初始化项目，由ModelHub XC社区提供模型

Model: BAAI/Emu3-Gen-hf
Source: Original Platform

.gitattributes

@@ -0,0 +1,44 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00006-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00007-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00008-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,147 @@
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: image-text-to-text
+inference: false
+tags:
+- vision
+- image-text-to-text
+arxiv: 2409.18869
+---
+
+
+<div align='center'>
+<h1>Emu3: Next-Token Prediction is All You Need</h1h1>
+<h3></h3>
+
+[Emu3 Team, BAAI](https://www.baai.ac.cn/english.html)
+
+</div>
+
+
+<div align='left'>
+<img src="https://github.com/baaivision/Emu3/blob/main/assets/arch.png?raw=True" class="interpolation-image" alt="arch." height="80%" width="70%" />
+</div>
+
+Below is the model card of Emu3-Chat model, which is adapted from the original Emu3 model card that you can find [here](https://huggingface.co/BAAI/Emu3-Gen).
+
+
+## Model details
+
+**Model type:**
+Emu3 is an open-source multimodal models trained  with next-token prediction task. By tokenizing images and text into a discrete space, Emu3 is trained as a single transformer from scratch on a mixture of multimodal sequences.
+It is an auto-regressive language model, based on the transformer architecture.
+
+**Paper or resources for more information:**
+https://github.com/baaivision/Emu3
+
+
+## Highlights
+
+- **Emu3** is capable of generating high-quality images following the text input, by simply predicting the next vision token. The model naturally supports flexible resolutions and styles.
+- **Emu3** shows strong vision-language understanding capabilities to see the physical world and provides coherent text responses. Notably, this capability is achieved without depending on a CLIP and a pretrained LLM.
+- **Emu3** simply generates a video causally by predicting the next token in a video sequence, unlike the video diffusion model as in Sora. With a video in context, Emu3 can also naturally extend the video and predict what will happen next. 
+- **Emu3** outperforms several well-established task-specific models in both generation and perception tasks, surpassing flagship open models such as SDXL, LLaVA-1.6 and OpenSora-1.2, while eliminating the need for diffusion or compositional architectures.
+
+
+## How to use the model
+
+First, make sure to have `transformers >= 4.48.0`. 
+Below is an example script to run generation in `float16` precision on a GPU device:
+
+```python
+import requests
+from PIL import Image
+
+import torch
+from transformers import AutoProcessor, Emu3ForConditionalGeneration
+
+model_id = "BAAI/Emu3-Gen-hf"
+model = Emu3ForConditionalGeneration.from_pretrained(
+    model_id, 
+    torch_dtype=torch.float16, 
+    low_cpu_mem_usage=True,
+    device_map="cuda:0",
+)
+
+processor = AutoProcessor.from_pretrained(model_id)
+inputs = processor(
+    text=["a portrait of young girl. masterpiece, film grained, best quality."],
+    padding=True,
+    return_tensors="pt",
+    return_for_image_generation=True,
+).to(model.device)
+
+image_sizes = inputs.pop("image_sizes")
+HEIGHT, WIDTH = image_sizes[0]
+VISUAL_TOKENS = model.vocabulary_mapping.image_tokens
+
+def prefix_allowed_tokens_fn(batch_id, input_ids):
+    height, width = HEIGHT, WIDTH
+    visual_tokens = VISUAL_TOKENS
+    image_wrapper_token_id = torch.tensor([processor.tokenizer.image_wrapper_token_id], device=model.device)
+    eoi_token_id = torch.tensor([processor.tokenizer.eoi_token_id], device=model.device)
+    eos_token_id = torch.tensor([processor.tokenizer.eos_token_id], device=model.device)
+    pad_token_id = torch.tensor([processor.tokenizer.pad_token_id], device=model.device)
+    eof_token_id = torch.tensor([processor.tokenizer.eof_token_id], device=model.device)
+    eol_token_id = processor.tokenizer.encode("<|extra_200|>", return_tensors="pt")[0]
+
+    position = torch.nonzero(input_ids == image_wrapper_token_id, as_tuple=True)[0][0]
+    offset = input_ids.shape[0] - position
+    if offset % (width + 1) == 0:
+        return (eol_token_id,)
+    elif offset == (width + 1) * height + 1:
+        return (eof_token_id,)
+    elif offset == (width + 1) * height + 2:
+        return (eoi_token_id,)
+    elif offset == (width + 1) * height + 3:
+        return (eos_token_id,)
+    elif offset > (width + 1) * height + 3:
+        return (pad_token_id,)
+    else:
+        return visual_tokens
+
+out = model.generate(
+    **inputs,
+    max_new_tokens=9_000,
+    prefix_allowed_tokens_fn=prefix_allowed_tokens_fn,
+    do_sample=True,
+)
+
+image = model.decode_image_tokens(out.sequences[:, inputs.input_ids.shape[1]: ], height=HEIGHT, width=WIDTH)
+images = processor.postprocess(list(image.float()), return_tensors="PIL.Image.Image")
+for i, image in enumerate(images['pixel_values']):
+    image.save(f"result{i}.png")
+  
+```
+
+### Model optimization
+
+
+#### Use Flash-Attention 2 to further speed-up generation
+
+First make sure to install `flash-attn`. Refer to the [original repository of Flash Attention](https://github.com/Dao-AILab/flash-attention) regarding that package installation. Simply change the snippet above with: 
+
+```diff
+model = Emu3ForConditionalGeneration.from_pretrained(
+    model_id, 
+    torch_dtype=torch.float16, 
+    low_cpu_mem_usage=True,
++   attn_implementation="flash_attention_2",
+    device_map="cuda:0",
+)
+```
+
+# Citation
+```
+@misc{wang2024emu3nexttokenpredictionneed,
+      title={Emu3: Next-Token Prediction is All You Need}, 
+      author={Xinlong Wang and Xiaosong Zhang and Zhengxiong Luo and Quan Sun and Yufeng Cui and Jinsheng Wang and Fan Zhang and Yueze Wang and Zhen Li and Qiying Yu and Yingli Zhao and Yulong Ao and Xuebin Min and Tao Li and Boya Wu and Bo Zhao and Bowen Zhang and Liangdong Wang and Guang Liu and Zheqi He and Xi Yang and Jingjing Liu and Yonghua Lin and Tiejun Huang and Zhongyuan Wang},
+      year={2024},
+      eprint={2409.18869},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2409.18869}, 
+}
+```

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{% if message['role'] != 'system' %}{{ message['role'].upper() + ': '}}{% endif %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] + ' '}}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] + ' '}}{% endgeneration %}{% endfor %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'ASSISTANT:' }}{% endif %}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% for message in messages %}{% if message['role'] != 'system' %}{{ message['role'].upper() + ': '}}{% endif %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] + ' '}}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] + ' '}}{% endgeneration %}{% endfor %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'ASSISTANT:' }}{% endif %}"
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "image-text-to-text", "allow_remote": true}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "do_sample": true,
+  "eos_token_id": 151850,
+  "max_new_tokens": 50000,
+  "pad_token_id": 151643,
+  "top_k": 2048,
+  "transformers_version": "4.53.0.dev0"
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:482870907a43f7cfd0240579049f12bbe848bd3ba8e346f6ebb61b25ef76f674
+size 4937517928

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3eaf1793568ff5929b99236951e71b9a624f6c734c6104ca13d15c07aba09b9
+size 4832007968

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f688ebc58dfc2ac385e4d6b87e38dda253dff9fe23c8c8b4811d3117fca5ac8f
+size 4999813680

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30fde22981ba7d706f86478f3f32a33d9bd63ec7e168d02860eaeddcb5735744
+size 4999813712

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00af28b0448f30c29138311dfb41a3d9a607907f91f2346a45fa8315174d9439
+size 4832008016

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee40365b2724ad5b05536fc60d0ab93f71fdfc5e1ee74380f1078d76c1cff013
+size 4999813704

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87cbb81f894dc637e50f1eb44c710b406eef97a3f29b55be8d361c56369ea4af
+size 2425287956

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b38d7edfa038674a74e612fe1e5df526b9845ace7efa38e92ef9033f03acee
+size 3024846976

model.safetensors.index.json

@@ -0,0 +1,793 @@
+{
+  "metadata": {
+    "total_size": 35051007548
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00008-of-00008.safetensors",
+    "model.text_model.embed_tokens.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.17.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.17.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.17.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.18.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.18.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.text_model.layers.2.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.2.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.2.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.text_model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.21.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.22.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.22.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.22.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.22.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.22.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.22.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.22.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.23.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.23.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.23.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.23.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.24.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.24.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.text_model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.26.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.26.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.26.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.26.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.26.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.27.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.27.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.27.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.27.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.27.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.27.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.27.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.27.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.27.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.28.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.28.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.28.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.28.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.3.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.30.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.text_model.layers.30.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.text_model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.30.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.text_model.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.text_model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.text_model.layers.31.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.text_model.layers.31.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.text_model.layers.31.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.text_model.layers.31.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.text_model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.text_model.layers.31.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.text_model.layers.31.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.text_model.layers.31.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.text_model.layers.31.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.text_model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.7.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.7.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.7.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.text_model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.8.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.8.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.8.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.8.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.8.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.8.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.text_model.norm.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.conv_in.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.conv_in.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.conv_out.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.conv_out.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.attn_1.k_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.attn_1.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.attn_1.out_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.attn_1.out_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.attn_1.q_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.attn_1.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.attn_1.v_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.attn_1.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.attn_norm.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.attn_norm.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.attn_norm.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.attn_norm.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.attn_norm.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.attn_norm.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_1.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_1.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_1.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_1.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_1.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_1.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_1.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_1.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_1.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_1.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_1.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_1.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_1.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_1.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_1.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_1.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_2.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_2.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_2.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_2.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_2.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_2.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_2.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_2.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_2.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_2.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_2.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_2.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_2.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_2.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_2.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.middle_block.block_2.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.norm_out.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.norm_out.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.norm_out.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.norm_out.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.norm_out.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.norm_out.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_conv.0.conv.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_conv.0.conv.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_conv.1.conv.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_conv.1.conv.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.0.conv1.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.0.conv1.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.0.conv2.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.0.conv2.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.0.norm1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.0.norm1.num_batches_tracked": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.0.norm1.running_mean": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.0.norm1.running_var": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.0.norm1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.0.norm2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.0.norm2.num_batches_tracked": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.0.norm2.running_mean": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.0.norm2.running_var": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.0.norm2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.1.conv1.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.1.conv1.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.1.conv2.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.1.conv2.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.1.norm1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.1.norm1.num_batches_tracked": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.1.norm1.running_mean": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.1.norm1.running_var": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.1.norm1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.1.norm2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.1.norm2.num_batches_tracked": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.1.norm2.running_mean": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.1.norm2.running_var": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.time_res_stack.1.norm2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.nin_shortcut.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.nin_shortcut.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.0.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.1.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.1.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.1.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.1.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.1.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.1.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.1.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.1.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.1.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.1.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.1.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.1.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.1.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.1.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.1.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.1.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.2.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.2.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.2.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.2.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.2.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.2.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.2.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.2.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.2.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.2.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.2.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.2.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.2.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.2.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.2.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.0.block.2.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.0.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.0.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.0.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.0.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.0.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.0.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.0.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.0.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.0.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.0.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.0.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.0.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.0.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.0.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.0.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.0.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.1.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.1.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.1.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.1.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.1.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.1.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.1.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.1.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.1.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.1.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.1.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.1.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.1.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.1.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.1.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.1.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.2.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.2.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.2.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.2.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.2.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.2.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.2.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.2.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.2.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.2.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.2.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.2.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.2.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.2.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.2.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.block.2.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.upsample.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.1.upsample.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.nin_shortcut.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.nin_shortcut.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.0.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.1.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.1.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.1.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.1.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.1.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.1.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.1.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.1.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.1.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.1.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.1.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.1.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.1.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.1.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.1.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.1.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.2.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.2.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.2.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.2.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.2.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.2.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.2.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.2.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.2.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.2.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.2.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.2.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.2.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.2.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.2.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.block.2.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.upsample.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.2.upsample.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.0.k_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.0.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.0.out_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.0.out_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.0.q_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.0.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.0.v_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.0.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.1.k_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.1.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.1.out_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.1.out_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.1.q_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.1.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.1.v_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.1.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.2.k_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.2.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.2.out_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.2.out_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.2.q_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.2.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.2.v_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn.2.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.0.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.0.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.0.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.0.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.0.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.0.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.attn_norms.2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.0.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.0.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.0.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.0.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.0.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.0.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.0.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.0.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.0.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.0.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.0.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.0.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.0.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.0.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.0.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.0.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.1.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.1.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.1.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.1.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.1.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.1.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.1.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.1.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.1.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.1.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.1.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.1.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.1.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.1.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.1.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.1.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.2.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.2.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.2.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.2.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.2.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.2.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.2.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.2.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.2.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.2.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.2.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.2.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.2.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.2.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.2.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.block.2.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.upsample.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.decoder.up_block.up.3.upsample.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.conv_in.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.conv_in.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.conv_out.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.conv_out.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.block.0.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.block.0.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.block.0.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.block.0.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.block.0.norm1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.block.0.norm1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.block.0.norm2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.block.0.norm2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.block.1.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.block.1.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.block.1.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.block.1.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.block.1.norm1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.block.1.norm1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.block.1.norm2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.block.1.norm2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.downsample.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.0.downsample.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.0.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.0.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.0.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.0.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.0.nin_shortcut.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.0.nin_shortcut.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.0.norm1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.0.norm1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.0.norm2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.0.norm2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.1.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.1.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.1.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.1.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.1.norm1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.1.norm1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.1.norm2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.block.1.norm2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.downsample.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.1.downsample.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.block.0.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.block.0.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.block.0.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.block.0.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.block.0.norm1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.block.0.norm1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.block.0.norm2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.block.0.norm2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.block.1.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.block.1.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.block.1.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.block.1.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.block.1.norm1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.block.1.norm1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.block.1.norm2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.block.1.norm2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.downsample.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.2.downsample.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn.0.k_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn.0.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn.0.out_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn.0.out_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn.0.q_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn.0.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn.0.v_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn.0.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn.1.k_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn.1.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn.1.out_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn.1.out_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn.1.q_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn.1.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn.1.v_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn.1.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn_norms.0.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn_norms.0.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn_norms.1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.attn_norms.1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.0.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.0.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.0.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.0.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.0.nin_shortcut.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.0.nin_shortcut.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.0.norm1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.0.norm1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.0.norm2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.0.norm2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.1.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.1.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.1.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.1.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.1.norm1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.1.norm1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.1.norm2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.down_block.down.3.block.1.norm2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.attn_1.k_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.attn_1.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.attn_1.out_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.attn_1.out_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.attn_1.q_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.attn_1.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.attn_1.v_proj.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.attn_1.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.attn_norm.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.attn_norm.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.block_1.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.block_1.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.block_1.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.block_1.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.block_1.norm1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.block_1.norm1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.block_1.norm2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.block_1.norm2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.block_2.conv1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.block_2.conv1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.block_2.conv2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.block_2.conv2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.block_2.norm1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.block_2.norm1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.block_2.norm2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.middle_block.block_2.norm2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.norm_out.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.norm_out.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_conv.0.conv.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_conv.0.conv.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_conv.1.conv.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_conv.1.conv.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.0.conv1.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.0.conv1.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.0.conv2.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.0.conv2.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.0.norm1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.0.norm1.num_batches_tracked": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.0.norm1.running_mean": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.0.norm1.running_var": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.0.norm1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.0.norm2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.0.norm2.num_batches_tracked": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.0.norm2.running_mean": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.0.norm2.running_var": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.0.norm2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.1.conv1.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.1.conv1.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.1.conv2.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.1.conv2.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.1.norm1.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.1.norm1.num_batches_tracked": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.1.norm1.running_mean": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.1.norm1.running_var": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.1.norm1.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.1.norm2.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.1.norm2.num_batches_tracked": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.1.norm2.running_mean": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.1.norm2.running_var": "model-00007-of-00008.safetensors",
+    "model.vqmodel.encoder.time_res_stack.1.norm2.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.post_quant_conv.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.post_quant_conv.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.quant_conv.conv.bias": "model-00007-of-00008.safetensors",
+    "model.vqmodel.quant_conv.conv.weight": "model-00007-of-00008.safetensors",
+    "model.vqmodel.quantize.embedding.weight": "model-00007-of-00008.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,30 @@
+{
+  "auto_map": {
+    "AutoImageProcessor": "BAAI/Emu3-VisionTokenizer--image_processing_emu3visionvq.Emu3VisionVQImageProcessor"
+  },
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Emu3ImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_pixels": 1048576,
+  "min_pixels": 262144,
+  "processor_class": "Emu3Processor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_pixels": 1048576,
+    "min_pixels": 262144
+  },
+  "spatial_factor": 8
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_token": "<image>",
+  "processor_class": "Emu3Processor"
+}

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "boi_token": "<|image start|>",
+  "bos_token": {
+    "content": "<|extra_203|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eof_token": "<|extra_201|>",
+  "eoi_token": "<|image end|>",
+  "eos_token": {
+    "content": "<|extra_204|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image>",
+  "image_wrapper_token": "<|image token|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c37805242c128a8cef44a0eb543fe94a6e6b0b82ff10588da527893171ae7cff
+size 19360696