Initial commit

.gitattributes

@@ -0,0 +1,39 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/EXAONE_Symbol+BI_3d.png filter=lfs diff=lfs merge=lfs -text
+assets/exaone45_input1.jpg filter=lfs diff=lfs merge=lfs -text
+assets/exaone45_input2.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,157 @@
+EXAONE AI Model License Agreement 1.2 - NC
+
+This License Agreement (“Agreement”) is entered into between you (“Licensee”) and LG Management Development
+Institute Co., Ltd. (“Licensor”), governing the use of the EXAONE AI Model (“Model”). By downloading,
+installing, copying, or using the Model, you agree to comply with and be bound by the terms of this Agreement.
+If you do not agree to all the terms, you must not download, install, copy, or use the Model. This Agreement
+constitutes a binding legal agreement between the Licensee and Licensor.
+
+1. Definitions
+    1.1 Model: The artificial intelligence model provided by Licensor, which includes any software,
+    algorithms, machine learning models, or related components supplied by Licensor. This definition extends
+    to encompass all updates, enhancements, improvements, bug fixes, patches, or other modifications that may
+    be provided by Licensor from time to time, whether automatically or manually implemented.
+    1.2 Derivatives: Any modifications, alterations, enhancements, improvements, adaptations, or derivative
+    works of the Model created by Licensee or any third party. This includes changes made to the Model's
+    architecture, parameters, data processing methods, or any other aspect of the Model that results in a
+    modification of its functionality or output.
+    1.3 Output: Any data, results, content, predictions, analyses, insights, or other materials generated by
+    the Model or Derivatives, regardless of whether they are in their original form or have been further
+    processed or modified by the Licensee. This includes, but is not limited to, textual or numerical produced
+    directly or indirectly through the use of the Model.
+    1.4 Licensor: LG Management Development Institute Co., Ltd., the owner, developer, and provider of the
+    EXAONE AI Model. The Licensor holds all rights, title, and interest in the Model and is responsible for
+    granting licenses to use the Model under the terms specified in this Agreement.
+    1.5 Licensee: The individual, organization, corporation, academic institution, government agency, or other
+    entity using or intending to use the Model under the terms and conditions of this Agreement. The Licensee
+    is responsible for ensuring compliance with the Agreement by all authorized users who access or utilize
+    the Model on behalf of the Licensee.
+
+2. License Grant
+    2.1 Grant of License: Subject to the terms and conditions outlined in this Agreement, the Licensor hereby
+    grants the Licensee a limited, non-exclusive, non-transferable, worldwide, and revocable license to:
+        a. Access, download, install, and use the Model solely for research and educational purposes. This 
+        includes evaluation, testing, academic research, experimentation, learning, teaching, training and 
+        participation in competitions, provided that such participation is in a non-commercial context. 
+        Notwithstanding Section 3.1, the Licensee may only provide the Model or Derivatives for a competition 
+        if no commercial license is granted to the competition organizer or any third party. 
+        b. Publicly disclose research results and findings derived from the use of the Model or Derivatives,
+        including publishing papers or presentations.
+        c. Modify the Model and create Derivatives based on the Model, provided that such modifications and
+        Derivatives are used exclusively for research and educational purposes. The Licensee may conduct 
+        experiments, perform analyses, and apply custom modifications to the Model to explore its capabilities
+        and performance under various scenarios. If the Model is modified, the modified Model must include 
+        "EXAONE" at the beginning of its name.
+        d. Distribute the Model and Derivatives in each case with a copy of this Agreement.
+    2.2 Scope of License: The license granted herein does not authorize the Licensee to use the Model for any
+    purpose not explicitly permitted under this Agreement. Any use beyond the scope of this license, including
+    any commercial application or external distribution, is strictly prohibited unless explicitly agreed upon
+    in writing by the Licensor.
+
+3. Restrictions
+    3.1 Commercial Use: The Licensee is expressly prohibited from using the Model, Derivatives, or Output for
+    any commercial purposes, including but not limited to, developing or deploying products, services, or
+    applications that generate revenue, whether directly or indirectly. Any commercial exploitation of the
+    Model or its derivatives requires a separate commercial license agreement with the Licensor. Furthermore,
+    the Licensee shall not use the Model, Derivatives or Output to develop or improve any models that compete
+    with the Licensor’s models.
+    3.2 Reverse Engineering: The Licensee shall not decompile, disassemble, reverse engineer, or attempt to
+    derive the source code, underlying ideas, algorithms, or structure of the Model, except to the extent that
+    such activities are expressly permitted by applicable law. Any attempt to bypass or circumvent
+    technological protection measures applied to the Model is strictly prohibited.
+    3.3 Unlawful Use: The Licensee shall not use the Model and Derivatives for any illegal, fraudulent, or
+    unauthorized activities, nor for any purpose that violates applicable laws or regulations. This includes
+    but is not limited to the creation, distribution, or dissemination of malicious, deceptive, or unlawful
+    content.
+    3.4 Ethical Use: The Licensee shall ensure that the Model or Derivatives is used in an ethical and
+    responsible manner, adhering to the following guidelines:
+        a. The Model and Derivatives shall not be used to generate, propagate, or amplify false, misleading,
+        or harmful information, including fake news, misinformation, or disinformation.
+        b. The Model and Derivatives shall not be employed to create, distribute, or promote content that is
+        discriminatory, harassing, defamatory, abusive, or otherwise offensive to individuals or groups based
+        on race, gender, sexual orientation, religion, nationality, or other protected characteristics.
+        c. The Model and Derivatives shall not infringe on the rights of others, including intellectual property
+        rights, privacy rights, or any other rights recognized by law. The Licensee shall obtain all necessary
+        permissions and consents before using the Model and Derivatives in a manner that may impact the rights
+        of third parties.
+        d. The Model and Derivatives shall not be used in a way that causes harm, whether physical, mental,
+        emotional, or financial, to individuals, organizations, or communities. The Licensee shall take all
+        reasonable measures to prevent misuse or abuse of the Model and Derivatives that could result in harm
+        or injury.
+
+4. Ownership
+    4.1 Intellectual Property: All rights, title, and interest in and to the Model, including any
+    modifications, Derivatives, and associated documentation, are and shall remain the exclusive property of
+    the Licensor. The Licensee acknowledges that this Agreement does not transfer any ownership rights to the
+    Licensee. All trademarks, service marks, and logos associated with the Model are the property of the
+    Licensor.
+    4.2 Output: Licensor claims no rights in Output. Licensee is solely responsible for the Output and its use.
+    4.3 Attribution: In any publication or presentation of results obtained using the Model, the Licensee
+    shall provide appropriate attribution to the Licensor, citing the Model's name and version, along with any
+    relevant documentation or references specified by the Licensor.
+
+5. No Warranty
+    5.1 “As-Is” Basis: The Model, Derivatives, and Output are provided on an “as-is” and “as-available” basis,
+    without any warranties or representations of any kind, whether express, implied, or statutory. The Licensor
+    disclaims all warranties, including but not limited to, implied warranties of merchantability, fitness for
+    a particular purpose, accuracy, reliability, non-infringement, or any warranty arising from the course of 
+    dealing or usage of trade.
+    5.2 Performance and Reliability: The Licensor does not warrant or guarantee that the Model, Derivatives or
+    Output will meet the Licensee’s requirements, that the operation of the Model, Derivatives or Output will
+    be uninterrupted or error-free, or that defects in the Model will be corrected. The Licensee acknowledges
+    that the use of the Model, Derivatives or Output is at its own risk and that the Model, Derivatives or
+    Output may contain bugs, errors, or other limitations.
+    5.3 No Endorsement: The Licensor does not endorse, approve, or certify any results, conclusions, or
+    recommendations derived from the use of the Model. The Licensee is solely responsible for evaluating the
+    accuracy, reliability, and suitability of the Model for its intended purposes.
+
+6. Limitation of Liability
+    6.1 No Liability for Damages: To the fullest extent permitted by applicable law, in no event shall the
+    Licensor be liable for any special, incidental, indirect, consequential, exemplary, or punitive damages,
+    including but not limited to, damages for loss of business profits, business interruption, loss of business
+    information, loss of data, or any other pecuniary or non-pecuniary loss arising out of or in connection with
+    the use or inability to use the Model, Derivatives or any Output, even if the Licensor has been advised of
+    the possibility of such damages.
+    6.2 Indemnification: The Licensee agrees to indemnify, defend, and hold harmless the Licensor, its
+    affiliates, officers, directors, employees, and agents from and against any claims, liabilities, damages,
+    losses, costs, or expenses (including reasonable attorneys' fees) arising out of or related to the
+    Licensee's use of the Model, any Derivatives, or any Output, including any violation of this Agreement or
+    applicable laws.
+
+7. Termination
+    7.1 Termination by Licensor: The Licensor reserves the right to terminate this Agreement and revoke the
+    Licensee’s rights to use the Model at any time, with or without cause, and without prior notice if the
+    Licensee breaches any of the terms or conditions of this Agreement. Termination shall be effective
+    immediately upon notice.
+    7.2 Effect of Termination: Upon termination of this Agreement, the Licensee must immediately cease all use
+    of the Model and Derivatives and destroy all copies of the Model and Derivatives in its possession or
+    control, including any backup or archival copies. The Licensee shall certify in writing to the Licensor that
+    such destruction has been completed.
+    7.3 Survival: The provisions of this Agreement that by their nature should survive termination, including
+    but not limited to, Sections 4 (Ownership), 5 (No Warranty), 6 (Limitation of Liability), and this Section 7
+    (Termination), shall continue to apply after termination.
+
+8. Governing Law
+    8.1 Governing Law: This Agreement shall be governed by and construed in accordance with the laws of the
+    Republic of Korea, without regard to its conflict of laws principles.
+    8.2 Arbitration: Any disputes, controversies, or claims arising out of or relating to this Agreement,
+    including its existence, validity, interpretation, performance, breach, or termination, shall be referred
+    to and finally resolved by arbitration administered by the Korean Commercial Arbitration Board (KCAB) in
+    accordance with the International Arbitration Rules of the Korean Commercial Arbitration Board in force at
+    the time of the commencement of the arbitration. The seat of arbitration shall be Seoul, Republic of Korea.
+    The tribunal shall consist of one arbitrator. The language of the arbitration shall be English.
+
+9. Alterations
+    9.1 Modifications: The Licensor reserves the right to modify or amend this Agreement at any time, in its
+    sole discretion. Any modifications will be effective upon posting the updated Agreement on the Licensor’s
+    website or through other means of communication. The Licensee is responsible for reviewing the Agreement
+    periodically for changes. Continued use of the Model after any modifications have been made constitutes
+    acceptance of the revised Agreement.
+    9.2 Entire Agreement: This Agreement constitutes the entire agreement between the Licensee and Licensor
+    concerning the subject matter hereof and supersedes all prior or contemporaneous oral or written agreements,
+    representations, or understandings. Any terms or conditions of any purchase order or other document
+    submitted by the Licensee in connection with the Model that are in addition to, different from, or
+    inconsistent with the terms and conditions of this Agreement are not binding on the Licensor and are void.
+
+By downloading, installing, or using the EXAONE AI Model, the Licensee acknowledges that it has read,
+understood, and agrees to be bound by the terms and conditions of this Agreement.

README.md

@@ -0,0 +1,820 @@
+---
+license: other
+license_name: exaone
+license_link: LICENSE
+language:
+  - en
+  - ko
+  - es
+  - de
+  - ja
+  - vi
+tags:
+  - lg-ai
+  - exaone
+pipeline_tag: image-text-to-text
+library_name: transformers
+---
+
+<br>
+<br>
+<p align="center">
+<img src="assets/EXAONE_Symbol+BI_3d.png" width="400">
+<br>
+<br>
+<br>
+
+<div align="center">
+  <a href="https://huggingface.co/collections/LGAI-EXAONE/exaone-45" style="text-decoration: none;">
+    <img src="https://img.shields.io/badge/🤗-HuggingFace-FC926C?style=for-the-badge" alt="HuggingFace">
+  </a>
+  <a href="https://www.lgresearch.ai/blog/view?seq=641" style="text-decoration: none;">
+    <img src="https://img.shields.io/badge/📝-Blog-E343BD?style=for-the-badge" alt="Blog">
+  </a>
+  <a href="https://github.com/LG-AI-EXAONE/EXAONE-4.5/blob/main/assets/Technical_Report__EXAONE_4_5.pdf" style="text-decoration: none;">
+    <img src="https://img.shields.io/badge/📑-Technical_Report_(TBU)-684CF4?style=for-the-badge" alt="Technical Report">
+  </a>
+  <a href="https://github.com/LG-AI-EXAONE/EXAONE-4.5" style="text-decoration: none;">
+    <img src="https://img.shields.io/badge/🖥️-GitHub-2B3137?style=for-the-badge" alt="GitHub">
+  </a>
+  <!-- <a href="#" style="text-decoration: none;">
+    <img src="https://img.shields.io/badge/✈️_API-Try_on_FriendliAI-2649BC?style=for-the-badge" alt="FriendliAI">
+  </a> -->
+</div>
+
+
+
+
+<br><br>
+
+# EXAONE 4.5
+
+We introduce EXAONE 4.5, the first open-weight vision language model developed by LG AI Research.
+Integrating a dedicated visual encoder into the existing EXAONE 4.0 framework, we expand the model's capability toward multimodality.
+EXAONE 4.5 features 33 billion parameters in total, including 1.2 billion parameters from the vision encoder. 
+EXAONE 4.5 achieves competitive performance in general benchmark while outperforming SOTA models of similar size in document understanding and Korean contextual reasoning, inheriting powerful language capabilities from our previous language models.
+
+For more details, please refer to the [technical report](https://github.com/LG-AI-EXAONE/EXAONE-4.5/blob/main/assets/Technical_Report__EXAONE_4_5.pdf), [blog](https://www.lgresearch.ai/blog/view?seq=641) and [GitHub](https://github.com/LG-AI-EXAONE/EXAONE-4.5).
+
+
+### Model Configuration
+
+- Model Type: Causal Language Model + Vision Encoder
+- Number of Parameters (Language Model): 31.7B
+- Number of Parameters (Vision Encoder): 1.29B
+- Hidden Dimension: 5,120
+- Intermediate size: 27,392
+- Number of Layers: 64 Main layers + 1 MTP layers
+  - Hybrid Attention Pattern: 16 x (3 Sliding window attention + 1 Global attention)
+  - Reordered Norm: Apply normalization after Attention/MLP, and before residual connection
+- Sliding Window Attention
+  - Number of Attention Heads: 40 Q-heads and 8 KV-heads
+  - Head Dimension: 128 for both Q/KV
+  - Sliding Window Size: 128
+- Global Attention
+  - Number of Attention Heads: 40 Q-heads and 8 KV-heads
+  - Head Dimension: 128 for both Q/KV
+  - No Rotary Positional Embedding Used (NoPE)
+- Vision Encoder
+  - Grouped Query Attention (GQA)
+  - 2D RoPE for vision embeddings
+- Vocab Size: 153,600
+- Context Length: 262,144 tokens
+- Knowledge Cutoff: Dec 2024 (2024/12)
+
+
+
+## Evaluation Results
+
+
+
+### Vision-Language Tasks
+
+<table>
+	<tr>
+		<th style="background: rgba(128,128,128,0.1); text-align: center;"> </th>
+		<th style="background: rgba(128,128,128,0.1); text-align: center;">EXAONE 4.5 33B (Reasoning)</th>
+		<th style="background: rgba(128,128,128,0.1); text-align: center;">GPT-5 mini (Reasoning: high)</th>
+		<th style="background: rgba(128,128,128,0.1); text-align: center;">Qwen3-VL 32B Thinking</th>
+		<th style="background: rgba(128,128,128,0.1); text-align: center;">Qwen3-VL 235B Thinking</th>
+		<th style="background: rgba(128,128,128,0.1); text-align: center;">Qwen3.5 27B (Reasoning)</th>
+	</tr>
+	<tr>
+		<td align="center">Architecture</td>
+		<td align="center">Dense</td>
+		<td align="center">-</td>
+		<td align="center">Dense</td>
+		<td align="center">MoE</td>
+		<td align="center">Dense</td>
+	</tr>
+	<tr>
+		<td align="center">Total Params</td>
+		<td align="center">33B</td>
+		<td align="center">-</td>
+		<td align="center">33B</td>
+		<td align="center">236B</td>
+		<td align="center">27B</td>
+	</tr>
+	<tr>
+		<td align="center">Active Params</td>
+		<td align="center">33B</td>
+		<td align="center">-</td>
+		<td align="center">33B</td>
+		<td align="center">22B</td>
+		<td align="center">27B</td>
+	</tr>
+	<tr>
+		<td align="center" colspan='7' style="background: linear-gradient(90deg, rgba(252,146,108,0.3) 0%, rgba(227,67,189,0.3) 50%, rgba(104,76,244,0.3) 100%); font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>STEM / Puzzle</i></td>
+	</tr>
+	<tr>
+		<td align="center">MMMU</td>
+		<td align="center">78.7</td>
+		<td align="center">79.0</td>
+		<td align="center">78.1</td>
+		<td align="center">80.6</td>
+		<td align="center">82.3</td>
+	</tr>
+	<tr>
+		<td align="center">MMMU-Pro</td>
+		<td align="center">68.6</td>
+		<td align="center">67.3</td>
+		<td align="center">68.1</td>
+		<td align="center">69.3</td>
+		<td align="center">75.0</td>
+	</tr>
+	<tr>
+		<td align="center">MedXpertQA-MM</td>
+		<td align="center">42.1</td>
+		<td align="center">34.4</td>
+		<td align="center">41.6</td>
+		<td align="center">47.6</td>
+		<td align="center">62.4</td>
+	</tr>
+	<tr>
+		<td align="center">MathVision</td>
+		<td align="center">75.2</td>
+		<td align="center">71.9</td>
+		<td align="center">70.2</td>
+		<td align="center">74.6</td>
+		<td align="center">86.0</td>
+	</tr>
+	<tr>
+		<td align="center">MathVista (mini)</td>
+		<td align="center">85.0</td>
+		<td align="center">79.1</td>
+		<td align="center">85.9</td>
+		<td align="center">85.8</td>
+		<td align="center">87.8</td>
+	</tr>
+	<tr>
+		<td align="center">WeMath</td>
+		<td align="center">79.1</td>
+		<td align="center">70.3</td>
+		<td align="center">71.6</td>
+		<td align="center">74.8</td>
+		<td align="center">84.0</td>
+	</tr>
+	<tr>
+		<td align="center">LogicVista</td>
+		<td align="center">73.8</td>
+		<td align="center">70.3</td>
+		<td align="center">70.9</td>
+		<td align="center">72.2</td>
+		<td align="center">77.0</td>
+	</tr>
+	<tr>
+		<td align="center">BabyVision</td>
+		<td align="center">18.8</td>
+		<td align="center">20.9</td>
+		<td align="center">17.4</td>
+		<td align="center">22.2</td>
+		<td align="center">44.6</td>
+	</tr>
+	<tr>
+		<td align="center" colspan='7' style="background: linear-gradient(90deg, rgba(252,146,108,0.3) 0%, rgba(227,67,189,0.3) 50%, rgba(104,76,244,0.3) 100%); font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>Document Understanding</i></td>
+	</tr>
+	<tr>
+		<td align="center">AI2D</td>
+		<td align="center">89.0</td>
+		<td align="center">88.2</td>
+		<td align="center">88.9</td>
+		<td align="center">89.2</td>
+		<td align="center">92.9</td>
+	</tr>
+	<tr>
+		<td align="center">ChartQAPro</td>
+		<td align="center">62.2</td>
+		<td align="center">60.9</td>
+		<td align="center">61.4</td>
+		<td align="center">61.2</td>
+		<td align="center">66.8</td>
+	</tr>
+	<tr>
+		<td align="center">CharXiv (RQ)</td>
+		<td align="center">71.7</td>
+		<td align="center">68.6</td>
+		<td align="center">65.2</td>
+		<td align="center">66.1</td>
+		<td align="center">79.5</td>
+	</tr>
+	<tr>
+		<td align="center">OCRBench v2</td>
+		<td align="center">63.2</td>
+		<td align="center">55.8</td>
+		<td align="center">68.4</td>
+		<td align="center">66.8</td>
+		<td align="center">67.3</td>
+	</tr>
+	<tr>
+		<td align="center">OmniDocBench v1.5</td>
+		<td align="center">81.2</td>
+		<td align="center">77.0</td>
+		<td align="center">83.1</td>
+		<td align="center">84.5</td>
+		<td align="center">88.9</td>
+	</tr>
+	<tr>
+		<td align="center" colspan='7' style="background: linear-gradient(90deg, rgba(252,146,108,0.3) 0%, rgba(227,67,189,0.3) 50%, rgba(104,76,244,0.3) 100%); font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>General</i></td>
+	</tr>
+	<tr>
+		<td align="center">MMStar</td>
+		<td align="center">74.9</td>
+		<td align="center">74.1</td>
+		<td align="center">79.4</td>
+		<td align="center">78.7</td>
+		<td align="center">81.0</td>
+	</tr>
+	<tr>
+		<td align="center">BLINK</td>
+		<td align="center">68.8</td>
+		<td align="center">67.7</td>
+		<td align="center">68.5</td>
+		<td align="center">67.1</td>
+		<td align="center">71.6</td>
+	</tr>
+	<tr>
+		<td align="center">HallusionBench</td>
+		<td align="center">63.7</td>
+		<td align="center">63.2</td>
+		<td align="center">67.4</td>
+		<td align="center">66.7</td>
+		<td align="center">70.0</td>
+	</tr>
+	<tr>
+		<td align="center" colspan='7' style="background: linear-gradient(90deg, rgba(252,146,108,0.3) 0%, rgba(227,67,189,0.3) 50%, rgba(104,76,244,0.3) 100%); font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>Korean</i></td>
+	</tr>
+	<tr>
+		<td align="center">KMMMU</td>
+		<td align="center">42.7</td>
+		<td align="center">42.6</td>
+		<td align="center">37.8</td>
+		<td align="center">42.1</td>
+		<td align="center">51.7</td>
+	</tr>
+	<tr>
+		<td align="center">K-Viscuit</td>
+		<td align="center">80.1</td>
+		<td align="center">78.5</td>
+		<td align="center">78.5</td>
+		<td align="center">83.9</td>
+		<td align="center">84.0</td>
+	</tr>
+	<tr>
+		<td align="center">KRETA</td>
+		<td align="center">91.9</td>
+		<td align="center">94.8</td>
+		<td align="center">90.3</td>
+		<td align="center">92.8</td>
+		<td align="center">96.5</td>
+	</tr>
+</table>
+
+
+### Language-only Tasks
+
+<table>
+	<tr>
+		<th style="background: rgba(128,128,128,0.1); text-align: center;"> </th>
+		<th style="background: rgba(128,128,128,0.1); text-align: center;">EXAONE 4.5 33B (Reasoning)</th>
+		<th style="background: rgba(128,128,128,0.1); text-align: center;">GPT-5 mini (Reasoning: high)</th>
+		<th style="background: rgba(128,128,128,0.1); text-align: center;">K-EXAONE 236B (Reasoning)</th>
+		<th style="background: rgba(128,128,128,0.1); text-align: center;">Qwen3-VL 235B Thinking</th>
+		<th style="background: rgba(128,128,128,0.1); text-align: center;">Qwen3.5 27B (Reasoning)</th>
+	</tr>
+	<tr>
+		<td align="center">Architecture</td>
+		<td align="center">Dense</td>
+		<td align="center">-</td>
+		<td align="center">MoE</td>
+		<td align="center">MoE</td>
+		<td align="center">Dense</td>
+	</tr>
+	<tr>
+		<td align="center">Total Params</td>
+		<td align="center">33B</td>
+		<td align="center">-</td>
+		<td align="center">236B</td>
+		<td align="center">236B</td>
+		<td align="center">27B</td>
+	</tr>
+	<tr>
+		<td align="center">Active Params</td>
+		<td align="center">33B</td>
+		<td align="center">-</td>
+		<td align="center">23B</td>
+		<td align="center">22B</td>
+		<td align="center">27B</td>
+	</tr>
+	<tr>
+		<td align="center" colspan='7' style="background: linear-gradient(90deg, rgba(252,146,108,0.3) 0%, rgba(227,67,189,0.3) 50%, rgba(104,76,244,0.3) 100%); font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>Reasoning</i></td>
+	</tr>
+	<tr>
+		<td align="center">AIME 2025</td>
+		<td align="center">92.9</td>
+		<td align="center">91.1</td>
+		<td align="center">92.8</td>
+		<td align="center">89.7</td>
+		<td align="center">93.5</td>
+	</tr>
+	<tr>
+		<td align="center">AIME 2026</td>
+		<td align="center">92.6</td>
+		<td align="center">92.4</td>
+		<td align="center">92.2</td>
+		<td align="center">89.4</td>
+		<td align="center">90.8</td>
+	</tr>
+	<tr>
+		<td align="center">GPQA-Diamond</td>
+		<td align="center">80.5</td>
+		<td align="center">82.3</td>
+		<td align="center">79.1</td>
+		<td align="center">77.1</td>
+		<td align="center">85.5</td>
+	</tr>
+	<tr>
+		<td align="center">LiveCodeBench v6</td>
+		<td align="center">81.4</td>
+		<td align="center">78.1</td>
+		<td align="center">80.7</td>
+		<td align="center">70.1</td>
+		<td align="center">80.7</td>
+	</tr>
+	<tr>
+		<td align="center">MMLU-Pro</td>
+		<td align="center">83.3</td>
+		<td align="center">83.3</td>
+		<td align="center">83.8</td>
+		<td align="center">83.8</td>
+		<td align="center">86.1</td>
+	</tr>
+	<tr>
+		<td align="center" colspan='7' style="background: linear-gradient(90deg, rgba(252,146,108,0.3) 0%, rgba(227,67,189,0.3) 50%, rgba(104,76,244,0.3) 100%); font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>Agentic Tool Use</i></td>
+	</tr>
+	<tr>
+		<td align="center">τ<sup>2</sup>-Bench (Retail)</td>
+		<td align="center">77.9</td>
+		<td align="center">78.3</td>
+		<td align="center">78.6</td>
+		<td align="center">67.0</td>
+		<td align="center">84.7</td>
+	</tr>
+	<tr>
+		<td align="center">τ<sup>2</sup>-Bench (Airline)</td>
+		<td align="center">56.5</td>
+		<td align="center">60.0</td>
+		<td align="center">60.4</td>
+		<td align="center">62.0</td>
+		<td align="center">67.5</td>
+	</tr>
+	<tr>
+		<td align="center">τ<sup>2</sup>-Bench (Telecom)</td>
+		<td align="center">73.0</td>
+		<td align="center">74.1</td>
+		<td align="center">73.5</td>
+		<td align="center">44.7</td>
+		<td align="center">99.3</td>
+	</tr>
+	<tr>
+		<td align="center" colspan='7' style="background: linear-gradient(90deg, rgba(252,146,108,0.3) 0%, rgba(227,67,189,0.3) 50%, rgba(104,76,244,0.3) 100%); font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>Instruction Following</i></td>
+	</tr>
+	<tr>
+		<td align="center">IFBench</td>
+		<td align="center">62.6</td>
+		<td align="center">74.0</td>
+		<td align="center">67.3</td>
+		<td align="center">59.2</td>
+		<td align="center">76.5</td>
+	</tr>
+	<tr>
+		<td align="center">IFEval</td>
+		<td align="center">89.6</td>
+		<td align="center">92.8</td>
+		<td align="center">89.7</td>
+		<td align="center">88.2</td>
+		<td align="center">95.0</td>
+	</tr>
+	<tr>
+		<td align="center" colspan='7' style="background: linear-gradient(90deg, rgba(252,146,108,0.3) 0%, rgba(227,67,189,0.3) 50%, rgba(104,76,244,0.3) 100%); font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>Long Context Understanding</i></td>
+	</tr>
+	<tr>
+		<td align="center">AA-LCR</td>
+		<td align="center">50.6</td>
+		<td align="center">68.0</td>
+		<td align="center">53.5</td>
+		<td align="center">58.7</td>
+		<td align="center">67.3</td>
+	</tr>
+	<tr>
+		<td align="center" colspan='7' style="background: linear-gradient(90deg, rgba(252,146,108,0.3) 0%, rgba(227,67,189,0.3) 50%, rgba(104,76,244,0.3) 100%); font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>Korean</i></td>
+	</tr>
+	<tr>
+		<td align="center">KMMLU-Pro</td>
+		<td align="center">67.6</td>
+		<td align="center">72.5</td>
+		<td align="center">67.3</td>
+		<td align="center">71.1</td>
+		<td align="center">73.0</td>
+	</tr>
+	<tr>
+		<td align="center">KoBALT</td>
+		<td align="center">52.1</td>
+		<td align="center">63.6</td>
+		<td align="center">61.8</td>
+		<td align="center">51.1</td>
+		<td align="center">54.9</td>
+	</tr>
+</table>
+
+
+
+
+## Quickstart
+
+
+### Serving EXAONE 4.5
+
+For better inference speed and memory usage, it is preferred to serve the model using optimized inference engines. The EXAONE 4.5 model is supported by various frameworks, including TensorRT-LLM, vLLM, SGLang, and llama.cpp. Support will be expanded in the future.
+
+Practically, you can serve the EXAONE 4.5 model with 256K context length on **single H200 GPU**, or **4x A100-40GB GPUs** by using a tensor-parallelism.
+
+
+### vLLM
+
+Both Transformers and vLLM of our forks are required to utilize EXAONE 4.5 model.
+You can install the requirements by running the following commands:
+
+```bash
+uv pip install git+https://github.com/lkm2835/vllm.git@add-exaone4_5
+uv pip install git+https://github.com/nuxlear/transformers.git@add-exaone4_5
+```
+
+After you install the vLLM, you can launch the server with the following code snippet. You can remove unnecessary arguments from the snippet.
+
+```bash
+vllm serve LGAI-EXAONE/EXAONE-4.5-33B \
+    --served-model-name EXAONE-4.5-33B \
+    --port 8000 \
+    --tensor-parallel-size 2 \
+    --max-model-len 262144 \
+    --reasoning-parser qwen3 \
+    --enable-auto-tool-choice \
+    --tool-call-parser hermes \
+    --limit-mm-per-prompt '{"image": 64}' \
+    --speculative_config '{
+        "method": "mtp", 
+        "num_speculative_tokens": 3
+    }'
+
+```
+
+An OpenAI-compatible API server will be available at http://localhost:8000/v1.
+
+
+### SGLang
+
+Both Transformers and SGLang of our forks are required to utilize EXAONE 4.5 model. 
+You can install the requirements by running the following commands:
+
+```bash
+uv pip install git+https://github.com/lkm2835/sglang.git@add-exaone4_5
+uv pip install git+https://github.com/nuxlear/transformers.git@add-exaone4_5
+```
+
+After you install the SGLang, you can launch the server with the following code snippet. You can remove unnecessary arguments from the snippet.
+
+```bash
+python -m sglang.launch_server \
+    --model-path LGAI-EXAONE/EXAONE-4.5-33B \
+    --served-model-name EXAONE-4.5-33B \
+    --port 8000 \
+    --tp-size 2 \
+    --mem-frac 0.81 \
+    --reasoning-parser qwen3 \
+    --tool-call-parser hermes \
+    --speculative-algorithm EAGLE \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4
+
+```
+
+An OpenAI-compatible API server will be available at http://localhost:8000/v1.
+
+
+
+### Using EXAONE 4.5
+
+After launching the OpenAI-compatible server with EXAONE 4.5, you can seamlessly use the model via API with a single code integration, even though the serving framework has changed. To use OpenAI Python SDK and following examples, you should install the `openai` library on your environment.
+
+
+> [!IMPORTANT]
+> To achieve the expected performance, we recommend using the following configurations:
+> - We recommend to use `temperature=1.0`, `top_p=0.95`, `presence_penalty=1.5` for general purpose.
+> - We recommend to use `temperature=0.6`, `top_p=0.95`, `presence_penalty=1.5`, `top_k=20` for OCR/document-related tasks, and Korean inputs.
+> - We recommend to use `temperature=1.0`, `top_p=0.95` for text-only inputs.
+> - Different from EXAONE-4.0, EXAONE 4.5 uses `enable_thinking=True` as default. Thus, you need to set `enable_thinking=False` when you want to use non-reasoning mode.
+> - EXAONE 4.5 prefers using `\boxed{}` format to answer the question. We recommend using this format with the corresponding format instruction for better parsing accuracy. 
+>
+
+
+
+You can easily try model's chat completions by using OpenAI Python SDK. For your server in local machine, you will need to change your `base_url` and `api_key` for the OpenAI client.
+
+
+### Image-Text QA
+
+#### Reasoning mode
+
+For tasks that require accurate results, you can run the EXAONE 4.5 model in reasoning mode as follows.
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    base_url="http://localhost:8000/v1",
+    api_key="EMPTY",
+)
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image_url",
+                "image_url": {
+                    "url": "https://github.com/Aim-Highest/EXAONE-4.5/blob/main/assets/exaone45_input2.png?raw=true",
+                },
+            },
+            {
+                "type": "text",
+                "text": "How much larger is the model released in winter 2025 compared with the one released in summer 2024?",
+            },
+        ]
+    }
+]
+
+response = client.chat.completions.create(
+    model="EXAONE-4.5-33B",
+    messages=messages,
+    max_tokens=32768,
+    temperature=1.0,
+    top_p=0.95,
+    presence_penalty=1.5,
+    extra_body={
+        "chat_template_kwargs": {
+            "enable_thinking": True,  # default: True
+        }
+    }, 
+)
+print(response)
+```
+
+#### Non-reasoning mode
+
+For tasks where latency matters more than accuracy, you can run the EXAONE 4.5 model in non-reasoning mode as follows.
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    base_url="http://localhost:8000/v1",
+    api_key="EMPTY",
+)
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image_url",
+                "image_url": {
+                    "url": "https://github.com/Aim-Highest/EXAONE-4.5/blob/main/assets/exaone45_input1.jpg?raw=true",
+                },
+            },
+            {
+                "type": "text",
+                "text": "What dish is the person preparing, and how is it made?",
+            },
+        ]
+    }
+]
+
+response = client.chat.completions.create(
+    model="EXAONE-4.5-33B",
+    messages=messages,
+    max_tokens=32768,
+    temperature=1.0,
+    top_p=0.95,
+    presence_penalty=1.5,
+    extra_body={
+        "chat_template_kwargs": {
+            "enable_thinking": False,  # default: True
+        }
+    }, 
+)
+print(response)
+
+```
+
+
+### Text-only QA
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    base_url="http://localhost:8000/v1",
+    api_key="EMPTY",
+)
+
+messages = [
+    {
+        "role": "user",
+        "content": "Explain how useful you are.",
+    }
+]
+
+response = client.chat.completions.create(
+    model="EXAONE-4.5-33B",
+    messages=messages,
+    max_tokens=32768,
+    temperature=1.0,
+    top_p=0.95,
+    extra_body={
+        "chat_template_kwargs": {
+            "enable_thinking": True,  # default: True
+        }
+    }, 
+)
+print(response)
+
+```
+
+
+### Agentic Use
+
+The following example demonstrates the agentic capability of EXAONE 4.5 for image-text inputs. You can use your own agents, skills, or other harnesses with the EXAONE 4.5 model.
+
+```python
+# If needed:
+# pip install langchain langchain-openai langchain-mcp-adapters
+# curl -LsSf https://astral.sh/uv/install.sh | sh
+# sudo apt-get update && sudo apt-get install -y nodejs npm
+
+import os
+import asyncio
+from langchain_openai import ChatOpenAI
+from langchain.agents import create_agent
+from langchain_mcp_adapters.client import MultiServerMCPClient
+
+def print_message(msg):
+    parts = msg.content if isinstance(msg.content, list) else [{"type": "text", "text": msg.content or ""}]
+    text_out, reasoning_out = [], []
+
+    for p in parts:
+        if isinstance(p, dict):
+            if p.get("type") in ("text", "output_text") and p.get("text"):
+                text_out.append(p["text"])
+            elif p.get("type") in ("reasoning", "reasoning_text") and p.get("text"):
+                reasoning_out.append(p["text"])
+
+    if reasoning_out:
+        print("\n[assistant_reasoning_content]")
+        print("\n".join(reasoning_out))
+    if text_out:
+        print("\n[assistant_content]")
+        print("\n".join(text_out))
+
+async def main():
+    model = ChatOpenAI(
+        model="EXAONE-4.5-33B",
+        base_url="http://localhost:8000/v1",
+        api_key="EMPTY",
+        temperature=1.0,
+        model_kwargs={"top_p": 0.95},
+    )
+
+    client = MultiServerMCPClient({
+        "filesystem": {
+            "transport": "stdio",
+            "command": "npx",
+            "args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"],
+        },
+        "fetch": {
+            "transport": "stdio",
+            "command": "uvx",
+            "args": ["mcp-server-fetch"],
+        },
+        "duckduckgo": {
+            "transport": "stdio",
+            "command": "uvx",
+            "args": ["duckduckgo-mcp-server"],
+        },
+    })
+
+    agent = create_agent(model, await client.get_tools())
+
+    inputs = {
+        "messages": [{
+            "role": "user",
+            "content": [
+                {
+                    "type": "text",
+                    "text": (
+                        "Look at the image and identify the landmark. "
+                        "Use the DuckDuckGo MCP tool to verify its name, height, and location. "
+                        "Then use the fetch tool to read a fuller article page about it. "
+                        "Create /tmp/mcp-demo and write a short markdown file to "
+                        "/tmp/mcp-demo/landmark.md with: name, location, height, and a one-sentence summary of the article. "
+                        "Finally, return only the exact file content."
+                    ),
+                },
+                {
+                    "type": "image_url",
+                    "image_url": {
+                        "url": "https://upload.wikimedia.org/wikipedia/commons/a/a8/Tour_Eiffel_Wikimedia_Commons.jpg"
+                    },
+                },
+            ],
+        }]
+    }
+
+    async for step in agent.astream(inputs, stream_mode="values"):
+        msg = step["messages"][-1]
+        if getattr(msg, "type", "") == "ai":
+            print_message(msg)
+            for tc in getattr(msg, "tool_calls", []) or []:
+                print(f"\n[tool call] {tc['name']}({tc['args']})")
+
+if __name__ == "__main__":
+    asyncio.run(main())
+
+```
+
+
+
+
+
+## Limitation
+
+EXAONE 4.5 models, like all existing multimodal models, have certain limitations and may occasionally generate
+inappropriate responses. The multimodal model generates responses based on the output probability of tokens, and it
+is determined during learning from training data. While we make every effort to exclude personal, harmful, and biased
+information from the training data, some problematic content may still be included, potentially leading to undesirable
+responses. Please note that the text generated by EXAONE 4.5 models does not reflect the views of LG AI Research.
+
+- Inappropriate answers may be generated, which contain personal, harmful or other inappropriate information.
+- Biased responses may be generated, which are associated with age, gender, race, and so on.
+- The generated responses rely heavily on statistics from the training data, which can result in the generation of
+semantically or syntactically incorrect sentences.
+- Since the models do not reflect the latest information, the responses may be false or contradictory.
+
+LG AI Research strives to reduce potential risks that may arise from EXAONE 4.5 models. Users are not allowed to
+engage in any malicious activities (e.g., keying in illegal information) that may induce the creation of inappropriate
+outputs violating LG AI’s ethical principles when using EXAONE 4.5 models.
+
+
+
+## License
+
+The model is licensed under [EXAONE AI Model License Agreement 1.2 - NC](./LICENSE)
+
+
+
+## Citation
+
+```
+@article{exaone-4.5,
+  title={EXAONE 4.5 Technical Report},
+  author={{LG AI Research}},
+  journal={arXiv preprint arXiv:XXXX.XXXXX},
+  year={2026}
+}
+```
+
+
+## Contact
+
+LG AI Research Technical Support: contact_us@lgresearch.ai
+

chat_template.jinja

@@ -0,0 +1,161 @@
+{% set image_count = namespace(value=0) %}
+{% set video_count = namespace(value=0) %}
+
+{%- set role_indicators = {
+    'user': '<|user|>\n',
+    'assistant': '<|assistant|>\n',
+    'system': '<|system|>\n',
+    'tool': '<|tool|>\n',
+    'tool_declare': '<|tool_declare|>\n'
+} %}
+{%- set end_of_turn = '<|endofturn|>\n' %}
+
+
+{%- macro declare_available_tools(tools) %}
+    {{- "# Tools" }}
+    {{- "\n" }}
+    {%- for tool in tools %}
+        {{- "<tool>" }}
+        {{- tool | tojson(ensure_ascii=False) | safe }}
+        {{- "</tool>\n" }}
+    {%- endfor %}
+{%- endmacro %}
+
+
+{%- set ns = namespace(last_query_index = messages|length - 1, last_query_index_not_yet_determined = true) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.last_query_index_not_yet_determined and message.role == "user" and message.content is string %}
+        {%- set ns.last_query_index = index -%}
+        {%- set ns.last_query_index_not_yet_determined = false -%}
+    {%- endif %}
+{%- endfor %}
+
+{%- if tools is defined and tools %}
+    {{- role_indicators['tool_declare'] }}
+    {{- declare_available_tools(tools) }}
+    {{- end_of_turn -}}  
+{%- endif %}
+
+{%- for i in range(messages | length) %}
+    {%- set msg = messages[i] %}
+    {%- set role = msg.role %}
+    {%- if role not in role_indicators %}
+        {{- raise_exception('Unknown role: ' ~ role) }}
+    {%- endif %}
+    
+    {%- if i == 0 %}
+        {%- if role == 'system' %}
+            {{- role_indicators['system'] }}
+            {{- msg.content }}
+            {{- end_of_turn -}}
+            {%- continue %}          
+        {%- endif %}
+    {%- endif %}
+
+    {%- if role == 'assistant' %}
+        {{- role_indicators['assistant'] }}
+
+        {%- set content = (msg.content if (msg.content is defined and msg.content) else "") -%}
+        {%- set reasoning = none -%}
+
+        {%- if msg.reasoning_content is defined and msg.reasoning_content%}
+            {%- set reasoning = msg.reasoning_content.strip() -%}
+        {%- elif content and "</think>" in content %}
+            {%- set _parts = content.split('</think>') -%}
+            {%- set reasoning = _parts[0].lstrip('<think>').strip() -%}
+            {%- set content = _parts[-1].strip() -%}
+        {%- endif %}
+
+        {%- if not (reasoning and i > ns.last_query_index) or (skip_think is defined and skip_think) %}
+            {%- set reasoning = none %}
+        {%- endif %}
+
+        {%- set content = content.strip() -%}
+        
+        {{- "<think>\n" }}
+        {{- (reasoning if reasoning is not none else "") }}
+        {{- "\n</think>\n\n" }}
+
+        {{- content }}
+
+        {%- if msg.tool_calls %}
+            {%- if content is defined and content %}
+                {{- "\n" }}
+            {%- endif %}
+            {%- for tool_call in msg.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+
+                {%- if tool_call.arguments is defined %}
+                    {%- set arguments = tool_call.arguments %}
+                {%- elif tool_call.parameters is defined %}
+                    {%- set arguments = tool_call.parameters %}
+                {%- else %}
+                    {{- raise_exception('arguments or parameters are mandatory: ' ~ tool_call) }}
+                {%- endif %}
+                {%- if arguments is string %}
+                    {{- "<tool_call>" }}{"name": "{{- tool_call.name }}", "arguments": {{ arguments }}}{{- "</tool_call>" }}
+                {%- else %}
+                    {{- "<tool_call>" }}{"name": "{{- tool_call.name }}", "arguments": {{ arguments | tojson(ensure_ascii=False) | safe }}}{{- "</tool_call>" }}
+                {%- endif %}
+                {%- if not loop.last %}
+                    {{- "\n" }}
+                {%- endif %}
+
+            {%- endfor %}
+        {%- endif %}
+        {{- end_of_turn -}}
+
+    {%- elif role == "tool" %}
+        {%- if i == 0 or messages[i - 1].role != "tool" %}
+            {{- role_indicators['tool'] }}
+        {%- endif %}
+        {%- if msg.content is defined %}          
+            {%- if msg.content is string %}  
+                {{- "<tool_result>" }}{{ msg.content }}{{- "</tool_result>" }} 
+            {%- else %}
+                {{- "<tool_result>" }}{{ msg.content | tojson(ensure_ascii=False) | safe }}{{- "</tool_result>" }}            
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.last or messages[i + 1].role != "tool" %}
+            {{- end_of_turn -}}
+        {%- else %}
+            {{- "\n" }}
+        {%- endif %}
+
+    {%- else %}
+        {{- role_indicators[role] }}
+        {%- if msg.content is string %}
+            {{- msg.content }}
+        {%- else %}
+            {%- for content in msg.content %} 
+                {%- if content.type == 'image' %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif %}
+                    {{- "<vision><|image_pad|></vision>\n" }}
+                {%- elif content.type == 'video' %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif %}
+                    {{- "<vision><|video_pad|></vision>\n" }}
+                {%- elif content.type == 'text' %}
+                    {{- content.text }}
+                {%- else %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- end_of_turn -}}
+    {%- endif %}
+{% endfor %}
+
+
+{%- if add_generation_prompt %}
+    {{- role_indicators['assistant'] }}
+    {%- if enable_thinking is not defined or enable_thinking is true %}
+        {{- "<think>\n" }}
+    {%- else %}
+        {{- "<think>\n\n</think>\n\n" }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,140 @@
+{
+  "architectures": [
+    "Exaone4_5_ForConditionalGeneration"
+  ],
+  "image_token_id": 67,
+  "model_type": "exaone4_5",
+  "text_config": {
+    "_num_mtp_layers": 1,
+    "architectures": [
+      "Exaone4ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "dtype": "bfloat16",
+    "eos_token_id": 53,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 27392,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 262144,
+    "num_nextn_predict_layers": 1,
+    "mtp_loss_scaling_factor": 0.05,
+    "mtp_share_layers": true,
+    "model_type": "exaone4_5_text",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "factor": 16.0,
+      "high_freq_factor": 4.0,
+      "low_freq_factor": 1.0,
+      "original_max_position_embeddings": 8192,
+      "rope_type": "llama3"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 4096,
+    "sliding_window_pattern": "LLLG",
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 153600
+  },
+  "transformers_version": "5.3.0.dev0",
+  "video_token_id": 68,
+  "vision_config": {
+    "depth": 28,
+    "dtype": "bfloat16",
+    "fullatt_block_indexes": [
+      6,
+      13,
+      20,
+      27
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 5120,
+    "model_type": "exaone4_5_vision",
+    "num_heads": 32,
+    "num_key_value_heads": 8,
+    "out_hidden_size": 5120,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "window_size": 112
+  },
+  "vision_end_token_id": 74,
+  "vision_start_token_id": 73,
+  "vision_token_id": 67,
+  "vocab_size": 153600
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 53,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "presence_penalty": 1.5,
+  "temperature": 1.0,
+  "top_p": 0.95,
+  "transformers_version": "5.3.0.dev0",
+  "use_cache": true
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:719196fefe7b934b0eb3f68d5f2550b9831dabf58f8829b8d9a88ea76a84ab66
+size 49736389848

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6322a2171b404e365b9f1bf1e8573f9da238c9cd6958c02e8709e914bd1a80
+size 18963941248

preprocessor_config.json

@@ -0,0 +1,35 @@
+{
+  "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": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Exaone4_5_ImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 3211264,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 3211264,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

processor_config.json

@@ -0,0 +1,73 @@
+{
+  "image_processor": {
+    "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": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Exaone4_5_ImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "input_data_format": null,
+    "max_pixels": 3211264,
+    "merge_size": 2,
+    "min_pixels": 3136,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_tensors": null,
+    "size": {
+      "longest_edge": 3211264,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Exaone4_5_Processor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": false,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Exaone4_5_ImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_frames": 768,
+    "max_pixels": 3211264,
+    "merge_size": 2,
+    "min_frames": 4,
+    "min_pixels": 3136,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 3211264,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Exaone4_5_VideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bd798efa30739e209d51f36cfc2f0a636711e37ad9d69b77e4e5c8ca5f09fab
+size 12160205

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endofturn|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {},
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "processor_class": "Exaone4_5_Processor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "[UNK]"
+}