Upload folder using huggingface_hub

.gitattributes

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

LICENSE

@@ -0,0 +1,53 @@
+SeaLLMs LICENSE AGREEMENT 
+SeaLLMs Release Date: December 5, 2023
+
+By clicking to agree or by using or distributing any portion or element of the SeaLLMs Materials, you will be deemed to have recognized and accepted the content of this Agreement, which is effective immediately.
+
+1. Definitions
+    a. This SeaLLMs LICENSE AGREEMENT (this "Agreement") shall mean the terms and conditions for use, reproduction, distribution and modification of the Materials as defined by this Agreement.
+    b.  "We"(or "Us") shall mean Damo Academy.
+    c.  "You" (or "Your") shall mean a natural person or legal entity exercising the rights granted by this Agreement and/or using the Materials for any purpose and in any field of use.
+    d.  "Third Parties" shall mean individuals or legal entities that are not under common control with Us or You. 
+    e. "SeaLLMs" shall mean the large language models (including different model versions), and software and 
+algorithms, consisting of trained model weights, parameters (including optimizer states), machine-learning model code, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Us.
+    f. "Materials" shall mean, collectively, Damo Academy's proprietary SeaLLMs and Documentation (and any portion thereof) made available under this Agreement.
+    g.  "Source" form shall mean the preferred form for making modifications, including but not limited to model source code, documentation source, and configuration files.
+    h. "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation,
+ and conversions to other media types.
+
+2. Grant of Rights
+You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Damo Academy's intellectual property or other rights owned by Us embodied in the Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Materials.  
+
+3. Redistribution
+You may reproduce and distribute copies of the Materials or derivative works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions:
+    a. You shall give any other recipients of the Materials or derivative works a copy of this Agreement; 
+    b. You shall cause any modified files to carry prominent notices stating that You changed the files; 
+    c. You shall retain in all copies of the Materials that You distribute the following attribution notices  within a "Notice" text file distributed as a part of such copies:"SeaLLMs is licensed under the SeaLLMs LICENSE AGREEMENT, Copyright (c) Damo Academy. All Rights Reserved."; and
+    d. You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such derivative works as a whole, provided Your use, reproduction, and distribution of the work otherwise complies with the terms and conditions of this Agreement.
+
+4. Restrictions
+If you are commercially using the Materials, and your product or service has more than 100 million monthly active users, You shall request a license from Us. You cannot exercise your rights under this Agreement without our express authorization.
+
+5. Rules of use
+    a. The Materials may be subject to export controls or restrictions in China, the United States or other countries or regions. You shall comply with applicable laws and regulations in your use of the Materials. 
+    b. You can not use the Materials or any output therefrom to improve any other large language model (excluding SeaLLMs or derivative works thereof).  
+
+6. Intellectual Property
+    a. We retain ownership of all intellectual property rights in and to the Materials and derivatives made by or for Us. Conditioned upon compliance with the terms and conditions of this Agreement, with respect to any derivative works and modifications of the Materials that are made by you, you are and will be the owner of such derivative works and modifications. 
+    b. No trademark license is granted to use the trade names, trademarks, service marks, or product names of Us, except as required to fulfill notice requirements under this Agreement or as required for reasonable and customary use in describing and redistributing the Materials. 
+    c. If you commence a lawsuit or other proceedings (including a cross-claim or counterclaim in a lawsuit) against Us or any entity alleging that the Materials or any output therefrom, or any part of the foregoing, infringe any intellectual property or other right owned or licensable by you, then all licences granted to you under this Agreement shall terminate as of the date such lawsuit or other proceeding is commenced or brought.
+
+7. Disclaimer of Warranty and Limitation of Liability
+
+    a. We are not obligated to support, update, provide training for, or develop any further version of the SeaLLMs Model or to grant any license thereto. 
+    b. THE MATERIALS ARE PROVIDED "AS IS" WITHOUT ANY EXPRESS OR IMPLIED WARRANTY OF ANY KIND INCLUDING WARRANTIES OF MERCHANTABILITY, NONINFRINGEMENT, OR FITNESS FOR A PARTICULAR PURPOSE. WE MAKE NO WARRANTY AND ASSUME NO RESPONSIBILITY FOR THE SAFETY OR STABILITY OF THE MATERIALS AND ANY OUTPUT THEREFROM.
+    c. IN NO EVENT SHALL WE BE LIABLE TO YOU FOR ANY DAMAGES, INCLUDING, BUT NOT LIMITED TO ANY DIRECT, OR INDIRECT, SPECIAL OR CONSEQUENTIAL DAMAGES ARISING FROM YOUR USE OR INABILITY TO USE THE MATERIALS OR ANY OUTPUT OF IT, NO MATTER HOW IT’S CAUSED.
+    d. You will indemnify and hold harmless Us from and against any claim by any third party arising out of or related to your use or distribution of the Materials.
+
+8. Survival and Termination. 
+    a. The term of this Agreement shall commence upon your acceptance of this Agreement or access to the Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein.
+    b. We may terminate this Agreement if you breach any of the terms or conditions of this Agreement. Upon termination of this Agreement, you must delete and cease use of the Materials. Sections 7 and 9 shall survive the termination of this Agreement.
+
+9. Governing Law and Jurisdiction. 
+    a. This Agreement and any dispute arising out of or relating to it will be governed by the laws of China, without regard to conflict of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. 
+    b. The People's Courts in Hangzhou City shall have exclusive jurisdiction over any dispute arising out of this Agreement.

README.md

@@ -0,0 +1,31 @@
+---
+library_name: transformers
+license: mit
+language:
+- th
+pipeline_tag: image-to-text
+base_model: Salesforce/blip2-opt-2.7b-coco
+---
+
+## THAI-BLIP-2
+ fine-tuned for image captioning task from [blip2-opt-2.7b-coco](Salesforce/blip2-opt-2.7b-coco) with MSCOCO2017 thai caption.
+
+## How to use:
+  ```python
+  from transformers import Blip2ForConditionalGeneration, Blip2Processor
+  from PIL import Image
+  import torch
+  
+  device = "cuda" if torch.cuda.is_available() else "cpu"
+  
+  processor = Blip2Processor.from_pretrained("kkatiz/THAI-BLIP-2")
+  model = Blip2ForConditionalGeneration.from_pretrained("kkatiz/THAI-BLIP-2", device_map=device, torch_dtype=torch.bfloat16)
+
+  img = Image.open("Your image...")
+  inputs = processor(images=img, return_tensors="pt").to(device, torch.bfloat16)
+
+  # Adjust your `max_length`
+  generated_ids = model.generate(**inputs, max_length=20)
+  generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
+  print(generated_text)
+  ```

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "./final_model",
+  "architectures": [
+    "Blip2ForConditionalGeneration"
+  ],
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "model_type": "blip-2",
+  "num_query_tokens": 32,
+  "pad_token_id": 0,
+  "qformer_config": {
+    "classifier_dropout": null,
+    "model_type": "blip_2_qformer"
+  },
+  "text_config": {
+    "_name_or_path": "SeaLLMs/SeaLLM-7B-v2.5",
+    "architectures": [
+      "GemmaForCausalLM"
+    ],
+    "attention_bias": false,
+    "eos_token_id": 1,
+    "head_dim": 256,
+    "hidden_act": "gelu",
+    "hidden_activation": null,
+    "hidden_size": 3072,
+    "initializer_range": 0.02,
+    "intermediate_size": 24576,
+    "max_position_embeddings": 8192,
+    "model_type": "gemma",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 16,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 256000
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "use_decoder_only_language_model": true,
+  "vision_config": {
+    "dropout": 0.0,
+    "image_size": 364,
+    "initializer_factor": 1.0,
+    "model_type": "blip_2_vision_model",
+    "num_channels": 3,
+    "projection_dim": 512
+  }
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.40.1"
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161c0b5a96d4711a7eb46ac14413bf6c76506a3d4bc6bca507114214be8f206c
+size 4376363208

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd6b9198e46abb01da610621dd54bb45c7c9de2258065e71b4c93b3e61e7e55
+size 4756367288

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f16d84521e2d694df2bd2ba90452d2a09bae91229efba2abe9be77b5ca135b84
+size 4731278032

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b7a89ddac5c517239c1cb3029c50db683684ded1c4224615c377877131e715
+size 4932629984

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55df5e6684e8a31c7732e3a90b15440277aeb1210c09f9e41c62f3c27c2eef35
+size 4731278072

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45810c92e1fb7cd98d344010c5717a81d5fa0eb3590a34912bb70cc46fc7d2fa
+size 4731278064

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426310b40c5c585fc0777b5a7bcc66e8c092902609aca4f0a33d52070c1a100e
+size 4932630024

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e2e8d54029d42cd94cb40f577708317e21a9c96f9801d012487314ffc6c92ef
+size 4731278072

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d52f791c6ad45517a2f3443ec41ec4fc0cc36574e35eb9166bcb183a20009fd
+size 604017280

model.safetensors.index.json

@@ -0,0 +1,992 @@
+{
+  "metadata": {
+    "total_size": 38526996480
+  },
+  "weight_map": {
+    "language_model.model.embed_tokens.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "language_model.model.norm.weight": "model-00009-of-00009.safetensors",
+    "language_projection.bias": "model-00001-of-00009.safetensors",
+    "language_projection.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.attention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.attention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.attention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.attention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.attention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.attention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.crossattention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.crossattention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.crossattention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.crossattention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.crossattention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.crossattention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.crossattention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.crossattention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.crossattention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.crossattention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.intermediate_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.intermediate_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.output_query.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.output_query.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.output_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.0.output_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.1.attention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.1.attention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.1.attention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.1.attention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.1.attention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.1.attention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.1.intermediate_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.1.intermediate_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.1.output_query.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.1.output_query.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.1.output_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.1.output_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.attention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.attention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.attention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.attention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.attention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.attention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.attention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.attention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.attention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.attention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.crossattention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.crossattention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.crossattention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.crossattention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.crossattention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.crossattention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.crossattention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.crossattention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.crossattention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.crossattention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.intermediate_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.intermediate_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.output_query.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.output_query.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.output_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.10.output_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.11.attention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.11.attention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.11.attention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.11.attention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.11.attention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.11.attention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.11.attention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.11.attention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.11.attention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.11.attention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.11.intermediate_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.11.intermediate_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.11.output_query.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.11.output_query.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.11.output_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.11.output_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.attention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.attention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.attention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.attention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.attention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.attention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.crossattention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.crossattention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.crossattention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.crossattention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.crossattention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.crossattention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.crossattention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.crossattention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.crossattention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.crossattention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.intermediate_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.intermediate_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.output_query.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.output_query.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.output_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.2.output_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.3.attention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.3.attention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.3.attention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.3.attention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.3.attention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.3.attention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.3.attention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.3.attention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.3.intermediate_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.3.intermediate_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.3.output_query.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.3.output_query.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.3.output_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.3.output_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.attention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.attention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.attention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.attention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.attention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.attention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.attention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.attention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.crossattention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.crossattention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.crossattention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.crossattention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.crossattention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.crossattention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.crossattention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.crossattention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.crossattention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.crossattention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.intermediate_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.intermediate_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.output_query.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.output_query.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.output_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.4.output_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.5.attention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.5.attention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.5.attention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.5.attention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.5.attention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.5.attention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.5.attention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.5.attention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.5.intermediate_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.5.intermediate_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.5.output_query.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.5.output_query.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.5.output_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.5.output_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.attention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.attention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.attention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.attention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.attention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.attention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.attention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.attention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.crossattention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.crossattention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.crossattention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.crossattention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.crossattention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.crossattention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.crossattention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.crossattention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.crossattention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.crossattention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.intermediate_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.intermediate_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.output_query.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.output_query.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.output_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.6.output_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.7.attention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.7.attention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.7.attention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.7.attention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.7.attention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.7.attention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.7.attention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.7.attention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.7.intermediate_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.7.intermediate_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.7.output_query.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.7.output_query.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.7.output_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.7.output_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.attention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.attention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.attention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.attention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.attention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.attention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.attention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.attention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.attention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.attention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.crossattention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.crossattention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.crossattention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.crossattention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.crossattention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.crossattention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.crossattention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.crossattention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.crossattention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.crossattention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.intermediate_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.intermediate_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.output_query.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.output_query.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.output_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.8.output_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.9.attention.attention.key.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.9.attention.attention.key.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.9.attention.attention.query.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.9.attention.attention.query.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.9.attention.attention.value.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.9.attention.attention.value.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.9.attention.output.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.9.attention.output.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.9.attention.output.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.9.attention.output.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.9.intermediate_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.9.intermediate_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.9.output_query.LayerNorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.9.output_query.LayerNorm.weight": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.9.output_query.dense.bias": "model-00001-of-00009.safetensors",
+    "qformer.encoder.layer.9.output_query.dense.weight": "model-00001-of-00009.safetensors",
+    "qformer.layernorm.bias": "model-00001-of-00009.safetensors",
+    "qformer.layernorm.weight": "model-00001-of-00009.safetensors",
+    "query_tokens": "model-00001-of-00009.safetensors",
+    "vision_model.embeddings.class_embedding": "model-00001-of-00009.safetensors",
+    "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00009.safetensors",
+    "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00009.safetensors",
+    "vision_model.embeddings.position_embedding": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.0.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.0.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.0.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.0.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.1.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.1.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.1.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.1.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.10.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.10.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.10.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.10.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.11.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.11.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.11.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.11.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.12.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.12.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.12.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.12.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.13.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.13.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.13.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.13.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.14.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.14.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.14.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.14.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.15.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.15.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.15.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.15.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.16.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.16.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.16.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.16.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.17.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.17.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.17.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.17.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.18.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.18.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.18.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.18.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.19.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.19.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.19.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.19.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.2.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.2.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.2.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.2.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.20.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.20.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.20.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.20.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.21.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.21.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.21.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.21.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.22.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.22.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.22.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.22.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.23.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.23.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.23.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.23.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.24.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.24.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.24.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.24.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.25.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.25.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.25.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.25.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.26.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.26.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.26.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.26.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.27.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.27.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.27.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.27.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.27.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.27.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.27.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.27.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.27.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.27.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.27.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.27.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.28.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.28.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.28.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.28.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.28.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.28.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.28.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.28.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.28.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.28.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.28.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.28.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.29.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.29.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.29.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.29.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.29.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.29.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.29.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.29.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.29.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.29.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.29.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.29.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.3.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.3.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.3.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.3.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.30.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.30.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.30.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.30.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.30.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.30.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.30.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.30.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.30.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.30.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.30.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.30.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.31.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.31.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.31.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.31.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.31.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.31.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.31.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.31.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.31.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.31.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.31.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.31.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.32.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.32.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.32.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.32.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.32.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.32.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.32.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.32.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.32.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.32.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.32.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.32.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.33.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.33.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.33.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.33.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.33.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.33.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.33.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.33.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.33.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.33.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.33.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.33.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.34.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.34.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.34.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.34.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.34.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.34.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.34.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.34.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.34.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.34.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.34.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.34.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.35.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.35.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.35.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.35.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.35.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.35.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.35.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.35.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.35.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.35.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.35.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.35.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.36.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.36.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.36.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.36.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.36.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.36.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.36.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.36.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.36.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.36.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.36.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.36.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.37.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.37.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.37.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.37.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.37.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.37.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.37.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.37.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.37.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.37.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.37.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.37.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.38.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.38.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.38.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.38.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.38.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.38.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.38.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.38.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.38.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.38.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.38.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.38.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.4.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.4.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.4.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.4.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.5.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.5.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.5.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.5.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.6.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.6.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.6.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.6.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.7.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.7.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.7.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.7.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.8.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.8.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.8.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.8.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.9.self_attn.projection.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.9.self_attn.projection.weight": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.9.self_attn.qkv.bias": "model-00001-of-00009.safetensors",
+    "vision_model.encoder.layers.9.self_attn.qkv.weight": "model-00001-of-00009.safetensors",
+    "vision_model.post_layernorm.bias": "model-00001-of-00009.safetensors",
+    "vision_model.post_layernorm.weight": "model-00001-of-00009.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_convert_rgb",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "BlipImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "Blip2Processor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 364,
+    "width": 364
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db21bfaffa1fd75fd741df2d95dc51e539d5cc38b07934bae0d7d129db90662
+size 17477581

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<eos>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "Blip2Processor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}