Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+llama_guard_4_12b_before_pruning.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1746014318

LICENSE

@@ -0,0 +1,32 @@
+LLAMA 4 COMMUNITY LICENSE AGREEMENT
+Llama 4 Version Effective Date: April 5, 2025
+
+“Agreement” means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.
+“Documentation” means the specifications, manuals and documentation accompanying Llama 4 distributed by Meta at https://www.llama.com/docs/overview.
+“Licensee” or “you” means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.
+“Llama 4” means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://www.llama.com/llama-downloads.
+“Llama Materials” means, collectively, Meta’s proprietary Llama 4 and Documentation (and any portion thereof) made available under this Agreement.
+“Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).
+By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials, you agree to be bound by this Agreement.
+
+1. License Rights and Redistribution.
+a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty- free limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.
+b. Redistribution and Use.
+i. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service (including another AI model) that contains any of them, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama” on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include “Llama” at the beginning of any such AI model name.
+
+ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.
+
+iii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a “Notice” text file distributed as a part of such copies: “Llama 4 is licensed under the Llama 4 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.”
+
+iv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.com/llama4/use-policy), which is hereby incorporated by reference into this Agreement.
+2. Additional Commercial Terms. If, on the Llama 4 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
+3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
+4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
+5. Intellectual Property.
+a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.
+b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.
+
+c. If you institute litigation or other proceedings against Meta or any entity (including a cross- claim or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 4 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.
+
+6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.
+7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.

README.md

@@ -1,3 +1,374 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+language:
+- en
+tags:
+- facebook
+- meta
+- pytorch
+- llama
+- llama4
+- safety
+extra_gated_prompt: >-
+    **LLAMA 4 COMMUNITY LICENSE AGREEMENT**
+
+    Llama 4 Version Effective Date: April 5, 2025
+
+    "**Agreement**" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.
+
+    "**Documentation**" means the specifications, manuals and documentation accompanying Llama 4 distributed by Meta at [https://www.llama.com/docs/overview](https://llama.com/docs/overview).
+
+    "**Licensee**" or "**you**" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.
+
+    "**Llama 4**" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at [https://www.llama.com/llama-downloads](https://www.llama.com/llama-downloads).
+
+    "**Llama Materials**" means, collectively, Meta’s proprietary Llama 4 and Documentation (and any portion thereof) made available under this Agreement.
+
+    "**Meta**" or "**we**" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).
+
+    By clicking "I Accept" below or by using or distributing any portion or element of the Llama Materials, you agree to be bound by this Agreement.
+
+    1\. **License Rights and Redistribution**.
+
+    a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.
+
+    b. Redistribution and Use.
+
+    i. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service (including another AI model) that contains any of them, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama” on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include “Llama” at the beginning of any such AI model name.
+
+    ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.
+
+    iii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a “Notice” text file distributed as a part of such copies: “Llama 4 is licensed under the Llama 4 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.”
+
+    iv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at [https://www.llama.com/llama4/use-policy](https://www.llama.com/llama4/use-policy)), which is hereby incorporated by reference into this Agreement.
+
+    2\. **Additional Commercial Terms**. If, on the Llama 4 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
+
+    3**. Disclaimer of Warranty**. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
+
+    4\. **Limitation of Liability**. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
+
+    5\. **Intellectual Property**.
+
+    a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use "Llama" (the "Mark") solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at [https://about.meta.com/brand/resources/meta/company-brand/](https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.
+
+    b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.
+
+    c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 4 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.
+
+    6\. **Term and Termination**. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.
+
+    7\. **Governing Law and Jurisdiction**. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.
+extra_gated_fields:
+  First Name: text
+  Last Name: text
+  Date of birth: date_picker
+  Country: country
+  Affiliation: text
+  Job title:
+    type: select
+    options:
+    - Student
+    - Research Graduate
+    - AI researcher
+    - AI developer/engineer
+    - Reporter
+    - Other
+  geo: ip_location
+  By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox
+extra_gated_description: >-
+  The information you provide will be collected, stored, processed and shared in
+  accordance with the [Meta Privacy
+  Policy](https://www.facebook.com/privacy/policy/).
+extra_gated_button_content: Submit
+extra_gated_heading: "Please be sure to provide your full legal name, date of birth, and full organization name with all corporate identifiers. Avoid the use of acronyms and special characters. Failure to follow these instructions may prevent you from accessing this model and others on Hugging Face. You will not have the ability to edit this form after submission, so please ensure all information is accurate."
+license: other
+license_name: llama4
+---
+# Llama Guard 4 Model Card
+
+## Model Details
+
+Llama Guard 4 is a natively multimodal safety classifier with 12 billion parameters trained jointly on text and multiple images. Llama Guard 4 is a dense architecture pruned from the Llama 4 Scout pre-trained model and fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It itself acts as an LLM: it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.
+
+Llama Guard 4 was aligned to safeguard against the standardized MLCommons [hazards taxonomy](https://arxiv.org/abs/2503.05731) and designed to support multimodal Llama 4 capabilities within a single safety classifier. Specifically, it combines the capabilities of the previous Llama Guard 3-8B and Llama Guard 3-11B-vision models by supporting English and multilingual text prompts (on the languages [supported by Llama Guard 3](https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Guard3/8B/MODEL_CARD.md#evaluation)) as well as mixed text-and-image prompts for image understanding. Unlike Llama Guard 3-11B-vision, Llama Guard 4 now supports safety classification when multiple images are given in the prompt as input. Llama Guard 4 is also integrated into the Llama Moderations API for text and images.
+
+## Getting Started
+
+Once you have access to the model weights, please refer to our [documentation](https://www.llama.com/docs/model-cards-and-prompt-formats/llama-guard-4/) to get started.
+
+## Hazard Taxonomy and Policy
+
+The model is trained to predict safety labels on the categories shown below, based on the MLCommons safety taxonomy. We include an additional category, Code Interpreter Abuse, for text-only tool-call use cases.
+
+<table align="center">
+<thead>
+  <tr>
+    <th colspan="2"><center><b>Hazard categories</b></center></th>
+  </tr>
+</thead>
+<tbody>
+  <tr>
+    <td>S1: Violent Crimes</td>
+    <td>S2: Non-Violent Crimes</td>
+  </tr>
+  <tr>
+    <td>S3: Sex-Related Crimes</td>
+    <td>S4: Child Sexual Exploitation</td>
+  </tr>
+  <tr>
+    <td>S5: Defamation</td>
+    <td>S6: Specialized Advice</td>
+  </tr>
+  <tr>
+    <td>S7: Privacy</td>
+    <td>S8: Intellectual Property</td>
+  </tr>
+  <tr>
+    <td>S9: Indiscriminate Weapons</td>
+    <td>S10: Hate</td>
+  </tr>
+  <tr>
+    <td>S11: Suicide & Self-Harm</td>
+    <td>S12: Sexual Content</td>
+  </tr>
+  <tr>
+    <td>S13: Elections</td>
+    <td>S14: Code Interpreter Abuse (text only)</td>
+  </tr>
+</tbody>
+</table>
+
+**S1 - Violent Crimes**
+
+Responses that enable, encourage, or endorse the commission of violent crimes, including: (1) unlawful violence toward people (ex: terrorism, genocide, murder, hate-motivated violent crimes, child abuse, assault, battery, kidnapping) and (2) unlawful violence toward animals (ex: animal abuse)
+
+**S2 - Non-Violent Crimes**
+
+Responses that enable, encourage, or endorse the commission of non-violent crimes, including: (1) personal crimes (ex: labor trafficking, threats, intimidation, hate-motivated non-violent crimes), (2) financial crimes (ex: fraud, scams, money laundering), (3) property crimes (ex: theft, arson, vandalism), (4) drug crimes (ex: creating or using regulated substances), (5) weapons crimes (ex: producing unlicensed firearms), and (6) cyber crimes (ex: hacking)
+
+**S3 - Sex-Related Crimes**
+
+Responses that enable, encourage, or endorse the commission of sex-related crimes, including: (1) sex trafficking, (2) sexual assault (ex: rape), (3) sexual harassment (physical, verbal, or visual), and (4) prostitution
+
+**S4 - Child Sexual Exploitation**
+
+Responses that contain, describe, enable, encourage, or endorse the sexual abuse of children
+
+**S5 - Defamation**
+
+Responses that are both verifiably false and likely to injure a living person’s reputation
+
+**S6 - Specialized Advice**
+
+Responses that contain specialized financial, medical, or legal advice, or that indicate dangerous activities or objects are safe
+
+**S7 - Privacy**
+
+Responses that contain sensitive, nonpublic personal information that could undermine someone’s physical, digital, or financial security
+
+**S8 - Intellectual Property**
+
+Responses that may violate the intellectual property rights of any third party
+
+**S9 - Indiscriminate Weapons**
+
+Responses that enable, encourage, or endorse the creation of indiscriminate weapons, including: (1) chemical weapons (ex: nerve gas), (2) biological weapons (ex: anthrax), (3) radiological weapons (ex: cobalt bombs), (4) nuclear weapons (ex: fission bombs), and (5) high-yield explosive weapons (ex: cluster munitions)
+
+**S10 - Hate**
+
+Responses that demean or dehumanize people on the basis of their sensitive, personal characteristics (i.e., race, color, ethnicity, national origin, disability, religious affiliation, caste, sexual orientation, sex, gender identity, and/or serious disease)
+
+**S11 - Suicide & Self-Harm**
+
+Responses that enable, encourage, or endorse acts of intentional self-harm, including: (1) suicide, (2) self-injury (ex: cutting), and (3) disordered eating
+
+**S12 - Sexual Content**
+
+Responses that contain erotica
+
+**S13 - Elections**
+
+Responses that contain factually incorrect information about electoral systems and processes, including in the time, place, or manner of voting in civic elections
+
+**S14 - Code Interpreter Abuse (text-only)**
+
+Responses that seek to abuse code interpreters, including those that enable denial of service attacks, container escapes or privilege escalation exploits
+
+## Model Architecture
+
+Llama Guard 4 is a natively multimodal safeguard model. The model has 12 billion parameters in total and uses an early fusion transformer architecture with dense layers to keep the overall size small. The model can be run on a single GPU. Llama Guard 4 shares the same tokenizer and vision encoder as Llama 4 Scout and Maverick.
+
+## Model Training
+
+### Pretraining and Pruning
+
+Llama Guard 4 employs a dense feedforward early-fusion architecture, and it differs from Llama 4 Scout, which employs Mixture-of-Experts (MoE) layers. In order to leverage Llama 4’s pre-training, we develop a method to prune the pre-trained Llama 4 Scout mixture-of-experts architecture into a dense one, and we perform no additional pre-training.
+
+We take the pre-trained Llama 4 Scout checkpoint, which consists of one shared dense expert and sixteen routed experts in each Mixture-of-Experts layer. We prune all the routed experts and the router layers, retaining only the shared expert. After pruning, the Mixture-of-Experts is reduced to a dense feedforward layer initiated from the shared expert weights.
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/meta-llama/PurpleLlama/refs/heads/main/Llama-Guard4/12B/llama_guard_4_12b_before_pruning.png" width="800"/>
+  <figcaption>Before pruning: Llama 4 Scout pre-trained checkpoint</figcaption>
+</p>
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/meta-llama/PurpleLlama/refs/heads/main/Llama-Guard4/12B/llama_guard_4_12b_after_pruning.png" width="800"/>
+  <figcaption>After pruning and post-training: Llama Guard 4</figcaption>
+</p>
+
+### Post-Training for Safety Classification
+
+We post-trained the model after pruning with a blend of data from the [Llama Guard 3-8B](https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Guard3/8B/README.md) and [Llama Guard 3-11B-vision](https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Guard3/11B-vision/README.md) models, with the following additional data:
+- Multi-image training data, with most samples containing from 2 to 5 images
+- Multilingual data, both written by expert human annotators and translated from English
+
+We blend the training data from both modalities, with a ratio of roughly 3:1 text-only data to multimodal data containing one or more images.
+
+## Evaluation
+
+### System-level safety
+
+Llama Guard 4 is designed to be used in an integrated system with a generative language model, reducing the overall rate of safety violations exposed to the user. Llama Guard 4 can be used for input filtering, output filtering, or both: input filtering relies on classifying the user prompts into an LLM as safe or unsafe, and output filtering relies on classifying an LLM’s generated output as safe or unsafe. The advantage of using input filtering is that unsafe content can be caught very early, before the LLM even responds, but the advantage of using output filtering is that the LLM is given a chance to potentially respond to an unsafe prompt in a safe way, and thus the final output from the model shown to the user would only be censored if it is found to itself be unsafe. Using both filtering types gives additional security.
+
+In some internal tests we have found that input filtering reduces safety violation rate and raises overall refusal rate more than output filtering does, but your experience may vary. We find that Llama Guard 4 roughly matches or exceeds the overall performance of the Llama Guard 3 models on both input and output filtering, for English and multilingual text and for mixed text and images.
+
+### Classifier performance
+
+The tables below demonstrate how Llama Guard 4 matches or exceeds the overall performance of Llama Guard 3-8B (LG3) on English and multilingual text, as well as Llama Guard 3-11B-vision (LG3v) on prompts with single or multiple images, using in-house test set:
+
+<br>
+
+<table align="center">
+<thead>
+  <tr>
+    <th></th>
+    <th colspan="3">Absolute values</th>
+    <th colspan="3">vs. Llama Guard 3</th>
+  </tr>
+</thead>
+<tbody>
+  <tr>
+    <td></td>
+    <td><center>R</center></td>
+    <td><center>FPR</center></td>
+    <td><center>F1</center></td>
+    <td><center>Δ R</center></td>
+    <td><center>Δ FPR</center></td>
+    <td><center>Δ F1</center></td>
+  </tr>
+  <tr>
+    <td><left>English</left></td>
+    <td>69%</td>
+    <td>11%</td>
+    <td>61%</td>
+    <td>4%</td>
+    <td>-3%</td>
+    <td>8%</td>
+  </tr>
+  <tr>
+    <td><left>Multilingual</left></td>
+    <td>43%</td>
+    <td>3%</td>
+    <td>51%</td>
+    <td>-2%</td>
+    <td>-1%</td>
+    <td>0%</td>
+  </tr>
+  <tr>
+    <td><left>Single-image</left></td>
+    <td>41%</td>
+    <td>9%</td>
+    <td>38%</td>
+    <td>10%</td>
+    <td>0%</td>
+    <td>8%</td>
+  </tr>
+  <tr>
+    <td><left>Multi-image</left></td>
+    <td>61%</td>
+    <td>9%</td>
+    <td>52%</td>
+    <td>20%</td>
+    <td>-1%</td>
+    <td>17%</td>
+  </tr>
+</tbody>
+</table>
+
+<br>
+
+R: recall, FPR: false positive rate. Values are from output filtering, flagging model outputs as either safe or unsafe. All values are an average over samples from safety categories S1 through S13 listed above, weighting each category equally, except for multilinguality, for which it is an average over the 7 shipped non-English languages of Llama Guard 3-8B: French, German, Hindi, Italian, Portuguese, Spanish, and Thai. For multi-image prompts, only the final image was input into Llama Guard 3-11B-vision, which does not support multiple images.
+
+We omit evals against competitor models, which are typically not aligned with the specific safety policy that this classifier was trained on, prohibiting the ability to make direct comparisons.
+
+## Getting Started with transformers
+
+You can get started with the model by running the following. Make sure you have the transformers release for Llama Guard 4 and hf_xet locally.
+
+```bash
+pip install git+https://github.com/huggingface/[email protected] hf_xet
+```
+
+Here's a basic snippet. For multi-turn and image-text inference, please refer to the [release blog](https://huggingface.co/blog/llama-guard-4)
+
+```python
+from transformers import AutoProcessor, Llama4ForConditionalGeneration
+import torch
+
+model_id = "meta-llama/Llama-Guard-4-12B"
+
+processor = AutoProcessor.from_pretrained(model_id)
+model = Llama4ForConditionalGeneration.from_pretrained(
+    model_id,
+    device_map="cuda",
+    torch_dtype=torch.bfloat16,
+)
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "text", "text": "how do I make a bomb?"}
+        ]
+    },
+]
+
+inputs = processor.apply_chat_template(
+    messages,
+    tokenize=True,
+    add_generation_prompt=True,
+    return_tensors="pt",
+    return_dict=True,
+).to("cuda")
+
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=10,
+    do_sample=False,
+)
+
+response = processor.batch_decode(outputs[:, inputs["input_ids"].shape[-1]:], skip_special_tokens=True)[0]
+print(response)
+
+# OUTPUT
+# unsafe
+# S9
+
+```
+
+## Limitations
+
+There are some limitations associated with Llama Guard 4. First, the classifier itself is an LLM fine-tuned on Llama 4, and thus its performance (e.g., judgments that need common-sense knowledge, multilingual capabilities, and policy coverage) might be limited by its (pre-)training data.
+
+Some hazard categories may require factual, up-to-date knowledge to be evaluated fully (for example, \[S5\] Defamation, \[S8\] Intellectual Property, and \[S13\] Elections). We believe that more complex systems should be deployed to accurately moderate these categories for use cases highly sensitive to these types of hazards, but that Llama Guard 4 provides a good baseline for generic use cases.
+
+Note that the performance of Llama Guard 4 was tested mostly with prompts containing a few images (three, most frequently), so performance may vary if using it to classify safety with a much larger number of images.
+
+Lastly, as an LLM, Llama Guard 4 may be susceptible to adversarial attacks or prompt injection attacks that could bypass or alter its intended use: see [Llama Prompt Guard 2](https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Prompt-Guard-2/86M/MODEL_CARD.md) for detecting prompt attacks. Please feel free to [report](https://github.com/meta-llama/PurpleLlama) vulnerabilities, and we will look into incorporating improvements into future versions of Llama Guard.
+
+Please refer to the [Developer Use Guide](https://www.llama.com/developer-use-guide/) for additional best practices and safety considerations.
+
+## References
+
+\[1\] [The Llama 3 Herd of Models](https://arxiv.org/pdf/2407.21783)

USE_POLICY.md

@@ -0,0 +1,78 @@
+**Llama 4** **Acceptable Use Policy**
+
+Meta is committed to promoting safe and fair use of its tools and features, including Llama 4. If you access or use Llama 4, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at [https://www.llama.com/llama4/use-policy](https://www.llama.com/llama4/use-policy).
+
+**Prohibited Uses**
+
+We want everyone to use Llama 4 safely and responsibly. You agree you will not use, or allow others to use, Llama 4 to:
+
+1. Violate the law or others’ rights, including to:
+
+   1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
+
+      1. Violence or terrorism
+
+      2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
+
+      3. Human trafficking, exploitation, and sexual violence
+
+      4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
+
+      5. Sexual solicitation
+
+      6. Any other criminal activity
+
+   2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
+
+   3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
+
+   4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
+
+   5. Collect, process, disclose, generate, or infer private or sensitive information about individuals, including information about individuals’ identity, health, or demographic information, unless you have obtained the right to do so in accordance with applicable law
+
+   6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
+
+   7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
+
+   8. Engage in any action, or facilitate any action, to intentionally circumvent or remove usage restrictions or other safety measures, or to enable functionality disabled by Meta
+
+3. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 4 related to the following:
+
+   1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons Convention Implementation Act of 1997
+
+   2. Guns and illegal weapons (including weapon development)
+
+   3. Illegal drugs and regulated/controlled substances
+
+   4. Operation of critical infrastructure, transportation technologies, or heavy machinery
+
+   5. Self-harm or harm to others, including suicide, cutting, and eating disorders
+
+   6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
+
+4. Intentionally deceive or mislead others, including use of Llama 4 related to the following:
+
+   1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
+
+   2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
+
+   3. Generating, promoting, or further distributing spam
+
+   4. Impersonating another individual without consent, authorization, or legal right
+
+   5. Representing that the use of Llama 4 or outputs are human generated
+
+   6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement
+
+5. Fail to appropriately disclose to end users any known dangers of your AI system
+
+6. Interact with third party tools, models, or software designed to generate unlawful content or engage in unlawful or harmful conduct and/or represent that the outputs of such tools, models, or software are associated with Meta or Llama 4
+
+With respect to any multimodal models included in Llama 4, the rights granted under Section 1(a) of the Llama 4 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models.
+
+Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
+
+* Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://github.com/meta-llama/llama-models/issues)
+* Reporting risky content generated by the model: [https://developers.facebook.com/llama_output_feedback](https://developers.facebook.com/llama_output_feedback)
+* Reporting bugs and security concerns: [https://facebook.com/whitehat/info](https://facebook.com/whitehat/info)
+* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama 4: [email protected]

chat_template.jinja

@@ -0,0 +1,98 @@
+{%- if messages | length % 2 == 0 -%}
+    {%- set role = 'Agent' -%}
+{%- else -%}
+    {%- set role = 'User' -%}
+{%- endif -%}
+
+{%- if categories is not defined -%}
+    {%- set ns = namespace(contains_image=false) -%}
+
+    {%- for message in messages -%}
+        {%- for content in message['content'] | selectattr('type', 'equalto', 'image') -%}
+            {%- set ns.contains_image = true -%}
+        {%- endfor -%}
+    {%- endfor -%}
+
+    {%- if ns.contains_image -%}
+        {%- set categories = {
+            "S1": "Violent Crimes.",
+            "S2": "Non-Violent Crimes.",
+            "S3": "Sex Crimes.",
+            "S4": "Child Exploitation.",
+            "S5": "Defamation.",
+            "S6": "Specialized Advice.",
+            "S7": "Privacy.",
+            "S8": "Intellectual Property.",
+            "S9": "Indiscriminate Weapons.",
+            "S10": "Hate.",
+            "S11": "Self-Harm.",
+            "S12": "Sexual Content.",
+            "S13": "Elections.",
+        } -%}
+    {%- else -%}
+        {%- set categories = {
+            "S1": "Violent Crimes.",
+            "S2": "Non-Violent Crimes.",
+            "S3": "Sex Crimes.",
+            "S4": "Child Exploitation.",
+            "S5": "Defamation.",
+            "S6": "Specialized Advice.",
+            "S7": "Privacy.",
+            "S8": "Intellectual Property.",
+            "S9": "Indiscriminate Weapons.",
+            "S10": "Hate.",
+            "S11": "Self-Harm.",
+            "S12": "Sexual Content.",
+            "S13": "Elections.",
+            "S14": "Code Interpreter Abuse.",
+        } -%}
+    {%- endif -%}
+{%- endif -%}
+
+{{ "<|begin_of_text|><|header_start|>user<|header_end|>\n" }}
+{{ "Task: Check if there is unsafe content in '" + role + "' messages in conversations according to our safety policy with the below categories.\n" }}
+{{ "<BEGIN UNSAFE CONTENT CATEGORIES>\n" }}
+
+{%- for key in categories -%}
+    {%- if key not in excluded_category_keys -%}
+        {{ key + ": " + categories[key] + "\n" }}
+    {%- endif -%}
+{%- endfor -%}
+
+{{ "<END UNSAFE CONTENT CATEGORIES>\n" }}
+{{ "<BEGIN CONVERSATION>\n" }}
+
+{%- for message in messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}
+    {%- endif -%}
+
+    {%- set content = message['content'] -%}
+
+    {%- if message['role'] == 'user' -%}
+        {%- set role = 'User' -%}
+    {%- elif message['role'] == 'assistant' -%}
+        {%- set role = 'Agent' -%}
+    {%- endif -%}
+
+    {#— #1 Accumulate all images for this message —#}
+    {%- set ns = namespace(img_tokens='') -%}
+    {%- for img in message.content | selectattr('type', 'equalto', 'image') -%}
+        {%- set ns.img_tokens = ns.img_tokens + '<|image|>' -%}
+    {%- endfor -%}
+
+    {#— #2 Then emit all text —#}
+    {%- for txt in message.content | selectattr('type','equalto','text') -%}
+        {{ role + ': ' }}{{ ns.img_tokens }}{{ txt.text | trim }}\n\n
+
+        {#— clear the buffer so only first text prints images —#}
+        {%- if loop.first -%}
+            {%- set ns.img_tokens = '' -%}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endfor -%}
+
+{{ "<END CONVERSATION>\n" }}
+{{ "Provide your safety assessment for ONLY THE LAST " + role + " message in the above conversation:" }}
+{{ " - First line must read 'safe' or 'unsafe'." }}
+{{ " - If unsafe, a second line must include a comma-separated list of violated categories. <|eot|><|header_start|>assistant<|header_end|>" }}

config.json

@@ -0,0 +1,135 @@
+{
+  "architectures": [
+    "Llama4ForConditionalGeneration"
+  ],
+  "boi_token_index": 200080,
+  "eoi_token_index": 200081,
+  "image_token_index": 200092,
+  "model_type": "llama4",
+  "text_config": {
+    "_attn_implementation_autoset": true,
+    "attention_bias": false,
+    "attention_chunk_size": null,
+    "attention_dropout": 0.0,
+    "attn_scale": 0.1,
+    "attn_temperature_tuning": true,
+    "bos_token_id": 200000,
+    "cache_implementation": "static",
+    "eos_token_id": [
+      200001,
+      200007,
+      200008
+    ],
+    "floor_scale": 8192,
+    "for_llm_compressor": false,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "interleave_moe_layer_step": 0,
+    "intermediate_size": 8192,
+    "intermediate_size_mlp": 8192,
+    "max_position_embeddings": 10485760,
+    "model_type": "llama4_text",
+    "moe_layers": [],
+    "no_rope_layers": [
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1,
+      1
+    ],
+    "num_attention_heads": 40,
+    "num_experts_per_tok": 1,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "num_local_experts": 0,
+    "output_router_logits": false,
+    "pad_token_id": 200018,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "factor": 16,
+      "high_freq_factor": 1,
+      "low_freq_factor": 1.0,
+      "original_max_position_embeddings": 8192,
+      "rope_type": "llama3"
+    },
+    "rope_theta": 500000.0,
+    "router_aux_loss_coef": 0.001,
+    "router_jitter_noise": 0.0,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "use_qk_norm": true,
+    "vocab_size": 202048
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.0.dev0",
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 1408,
+    "image_size": 336,
+    "initializer_range": 0.02,
+    "intermediate_size": 5632,
+    "model_type": "llama4_vision_model",
+    "multi_modal_projector_bias": false,
+    "norm_eps": 1e-05,
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 34,
+    "patch_size": 14,
+    "pixel_shuffle_ratio": 0.5,
+    "projector_dropout": 0.0,
+    "projector_input_dim": 4096,
+    "projector_output_dim": 4096,
+    "rope_theta": 10000,
+    "vision_feature_layer": -1,
+    "vision_feature_select_strategy": "default",
+    "vision_output_dim": 4096
+  }
+}

configuration.json

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

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 200000,
+  "cache_implementation": "static",
+  "eos_token_id": [
+    200001,
+    200007,
+    200008
+  ],
+  "pad_token_id": 200018,
+  "transformers_version": "4.52.0.dev0"
+}

handler.py

@@ -0,0 +1,38 @@
+from typing import Any, Dict, List
+
+import torch
+from transformers import AutoProcessor, Llama4ForConditionalGeneration
+
+
+class EndpointHandler():
+    def __init__(self, path=""):
+        self.model=Llama4ForConditionalGeneration.from_pretrained(path,device_map="cuda",torch_dtype=torch.bfloat16)
+        self.processor=AutoProcessor.from_pretrained(path)
+
+    def __call__(self, data: Any):
+        inputs = data.pop("inputs", data)
+        messages = [
+            {
+                "role": "user",
+                "content": [
+                    {"type": "text", "text": inputs}
+                ]
+            },
+        ]
+        process_inputs=self.processor.apply_chat_template(
+            messages,
+            tokenize=True,
+            add_generation_prompt=True,
+            return_tensors="pt",
+            return_dict=True,
+        ).to('cuda')
+
+        outputs=self.model.generate(
+            **process_inputs,
+            max_new_tokens=10,
+            do_sample=False,
+        )
+
+        response=self.processor.batch_decode(outputs[:, process_inputs["input_ids"].shape[-1]:], skip_special_tokens=True)[0]
+
+        return response

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b3e93a5c09f732537068482a5f00c29a675092f0ae456ebd60043af59c21299
+size 4997861792

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08150644f6be3ae2474a8a9f3290edbc62ac876522217c6bf70ce304ed1351e2
+size 4981018296

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d30c028733fc776ac18a369d565bb395fa4473aa2317cbedeef1cd216c6b327
+size 4991503856

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecd9fed60f059359941913c3ade611e8c67a63ba453efbc071de8af007c586e7
+size 4991503856

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57aa2d6a20feb15010f74599e4a4f9f4985cb1b87a975dc6ffc1d34780de7599
+size 4040434224

model.safetensors.index.json

@@ -0,0 +1,996 @@
+{
+  "metadata": {
+    "total_size": 24002194432
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.feed_forward.down_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.feed_forward.up_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.feed_forward.down_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.feed_forward.up_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.10.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.16.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.16.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.16.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.17.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.2.feed_forward.down_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.feed_forward.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.feed_forward.up_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.20.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.28.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.28.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.28.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.29.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.29.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.3.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.3.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.3.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.30.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.39.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.39.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.39.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.39.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.4.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.4.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.4.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.40.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.40.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.40.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.40.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.40.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.40.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.40.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.40.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.40.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.41.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.41.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.41.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.41.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.41.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.41.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.41.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.41.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.42.feed_forward.down_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.42.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.42.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.42.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.42.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.42.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.42.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.42.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.42.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.43.feed_forward.down_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.43.feed_forward.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.43.feed_forward.up_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.43.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.43.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.43.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.43.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.43.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.43.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.44.feed_forward.down_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.44.feed_forward.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.44.feed_forward.up_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.44.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.44.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.44.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.44.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.44.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.44.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.45.feed_forward.down_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.45.feed_forward.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.45.feed_forward.up_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.45.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.45.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.45.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.45.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.45.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.45.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.46.feed_forward.down_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.46.feed_forward.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.46.feed_forward.up_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.46.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.46.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.46.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.46.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.46.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.46.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.47.feed_forward.down_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.47.feed_forward.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.47.feed_forward.up_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.47.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.47.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.47.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.47.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.47.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.47.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.5.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.norm.weight": "model-00005-of-00005.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.class_embedding": "model-00001-of-00005.safetensors",
+    "vision_model.layernorm_post.bias": "model-00001-of-00005.safetensors",
+    "vision_model.layernorm_post.weight": "model-00001-of-00005.safetensors",
+    "vision_model.layernorm_pre.bias": "model-00001-of-00005.safetensors",
+    "vision_model.layernorm_pre.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.0.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.0.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.0.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.0.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.0.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.0.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.0.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.1.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.1.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.1.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.1.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.1.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.1.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.1.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.10.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.10.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.10.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.10.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.10.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.10.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.10.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.10.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.10.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.10.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.11.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.11.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.11.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.11.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.11.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.11.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.11.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.11.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.11.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.11.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.12.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.12.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.12.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.12.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.12.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.12.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.12.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.12.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.12.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.12.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.13.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.13.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.13.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.13.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.13.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.13.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.13.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.13.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.13.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.13.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.13.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.14.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.14.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.14.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.14.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.14.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.14.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.14.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.14.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.14.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.14.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.14.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.15.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.15.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.15.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.15.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.15.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.15.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.15.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.15.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.15.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.15.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.15.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.16.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.16.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.16.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.16.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.16.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.16.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.16.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.16.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.16.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.16.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.16.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.17.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.17.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.17.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.17.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.17.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.17.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.17.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.17.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.17.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.17.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.17.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.18.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.18.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.18.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.18.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.18.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.18.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.18.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.18.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.18.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.18.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.18.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.19.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.19.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.19.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.19.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.19.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.19.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.19.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.19.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.19.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.19.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.19.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.2.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.2.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.2.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.2.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.2.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.2.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.2.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.20.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.20.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.20.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.20.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.20.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.20.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.20.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.20.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.20.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.20.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.20.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.21.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.21.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.21.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.21.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.21.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.21.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.21.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.21.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.21.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.21.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.21.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.21.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.22.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.22.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.22.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.22.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.22.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.22.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.22.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.22.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.22.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.22.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.22.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.22.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.22.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.23.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.23.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.23.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.23.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.23.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.23.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.23.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.23.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.23.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.23.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.23.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.23.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.23.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.24.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.24.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.24.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.24.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.24.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.24.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.24.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.24.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.24.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.24.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.24.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.24.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.24.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.24.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.24.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.24.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.25.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.25.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.25.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.25.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.25.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.25.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.25.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.25.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.25.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.25.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.25.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.25.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.25.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.25.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.25.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.25.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.26.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.26.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.26.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.26.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.26.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.26.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.26.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.26.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.26.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.26.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.26.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.26.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.26.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.26.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.26.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.26.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.27.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.27.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.27.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.27.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.27.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.27.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.27.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.27.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.27.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.27.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.27.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.27.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.27.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.27.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.27.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.27.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.28.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.28.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.28.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.28.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.28.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.28.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.28.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.28.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.28.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.28.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.28.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.28.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.28.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.28.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.28.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.28.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.29.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.29.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.29.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.29.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.29.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.29.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.29.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.29.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.29.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.29.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.29.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.29.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.29.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.29.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.29.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.29.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.3.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.3.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.3.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.3.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.3.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.3.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.3.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.30.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.30.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.30.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.30.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.30.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.30.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.30.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.30.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.30.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.30.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.30.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.30.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.30.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.30.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.30.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.30.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.31.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.31.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.31.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.31.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.31.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.31.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.31.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.31.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.31.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.31.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.31.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.31.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.31.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.31.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.31.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.31.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.32.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.32.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.32.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.32.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.32.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.32.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.32.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.32.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.32.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.32.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.32.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.32.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.32.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.32.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.32.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.32.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.33.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.33.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.33.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.33.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.33.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.33.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.33.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.33.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.33.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.33.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.33.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.33.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.33.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.33.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.33.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.33.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.4.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.4.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.4.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.4.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.4.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.4.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.4.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.5.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.5.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.5.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.5.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.5.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.5.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.5.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.6.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.6.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.6.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.6.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.6.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.6.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.6.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.7.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.7.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.7.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.7.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.7.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.7.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.7.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.8.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.8.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.8.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.8.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.8.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.8.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.8.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.8.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.8.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.8.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.9.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.9.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.9.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.9.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.9.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.9.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.9.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.9.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.9.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.9.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.9.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "vision_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.patch_embedding.linear.weight": "model-00001-of-00005.safetensors",
+    "vision_model.positional_embedding_vlm": "model-00001-of-00005.safetensors",
+    "vision_model.vision_adapter.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.vision_adapter.mlp.fc2.weight": "model-00001-of-00005.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,33 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Llama4ImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_patches": 16,
+  "processor_class": "Llama4Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "resize_to_max_canvas": false,
+  "return_tensors": null,
+  "size": {
+    "height": 336,
+    "width": 336
+  }
+}

processor_config.json

@@ -0,0 +1,6 @@
+{
+  "fake_image_token": "<|image|>",
+  "image_token": "<|image|>",
+  "patch_size": 14,
+  "processor_class": "Llama4Processor"
+}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|eot|>",
+  "pad_token": "<|finetune_right_pad_id|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e009b4fcb58eddbabf347e71b9881ea1e6eb72d44e5ea9477c7587df68fd8d
+size 27948580