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.29.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.29.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.29.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.29.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.29.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.29.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.29.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.29.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.29.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.29.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.3.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.3.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.3.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.3.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.3.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.3.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.3.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.3.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.3.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.30.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.30.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.30.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.30.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.30.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.30.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.30.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.30.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.30.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.30.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.30.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.30.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.30.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.30.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.30.norm2.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.31.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.31.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.31.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.31.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.31.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.31.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.31.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.31.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.31.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.31.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.31.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.31.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.31.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.31.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.31.norm2.weight": "diffusion_pytorch_model-00002-of-00002.bin",
+    "single_stream_layers.4.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.4.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.4.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.4.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.4.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.4.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.4.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.4.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.4.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.4.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.4.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.4.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.4.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.4.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.4.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.5.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.5.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.5.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.5.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.5.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.5.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.5.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.5.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.5.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.5.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.5.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.5.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.5.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.5.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.5.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.6.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.6.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.6.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.6.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.6.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.6.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.6.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.6.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.6.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.6.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.6.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.6.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.6.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.6.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.6.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.7.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.7.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.7.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.7.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.7.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.7.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.7.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.7.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.7.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.7.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.7.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.7.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.7.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.7.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.7.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.8.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.8.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.8.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.8.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.8.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.8.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.8.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.8.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.8.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.8.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.8.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.8.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.8.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.8.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.8.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.9.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.9.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.9.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.9.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.9.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.9.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.9.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.9.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.9.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.9.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.9.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.9.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.9.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.9.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "single_stream_layers.9.norm2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "time_caption_embed.caption_embedder.0.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "time_caption_embed.caption_embedder.1.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "time_caption_embed.caption_embedder.1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "time_caption_embed.timestep_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "time_caption_embed.timestep_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "time_caption_embed.timestep_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "time_caption_embed.timestep_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.bin",
+    "x_embedder.bias": "diffusion_pytorch_model-00001-of-00002.bin",
+    "x_embedder.weight": "diffusion_pytorch_model-00001-of-00002.bin"
+  }
+}

transformer/transformer_boogu.py

@@ -0,0 +1,32 @@
+# Copyright (C) 2026 Boogu Team.
+# This repository is a fork by Boogu Team; modifications have been made.
+
+"""
+Compatibility entry point for the released Boogu base pipeline transformer.
+
+The inference code in this repository owns the canonical transformer
+implementation. Keeping another full copy here easily causes drift between the
+released pipeline package and the active codebase. Diffusers only needs this
+module to expose `BooguImageTransformer2DModel` for
+`model_index.json`, so this file intentionally re-exports the repository class.
+"""
+
+try:
+    from boogu.models.transformers.transformer_boogu import (
+        BooguImageTransformer2DModel,
+        PromptEmbedding,
+    )
+except ModuleNotFoundError as exc:
+    if exc.name != "boogu":
+        raise
+    raise ModuleNotFoundError(
+        "Failed to import the canonical Boogu transformer implementation. "
+        "Run inference from the Boogu-Image repository root "
+        "or add that directory to PYTHONPATH before loading the pipeline."
+    ) from exc
+
+
+__all__ = [
+    "BooguImageTransformer2DModel",
+    "PromptEmbedding",
+]

vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.35.2",
+  "_name_or_path": "/share_2/luoxin/modelscope/hub/models/FLUX.1-dev",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 16,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.3611,
+  "shift_factor": 0.1159,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": false,
+  "use_quant_conv": false
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c717328c8ad41faab2ccfd52ae17332505c6833cf176aad56e7b58f2c4d4c94
+size 335306212