@huggingface/transformers 4.0.0-next.6 → 4.0.0-next.8

package/README.md

@@ -47,7 +47,7 @@ npm i @huggingface/transformers
 Alternatively, you can use it in vanilla JS, without any bundler, by using a CDN or static hosting. For example, using [ES Modules](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Modules), you can import the library with:
 ```html
 <script type="module">
-    import { pipeline } from 'https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.0.0-next.6';
+    import { pipeline } from 'https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.0.0-next.8';
 </script>
 ```
 
@@ -134,7 +134,7 @@ Ready to dive in? Explore our wide variety of demo applications and templates [h
 
 
 
-By default, Transformers.js uses [hosted pretrained models](https://huggingface.co/models?library=transformers.js) and [precompiled WASM binaries](https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.0.0-next.6/dist/), which should work out-of-the-box. You can customize this as follows:
+By default, Transformers.js uses [hosted pretrained models](https://huggingface.co/models?library=transformers.js) and [precompiled WASM binaries](https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.0.0-next.8/dist/), which should work out-of-the-box. You can customize this as follows:
 
 ### Settings
 
@@ -251,6 +251,8 @@ To find compatible models on the Hub, select the "transformers.js" library tag i
 1. **[BlenderbotSmall](https://huggingface.co/docs/transformers/model_doc/blenderbot-small)** (from Facebook) released with the paper [Recipes for building an open-domain chatbot](https://huggingface.co/papers/2004.13637) by Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Kurt Shuster, Eric M. Smith, Y-Lan Boureau, Jason Weston.
 1. **[BLOOM](https://huggingface.co/docs/transformers/model_doc/bloom)** (from BigScience workshop) released by the [BigScience Workshop](https://bigscience.huggingface.co/).
 1. **[CamemBERT](https://huggingface.co/docs/transformers/model_doc/camembert)** (from Inria/Facebook/Sorbonne) released with the paper [CamemBERT: a Tasty French Language Model](https://huggingface.co/papers/1911.03894) by Louis Martin*, Benjamin Muller*, Pedro Javier Ortiz Suárez*, Yoann Dupont, Laurent Romary, Éric Villemonte de la Clergerie, Djamé Seddah and Benoît Sagot.
+1. **[CHMv2](https://huggingface.co/docs/transformers/main/model_doc/chmv2)** (from Meta) released with the paper [CHMv2: Improvements in Global Canopy Height Mapping using DINOv3](https://huggingface.co/papers/2603.06382) by John Brandt, Seungeun Yi, Jamie Tolan, Xinyuan Li, Peter Potapov, Jessica Ertel, Justine Spore, Huy V. Vo, Michaël Ramamonjisoa, Patrick Labatut, Piotr Bojanowski, Camille Couprie.
+1. **Chatterbox** (from Resemble AI) released with the repository [Chatterbox TTS](https://github.com/resemble-ai/chatterbox) by the Resemble AI team.
 1. **[Chinese-CLIP](https://huggingface.co/docs/transformers/model_doc/chinese_clip)** (from OFA-Sys) released with the paper [Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese](https://huggingface.co/papers/2211.01335) by An Yang, Junshu Pan, Junyang Lin, Rui Men, Yichang Zhang, Jingren Zhou, Chang Zhou.
 1. **[CLAP](https://huggingface.co/docs/transformers/model_doc/clap)** (from LAION-AI) released with the paper [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://huggingface.co/papers/2211.06687) by Yusong Wu, Ke Chen, Tianyu Zhang, Yuchen Hui, Taylor Berg-Kirkpatrick, Shlomo Dubnov.
 1. **[CLIP](https://huggingface.co/docs/transformers/model_doc/clip)** (from OpenAI) released with the paper [Learning Transferable Visual Models From Natural Language Supervision](https://huggingface.co/papers/2103.00020) by Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, Ilya Sutskever.
@@ -267,6 +269,7 @@ To find compatible models on the Hub, select the "transformers.js" library tag i
 1. **[DeBERTa](https://huggingface.co/docs/transformers/model_doc/deberta)** (from Microsoft) released with the paper [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://huggingface.co/papers/2006.03654) by Pengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu Chen.
 1. **[DeBERTa-v2](https://huggingface.co/docs/transformers/model_doc/deberta-v2)** (from Microsoft) released with the paper [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://huggingface.co/papers/2006.03654) by Pengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu Chen.
 1. **[Decision Transformer](https://huggingface.co/docs/transformers/model_doc/decision_transformer)** (from Berkeley/Facebook/Google) released with the paper [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://huggingface.co/papers/2106.01345) by Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, Igor Mordatch.
+1. **[DeepSeek-V3](https://huggingface.co/docs/transformers/model_doc/deepseek_v3)** (from DeepSeek-AI) released with the paper [DeepSeek-V3 Technical Report](https://huggingface.co/papers/2412.19437) by the DeepSeek-AI team.
 1. **[DeiT](https://huggingface.co/docs/transformers/model_doc/deit)** (from Facebook) released with the paper [Training data-efficient image transformers & distillation through attention](https://huggingface.co/papers/2012.12877) by Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, Hervé Jégou.
 1. **[Depth Anything](https://huggingface.co/docs/transformers/main/model_doc/depth_anything)** (from University of Hong Kong and TikTok) released with the paper [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://huggingface.co/papers/2401.10891) by Lihe Yang, Bingyi Kang, Zilong Huang, Xiaogang Xu, Jiashi Feng, Hengshuang Zhao.
 1. **Depth Pro** (from Apple) released with the paper [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://huggingface.co/papers/2410.02073) by Aleksei Bochkovskii, Amaël Delaunoy, Hugo Germain, Marcel Santos, Yichao Zhou, Stephan R. Richter, Vladlen Koltun.
@@ -283,6 +286,7 @@ To find compatible models on the Hub, select the "transformers.js" library tag i
 1. **[ELECTRA](https://huggingface.co/docs/transformers/model_doc/electra)** (from Google Research/Stanford University) released with the paper [ELECTRA: Pre-training text encoders as discriminators rather than generators](https://huggingface.co/papers/2003.10555) by Kevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. Manning.
 1. **ERNIE-4.5** (from Baidu ERNIE Team) released with the blog post [Announcing the Open Source Release of the ERNIE 4.5 Model Family](https://ernie.baidu.com/blog/posts/ernie4.5/) by the Baidu ERNIE Team.
 1. **[ESM](https://huggingface.co/docs/transformers/model_doc/esm)** (from Meta AI) are transformer protein language models.  **ESM-1b** was released with the paper [Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences](https://www.pnas.org/content/118/15/e2016239118) by Alexander Rives, Joshua Meier, Tom Sercu, Siddharth Goyal, Zeming Lin, Jason Liu, Demi Guo, Myle Ott, C. Lawrence Zitnick, Jerry Ma, and Rob Fergus. **ESM-1v** was released with the paper [Language models enable zero-shot prediction of the effects of mutations on protein function](https://doi.org/10.1101/2021.07.09.450648) by Joshua Meier, Roshan Rao, Robert Verkuil, Jason Liu, Tom Sercu and Alexander Rives. **ESM-2 and ESMFold** were released with the paper [Language models of protein sequences at the scale of evolution enable accurate structure prediction](https://doi.org/10.1101/2022.07.20.500902) by Zeming Lin, Halil Akin, Roshan Rao, Brian Hie, Zhongkai Zhu, Wenting Lu, Allan dos Santos Costa, Maryam Fazel-Zarandi, Tom Sercu, Sal Candido, Alexander Rives.
+1. **[EuroBERT](https://huggingface.co/docs/transformers/model_doc/eurobert)** (from the EuroBERT team) released with the paper [EuroBERT: Scaling Multilingual Encoders for European Languages](https://huggingface.co/papers/2503.05500) by Nicolas Boizard, Hippolyte Gisserot-Boukhlef, Duarte M. Alves, André Martins, Ayoub Hammal, Caio Corro, Céline Hudelot, Emmanuel Malherbe, Etienne Malaboeuf, Fanny Jourdan, Gabriel Hautreux, João Alves, Kevin El-Haddad, Manuel Faysse, Maxime Peyrard, Nuno M. Guerreiro, Patrick Fernandes, Ricardo Rei, Pierre Colombo.
 1. **EXAONE** (from LG AI Research) released with the papers [EXAONE 3.0 7.8B Instruction Tuned Language Model](https://huggingface.co/papers/2408.03541) and [EXAONE 3.5: Series of Large Language Models for Real-world Use Cases](https://huggingface.co/papers/2412.04862) by the LG AI Research team.
 1. **[Falcon](https://huggingface.co/docs/transformers/model_doc/falcon)** (from Technology Innovation Institute) by Almazrouei, Ebtesam and Alobeidli, Hamza and Alshamsi, Abdulaziz and Cappelli, Alessandro and Cojocaru, Ruxandra and Debbah, Merouane and Goffinet, Etienne and Heslow, Daniel and Launay, Julien and Malartic, Quentin and Noune, Badreddine and Pannier, Baptiste and Penedo, Guilherme.
 1. **[FalconH1](https://huggingface.co/docs/transformers/model_doc/falcon_h1)** (from Technology Innovation Institute) released with the blog post [Falcon-H1-Tiny: A series of extremely small, yet powerful language models redefining capabilities at small scale](https://huggingface.co/spaces/tiiuae/tiny-h1-blogpost) by the Falcon-LLM team.
@@ -294,6 +298,8 @@ To find compatible models on the Hub, select the "transformers.js" library tag i
 1. **[Gemma3](https://huggingface.co/docs/transformers/main/model_doc/gemma3)** (from Google) released with the paper [Introducing Gemma 3: The most capable model you can run on a single GPU or TPU](https://blog.google/technology/developers/gemma-3/) by the Gemma Google team.
 1. **[Gemma3n](https://huggingface.co/docs/transformers/main/model_doc/gemma3n)** (from Google) released with the paper [Announcing Gemma 3n preview: powerful, efficient, mobile-first AI](https://developers.googleblog.com/en/introducing-gemma-3n/) by the Gemma Google team.
 1. **[GLM](https://huggingface.co/docs/transformers/main/model_doc/glm)** (from the GLM Team, THUDM & ZhipuAI) released with the paper [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://huggingface.co/papers/2406.12793v2) by Team GLM: Aohan Zeng, Bin Xu, Bowen Wang, Chenhui Zhang, Da Yin, Dan Zhang, Diego Rojas, Guanyu Feng, Hanlin Zhao, Hanyu Lai, Hao Yu, Hongning Wang, Jiadai Sun, Jiajie Zhang, Jiale Cheng, Jiayi Gui, Jie Tang, Jing Zhang, Jingyu Sun, Juanzi Li, Lei Zhao, Lindong Wu, Lucen Zhong, Mingdao Liu, Minlie Huang, Peng Zhang, Qinkai Zheng, Rui Lu, Shuaiqi Duan, Shudan Zhang, Shulin Cao, Shuxun Yang, Weng Lam Tam, Wenyi Zhao, Xiao Liu, Xiao Xia, Xiaohan Zhang, Xiaotao Gu, Xin Lv, Xinghan Liu, Xinyi Liu, Xinyue Yang, Xixuan Song, Xunkai Zhang, Yifan An, Yifan Xu, Yilin Niu, Yuantao Yang, Yueyan Li, Yushi Bai, Yuxiao Dong, Zehan Qi, Zhaoyu Wang, Zhen Yang, Zhengxiao Du, Zhenyu Hou, Zihan Wang.
+1. **[GLM-MoE-DSA](https://huggingface.co/docs/transformers/main/model_doc/glm_moe_dsa)** (from the GLM Team, ZhipuAI & Tsinghua University) released with the paper [GLM-5: from Vibe Coding to Agentic Engineering](https://huggingface.co/papers/2602.15763) by Team GLM.
+1. **[GLM-OCR](https://huggingface.co/docs/transformers/main/model_doc/glm_ocr)** (from the GLM Team, ZhipuAI & Tsinghua University) released with the paper [GLM-OCR Technical Report](https://huggingface.co/papers/2603.10910) by Team GLM: Shuaiqi Duan, Yadong Xue, Weihan Wang, Zhe Su, Huan Liu, Sheng Yang, Guobing Gan, Guo Wang, Zihan Wang, Shengdong Yan, Dexin Jin, Yuxuan Zhang, Guohong Wen, Yanfeng Wang, Yutao Zhang, Xiaohan Zhang, Wenyi Hong, Yukuo Cen, Da Yin, Bin Chen, Wenmeng Yu, Xiaotao Gu, Jie Tang.
 1. **[GLPN](https://huggingface.co/docs/transformers/model_doc/glpn)** (from KAIST) released with the paper [Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth](https://huggingface.co/papers/2201.07436) by Doyeon Kim, Woonghyun Ga, Pyungwhan Ahn, Donggyu Joo, Sehwan Chun, Junmo Kim.
 1. **[GPT Neo](https://huggingface.co/docs/transformers/model_doc/gpt_neo)** (from EleutherAI) released in the repository [EleutherAI/gpt-neo](https://github.com/EleutherAI/gpt-neo) by Sid Black, Stella Biderman, Leo Gao, Phil Wang and Connor Leahy.
 1. **[GPT NeoX](https://huggingface.co/docs/transformers/model_doc/gpt_neox)** (from EleutherAI) released with the paper [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://huggingface.co/papers/2204.06745) by Sid Black, Stella Biderman, Eric Hallahan, Quentin Anthony, Leo Gao, Laurence Golding, Horace He, Connor Leahy, Kyle McDonell, Jason Phang, Michael Pieler, USVSN Sai Prashanth, Shivanshu Purohit, Laria Reynolds, Jonathan Tow, Ben Wang, Samuel Weinbach
@@ -303,6 +309,7 @@ To find compatible models on the Hub, select the "transformers.js" library tag i
 1. **[GPTBigCode](https://huggingface.co/docs/transformers/model_doc/gpt_bigcode)** (from BigCode) released with the paper [SantaCoder: don't reach for the stars!](https://huggingface.co/papers/2301.03988) by Loubna Ben Allal, Raymond Li, Denis Kocetkov, Chenghao Mou, Christopher Akiki, Carlos Munoz Ferrandis, Niklas Muennighoff, Mayank Mishra, Alex Gu, Manan Dey, Logesh Kumar Umapathi, Carolyn Jane Anderson, Yangtian Zi, Joel Lamy Poirier, Hailey Schoelkopf, Sergey Troshin, Dmitry Abulkhanov, Manuel Romero, Michael Lappert, Francesco De Toni, Bernardo García del Río, Qian Liu, Shamik Bose, Urvashi Bhattacharyya, Terry Yue Zhuo, Ian Yu, Paulo Villegas, Marco Zocca, Sourab Mangrulkar, David Lansky, Huu Nguyen, Danish Contractor, Luis Villa, Jia Li, Dzmitry Bahdanau, Yacine Jernite, Sean Hughes, Daniel Fried, Arjun Guha, Harm de Vries, Leandro von Werra.
 1. **[Granite](https://huggingface.co/docs/transformers/main/model_doc/granite)** (from IBM) released with the paper [Power Scheduler: A Batch Size and Token Number Agnostic Learning Rate Scheduler](https://huggingface.co/papers/2408.13359) by Yikang Shen, Matthew Stallone, Mayank Mishra, Gaoyuan Zhang, Shawn Tan, Aditya Prasad, Adriana Meza Soria, David D. Cox, Rameswar Panda.
 1. **[GraniteMoeHybrid](https://huggingface.co/docs/transformers/main/model_doc/granitemoehybrid)** (from IBM) released with the blog post [IBM Granite 4.0: hyper-efficient, high performance hybrid models for enterprise](https://www.ibm.com/new/announcements/ibm-granite-4-0-hyper-efficient-high-performance-hybrid-models) by the IBM Granite team.
+1. **[Granite Speech](https://huggingface.co/docs/transformers/main/model_doc/granite_speech)** (from IBM) released with the paper [Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities](https://huggingface.co/papers/2505.08699) by the IBM Granite team.
 1. **[Grounding DINO](https://huggingface.co/docs/transformers/model_doc/grounding-dino)** (from IDEA-Research) released with the paper [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://huggingface.co/papers/2303.05499) by Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Qing Jiang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, Lei Zhang.
 1. **[GroupViT](https://huggingface.co/docs/transformers/model_doc/groupvit)** (from UCSD, NVIDIA) released with the paper [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://huggingface.co/papers/2202.11094) by Jiarui Xu, Shalini De Mello, Sifei Liu, Wonmin Byeon, Thomas Breuel, Jan Kautz, Xiaolong Wang.
 1. **[Helium](https://huggingface.co/docs/transformers/main/model_doc/helium)** (from the Kyutai Team) released with the blog post [Announcing Helium-1 Preview](https://kyutai.org/2025/01/13/helium.html) by the Kyutai Team.
@@ -319,6 +326,8 @@ To find compatible models on the Hub, select the "transformers.js" library tag i
 1. **[LongT5](https://huggingface.co/docs/transformers/model_doc/longt5)** (from Google AI) released with the paper [LongT5: Efficient Text-To-Text Transformer for Long Sequences](https://huggingface.co/papers/2112.07916) by Mandy Guo, Joshua Ainslie, David Uthus, Santiago Ontanon, Jianmo Ni, Yun-Hsuan Sung, Yinfei Yang.
 1. **[LFM2](https://huggingface.co/docs/transformers/model_doc/lfm2)** (from Liquid AI) released with the blog post [Introducing LFM2: The Fastest On-Device Foundation Models on the Market](https://www.liquid.ai/blog/liquid-foundation-models-v2-our-second-series-of-generative-ai-models) by the Liquid AI Team.
 1. **[Lfm2Moe](https://huggingface.co/docs/transformers/model_doc/lfm2_moe)** (from Liquid AI) released with the blog post [LFM2-8B-A1B: An Efficient On-device Mixture-of-Experts](https://www.liquid.ai/blog/lfm2-8b-a1b-an-efficient-on-device-mixture-of-experts) by the Liquid AI Team.
+1. **[LFM2-VL](https://huggingface.co/docs/transformers/model_doc/lfm2_vl)** (from Liquid AI) released with the blog post [LFM2-VL: Efficient Vision-Language Models](https://www.liquid.ai/blog/lfm2-vl-efficient-vision-language-models) by the Liquid AI Team.
+1. **[LightOnOcr](https://huggingface.co/docs/transformers/model_doc/lighton_ocr)** (from LightOn) released with the blog post [LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR](https://huggingface.co/blog/lightonai/lightonocr) by the LightOn Team.
 1. **[LLaMA](https://huggingface.co/docs/transformers/model_doc/llama)** (from The FAIR team of Meta AI) released with the paper [LLaMA: Open and Efficient Foundation Language Models](https://huggingface.co/papers/2302.13971) by Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, Guillaume Lample.
 1. **[Llama2](https://huggingface.co/docs/transformers/model_doc/llama2)** (from The FAIR team of Meta AI) released with the paper [Llama2: Open Foundation and Fine-Tuned Chat Models](https://huggingface.co/papers/2307.09288) by Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller, Cynthia Gao, Vedanuj Goswami, Naman Goyal, Anthony Hartshorn, Saghar Hosseini, Rui Hou, Hakan Inan, Marcin Kardas, Viktor Kerkez Madian Khabsa, Isabel Kloumann, Artem Korenev, Punit Singh Koura, Marie-Anne Lachaux, Thibaut Lavril, Jenya Lee, Diana Liskovich, Yinghai Lu, Yuning Mao, Xavier Martinet, Todor Mihaylov, Pushka rMishra, Igor Molybog, Yixin Nie, Andrew Poulton, Jeremy Reizenstein, Rashi Rungta, Kalyan Saladi, Alan Schelten, Ruan Silva, Eric Michael Smith, Ranjan Subramanian, Xiaoqing EllenTan, Binh Tang, Ross Taylor, Adina Williams, Jian Xiang Kuan, Puxin Xu, Zheng Yan, Iliyan Zarov, Yuchen Zhang, Angela Fan, Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, Thomas Scialom.
 1. **[Llama3](https://huggingface.co/docs/transformers/model_doc/llama3)** (from The FAIR team of Meta AI) released with the paper [The Llama 3 Herd of Models](https://huggingface.co/papers/2407.21783) by the Llama Team at Meta.
@@ -339,6 +348,7 @@ To find compatible models on the Hub, select the "transformers.js" library tag i
 1. **[Ministral3](https://huggingface.co/docs/transformers/model_doc/ministral3)** (from Mistral AI) by The [Mistral AI](https://mistral.ai) team.
 1. **[Mistral](https://huggingface.co/docs/transformers/model_doc/mistral)** (from Mistral AI) by The [Mistral AI](https://mistral.ai) team: Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.
 1. **[Mistral3](https://huggingface.co/docs/transformers/model_doc/mistral3)** (from Mistral AI) by The [Mistral AI](https://mistral.ai) team.
+1. **[Mistral4](https://huggingface.co/docs/transformers/model_doc/mistral4)** (from Mistral AI) by The [Mistral AI](https://mistral.ai) team.
 1. **[MMS](https://huggingface.co/docs/transformers/model_doc/mms)** (from Facebook) released with the paper [Scaling Speech Technology to 1,000+ Languages](https://huggingface.co/papers/2305.13516) by Vineel Pratap, Andros Tjandra, Bowen Shi, Paden Tomasello, Arun Babu, Sayani Kundu, Ali Elkahky, Zhaoheng Ni, Apoorv Vyas, Maryam Fazel-Zarandi, Alexei Baevski, Yossi Adi, Xiaohui Zhang, Wei-Ning Hsu, Alexis Conneau, Michael Auli.
 1. **[MobileBERT](https://huggingface.co/docs/transformers/model_doc/mobilebert)** (from CMU/Google Brain) released with the paper [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://huggingface.co/papers/2004.02984) by Zhiqing Sun, Hongkun Yu, Xiaodan Song, Renjie Liu, Yiming Yang, and Denny Zhou.
 1. **MobileCLIP** (from Apple) released with the paper [MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training](https://huggingface.co/papers/2311.17049) by Pavan Kumar Anasosalu Vasu, Hadi Pouransari, Fartash Faghri, Raviteja Vemulapalli, Oncel Tuzel.
@@ -357,6 +367,8 @@ To find compatible models on the Hub, select the "transformers.js" library tag i
 1. **[MPT](https://huggingface.co/docs/transformers/model_doc/mpt)** (from MosaicML) released with the repository [llm-foundry](https://github.com/mosaicml/llm-foundry/) by the MosaicML NLP Team.
 1. **[MT5](https://huggingface.co/docs/transformers/model_doc/mt5)** (from Google AI) released with the paper [mT5: A massively multilingual pre-trained text-to-text transformer](https://huggingface.co/papers/2010.11934) by Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, Colin Raffel.
 1. **[NanoChat](https://huggingface.co/docs/transformers/model_doc/nanochat)** released with the repository [nanochat: The best ChatGPT that $100 can buy](https://github.com/karpathy/nanochat) by Andrej Karpathy.
+1. **[Nemotron](https://huggingface.co/docs/transformers/model_doc/nemotron)** (from NVIDIA) released with the blog post [NVIDIA AI Foundation Models: Build Custom Enterprise Chatbots and Co-Pilots with Production-Ready LLMs](https://developer.nvidia.com/blog/nvidia-ai-foundation-models-build-custom-enterprise-chatbots-and-co-pilots-with-production-ready-llms/) by the Nemotron team.
+1. **[Nemotron-H](https://huggingface.co/docs/transformers/model_doc/nemotron_h)** (from NVIDIA) released with the papers [Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models](https://huggingface.co/papers/2504.03624), [NVIDIA Nemotron 3: Efficient and Open Intelligence](https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3-White-Paper.pdf), [Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning](https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3-Nano-Technical-Report.pdf), and [Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning](https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3-Super-Technical-Report.pdf) by the Nemotron team.
 1. **NeoBERT** (from Chandar Research Lab) released with the paper [NeoBERT: A Next-Generation BERT](https://huggingface.co/papers/2502.19587) by Lola Le Breton, Quentin Fournier, Mariam El Mezouar, John X. Morris, Sarath Chandar.
 1. **[NLLB](https://huggingface.co/docs/transformers/model_doc/nllb)** (from Meta) released with the paper [No Language Left Behind: Scaling Human-Centered Machine Translation](https://huggingface.co/papers/2207.04672) by the NLLB team.
 1. **[Nougat](https://huggingface.co/docs/transformers/model_doc/nougat)** (from Meta AI) released with the paper [Nougat: Neural Optical Understanding for Academic Documents](https://huggingface.co/papers/2308.13418) by Lukas Blecher, Guillem Cucurull, Thomas Scialom, Robert Stojnic.
@@ -402,6 +414,7 @@ To find compatible models on the Hub, select the "transformers.js" library tag i
 1. **[SigLIP](https://huggingface.co/docs/transformers/main/model_doc/siglip)** (from Google AI) released with the paper [Sigmoid Loss for Language Image Pre-Training](https://huggingface.co/papers/2303.15343) by Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, Lucas Beyer.
 1. **[SmolLM3](https://huggingface.co/docs/transformers/main/model_doc/smollm3) (from Hugging Face) released with the blog post [SmolLM3: smol, multilingual, long-context reasoner](https://huggingface.co/blog/smollm3) by the Hugging Face TB Research team.
 1. **[SmolVLM](https://huggingface.co/docs/transformers/main/model_doc/smolvlm) (from Hugging Face) released with the blog posts [SmolVLM - small yet mighty Vision Language Model](https://huggingface.co/blog/smolvlm) and [SmolVLM Grows Smaller – Introducing the 250M & 500M Models!](https://huggingface.co/blog/smolervlm) by the Hugging Face TB Research team.
+1. **[SolarOpen](https://huggingface.co/docs/transformers/main/model_doc/solar_open)** (from Upstage) released with the paper [Solar Open Technical Report](https://huggingface.co/papers/2601.07022) by Sungrae Park, Sanghoon Kim, Jungho Cho, Gyoungjin Gim, Dawoon Jung, Mikyoung Cha, Eunhae Choo, Taekgyu Hong, Minbyul Jeong, SeHwan Joo, Minsoo Khang, Eunwon Kim, Minjeong Kim, Sujeong Kim, Yunsu Kim, Hyeonju Lee, Seunghyun Lee, Sukyung Lee, Siyoung Park, Gyungin Shin, Inseo Song, Wonho Song, Seonghoon Yang, Seungyoun Yi, Sanghoon Yoon, Jeonghyun Ko, Seyoung Song, Keunwoo Choi, Hwalsuk Lee, Sunghun Kim, Du-Seong Chang, Kyunghyun Cho, Junsuk Choe, Hwaran Lee, Jae-Gil Lee, KyungTae Lim, Alice Oh.
 1. **SNAC** (from Papla Media, ETH Zurich) released with the paper [SNAC: Multi-Scale Neural Audio Codec](https://huggingface.co/papers/2410.14411) by Hubert Siuzdak, Florian Grötschla, Luca A. Lanzendörfer.
 1. **[SpeechT5](https://huggingface.co/docs/transformers/model_doc/speecht5)** (from Microsoft Research) released with the paper [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://huggingface.co/papers/2110.07205) by Junyi Ao, Rui Wang, Long Zhou, Chengyi Wang, Shuo Ren, Yu Wu, Shujie Liu, Tom Ko, Qing Li, Yu Zhang, Zhihua Wei, Yao Qian, Jinyu Li, Furu Wei.
 1. **[SqueezeBERT](https://huggingface.co/docs/transformers/model_doc/squeezebert)** (from Berkeley) released with the paper [SqueezeBERT: What can computer vision teach NLP about efficient neural networks?](https://huggingface.co/papers/2006.11316) by Forrest N. Iandola, Albert E. Shaw, Ravi Krishna, and Kurt W. Keutzer.
@@ -426,6 +439,7 @@ To find compatible models on the Hub, select the "transformers.js" library tag i
 1. **[ViTPose](https://huggingface.co/docs/transformers/model_doc/vitpose)** (from The University of Sydney) released with the paper [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://huggingface.co/papers/2204.12484) by Yufei Xu, Jing Zhang, Qiming Zhang, Dacheng Tao.
 1. **[VITS](https://huggingface.co/docs/transformers/model_doc/vits)** (from Kakao Enterprise) released with the paper [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://huggingface.co/papers/2106.06103) by Jaehyeon Kim, Jungil Kong, Juhee Son.
 1. **[Voxtral](https://huggingface.co/docs/transformers/model_doc/voxtral)** (from Mistral AI) released with the paper [Voxtral](https://huggingface.co/papers/2507.13264) by Alexander H. Liu, Andy Ehrenberg, Andy Lo, Clément Denoix, Corentin Barreau, Guillaume Lample, Jean-Malo Delignon, Khyathi Raghavi Chandu, Patrick von Platen, Pavankumar Reddy Muddireddy, Sanchit Gandhi, Soham Ghosh, Srijan Mishra, Thomas Foubert, Abhinav Rastogi, Adam Yang, Albert Q. Jiang, Alexandre Sablayrolles, Amélie Héliou, Amélie Martin, Anmol Agarwal, Antoine Roux, Arthur Darcet, Arthur Mensch, Baptiste Bout, Baptiste Rozière, Baudouin De Monicault, Chris Bamford, Christian Wallenwein, Christophe Renaudin, Clémence Lanfranchi, Darius Dabert, Devendra Singh Chaplot, Devon Mizelle, Diego de las Casas, Elliot Chane-Sane, Emilien Fugier, Emma Bou Hanna, Gabrielle Berrada, Gauthier Delerce, Gauthier Guinet, Georgii Novikov, Guillaume Martin, Himanshu Jaju, Jan Ludziejewski, Jason Rute, Jean-Hadrien Chabran, Jessica Chudnovsky, Joachim Studnia, Joep Barmentlo, Jonas Amar, Josselin Somerville Roberts, Julien Denize, Karan Saxena, Karmesh Yadav, Kartik Khandelwal, Kush Jain, Lélio Renard Lavaud, Léonard Blier, Lingxiao Zhao, Louis Martin, Lucile Saulnier, Luyu Gao, Marie Pellat, Mathilde Guillaumin, Mathis Felardos, Matthieu Dinot, Maxime Darrin, Maximilian Augustin, Mickaël Seznec, Neha Gupta, Nikhil Raghuraman, Olivier Duchenne, Patricia Wang, Patryk Saffer, Paul Jacob, Paul Wambergue, Paula Kurylowicz, Philomène Chagniot, Pierre Stock, Pravesh Agrawal, Rémi Delacourt, Romain Sauvestre, Roman Soletskyi, Sagar Vaze, Sandeep Subramanian, Saurabh Garg, Shashwat Dalal, Siddharth Gandhi, Sumukh Aithal, Szymon Antoniak, Teven Le Scao, Thibault Schueller, Thibaut Lavril, Thomas Robert, Thomas Wang, Timothée Lacroix, Tom Bewley, Valeriia Nemychnikova, Victor Paltz , Virgile Richard, Wen-Ding Li, William Marshall, Xuanyu Zhang, Yihan Wan, Yunhao Tang.
+1. **[Voxtral Realtime](https://huggingface.co/docs/transformers/model_doc/voxtral_realtime)** (from Mistral AI) released with the paper [Voxtral Realtime](https://huggingface.co/papers/2602.11298) by Alexander H. Liu, Andy Ehrenberg, Andy Lo, Chen-Yo Sun, Guillaume Lample, Jean-Malo Delignon, Khyathi Raghavi Chandu, Patrick von Platen, Pavankumar Reddy Muddireddy, Rohin Arora, Sanchit Gandhi, Sandeep Subramanian, Soham Ghosh, Srijan Mishra, Abhinav Rastogi, Adrien Sadé, Alan Jeffares, Albert Jiang, Alexandre Cahill, Alexandre Gavaudan, Alexandre Sablayrolles, Amélie Héliou, Amos You, Andrew Bai, Angele Lenglemetz, Anmol Agarwal, Anton Eliseev, Antonia Calvi, Arjun Majumdar, Avi Sooriyarachchi, Baptiste Bout, Baptiste Rozière, Baudouin De Monicault, Benjamin Tibi, Charlotte Cronjäger, Clémence Lanfranchi, Connor Chen, Corentin Barreau, Corentin Sautier, Cyprien Courtot, Darius Dabert, Diego de las Casas, Elizaveta Demyanenko, Elliot Chane-Sane, Enguerrand Paquin, Etienne Goffinet, Fabien Niel, Faruk Ahmed, Federico Baldassarre, Gabrielle Berrada, Gaëtan Ecrepont, Gauthier Guinet, Genevieve Hayes, Georgii Novikov, Giada Pistilli, Guillaume Kunsch, Guillaume Martin, Guillaume Raille, Gunjan Dhanuka, Gunshi Gupta, Han Zhou, Harshil Shah, Hope McGovern, Hugo Thimonier, Indraneel Mukherjee, Irene Zhang, Jaeyoung Kim, Jan Ludziejewski, Jason Rute, Joachim Studnia, John Harvill, Jonas Amar, Joséphine Delas, Josselin Somerville Roberts, Julien Tauran, Karmesh Yadav, Kartik Khandelwal, Kilian Tep, Kush Jain, Laurence Aitchison, Laurent Fainsin, Léonard Blier, Lingxiao Zhao, Louis Martin, Lucile Saulnier, Luyu Gao, Maarten Buyl, Manan Sharma, Margaret Jennings, Marie Pellat, Mark Prins, Martin Alexandre, Mathieu Poirée, Mathilde Guillaumin, Matthieu Dinot, Matthieu Futeral, Maxime Darrin, Maximilian Augustin, Mert Unsal, Mia Chiquier , Minh-Quang Pham, Nathan Grinsztajn, Neha Gupta, Olivier Bousquet, Olivier Duchenne, Patricia Wang, Paul Jacob, Paul Wambergue, Paula Kurylowicz, Philippe Pinel, Philomène Chagniot, Pierre Stock, Piotr Miłoś, Prateek Gupta, Pravesh Agrawal, Quentin Torroba, Ram Ramrakhya, Rishi Shah, Romain Sauvestre, Roman Soletskyi, Rosalie Millner, Rupert Menneer, Sagar Vaze, Samuel Barry, Samuel Humeau, Sean Cha, Shashwat Verma, Siddhant Waghjale, Siddharth Gandhi, Simon Lepage, Sumukh Aithal, Szymon Antoniak, Teven Le Scao, Théo Cachet, Theo Simon Sorg, Thibaut Lavril, Thomas Chabal, Thomas Foubert, Thomas Robert, Thomas Wang, Tim Lawson, Tom Bewley, Tom Edwards, Tyler Wang, Umar Jamil, Umberto Tomasini, Valeriia Nemychnikova, Van Phung, Vedant Nanda, Victor Jouault, Vincent Maladière, Virgile Richard, Vladislav Bataev, Wassim Bouaziz, Wen-Ding Li, William Havard, William Marshall, Xinghui Li, Xingran Guo, Xinyu Yang, Yannic Neuhaus, Yassine El Ouahidi, Yassir Bendou, Yihan Wang, Yimu Pan, Zaccharie Ramzi, Zhenlin Xu.
 1. **[Wav2Vec2](https://huggingface.co/docs/transformers/model_doc/wav2vec2)** (from Facebook AI) released with the paper [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://huggingface.co/papers/2006.11477) by Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, Michael Auli.
 1. **[Wav2Vec2-BERT](https://huggingface.co/docs/transformers/main/model_doc/wav2vec2-bert)** (from Meta AI) released with the paper [Seamless: Multilingual Expressive and Streaming Speech Translation](https://ai.meta.com/research/publications/seamless-multilingual-expressive-and-streaming-speech-translation/) by the Seamless Communication team.
 1. **[WavLM](https://huggingface.co/docs/transformers/model_doc/wavlm)** (from Microsoft Research) released with the paper [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://huggingface.co/papers/2110.13900) by Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, Jian Wu, Long Zhou, Shuo Ren, Yanmin Qian, Yao Qian, Jian Wu, Michael Zeng, Furu Wei.

package/dist/ort-wasm-simd-threaded.jsep.mjs

@@ -12,7 +12,7 @@ if(m){var Ba=!1;self.onunhandledrejection=b=>{throw b.reason||b;};function a(b){
 e)throw e;}}else"setimmediate"!==d.target&&("checkMailbox"===c?Ba&&Ka():c&&(r(`worker: received unknown command ${c}`),r(d)))}catch(e){throw La(),e;}}self.onmessage=a}var A,B,Ma,Na,C,D,Oa,E,F,Pa,Qa=!1;function wa(){var a=x.buffer;f.HEAP8=A=new Int8Array(a);Ma=new Int16Array(a);f.HEAPU8=B=new Uint8Array(a);Na=new Uint16Array(a);f.HEAP32=C=new Int32Array(a);f.HEAPU32=D=new Uint32Array(a);Oa=new Float32Array(a);E=new Float64Array(a);F=new BigInt64Array(a);Pa=new BigUint64Array(a)}
 function Ra(){Qa=!0;m?Aa():G.tb()}function H(a){a="Aborted("+a+")";r(a);t=!0;a=new WebAssembly.RuntimeError(a+". Build with -sASSERTIONS for more info.");ya?.(a);throw a;}var Sa;async function Ta(a){if(!ta)try{var b=await la(a);return new Uint8Array(b)}catch{}if(a==Sa&&ta)a=new Uint8Array(ta);else if(ma)a=ma(a);else throw"both async and sync fetching of the wasm failed";return a}
 async function Ua(a,b){try{var d=await Ta(a);return await WebAssembly.instantiate(d,b)}catch(c){r(`failed to asynchronously prepare wasm: ${c}`),H(c)}}async function Va(a){var b=Sa;if(!ta&&!na(b)&&!h)try{var d=fetch(b,{credentials:"same-origin"});return await WebAssembly.instantiateStreaming(d,a)}catch(c){r(`wasm streaming compile failed: ${c}`),r("falling back to ArrayBuffer instantiation")}return Ua(b,a)}
-function Wa(){Xa={ma:Ya,hb:Za,g:$a,J:ab,f:bb,o:cb,h:db,ha:eb,b:fb,T:gb,Ia:hb,n:ib,_:jb,Ya:mb,Ea:nb,Ga:ob,Za:pb,Wa:qb,Pa:rb,Va:sb,ka:tb,Fa:ub,Ca:vb,Xa:wb,Da:xb,cb:yb,ea:zb,xa:Ab,va:Bb,da:Cb,O:Db,H:Eb,wa:Fb,Z:Gb,ya:Hb,Sa:Ib,Aa:Jb,Ja:Kb,ta:Lb,fa:Mb,Ra:Ha,$a:Nb,R:Ob,r:Pb,c:Qb,ib:Rb,y:Sb,M:Tb,D:Ub,m:Vb,t:Wb,jb:Xb,I:Yb,S:Zb,j:$b,v:ac,q:bc,l:cc,Ma:dc,Na:ec,Oa:fc,Ka:gc,La:hc,ua:ic,eb:jc,bb:kc,u:lc,aa:mc,ga:nc,ab:oc,V:pc,_a:qc,Ba:rc,F:sc,U:tc,la:uc,za:vc,gb:wc,fb:xc,Ta:yc,Ua:zc,Ha:Ac,$:Bc,ja:Cc,Qa:Dc,ia:Ec,
+function Wa(){Xa={ma:Ya,hb:Za,g:$a,J:ab,f:bb,n:cb,h:db,ha:eb,b:fb,T:gb,Ia:hb,o:ib,_:jb,Ya:mb,Ea:nb,Ga:ob,Za:pb,Wa:qb,Pa:rb,Va:sb,ka:tb,Fa:ub,Ca:vb,Xa:wb,Da:xb,cb:yb,ea:zb,xa:Ab,va:Bb,da:Cb,O:Db,H:Eb,wa:Fb,Z:Gb,ya:Hb,Sa:Ib,Aa:Jb,Ja:Kb,ta:Lb,fa:Mb,Ra:Ha,$a:Nb,R:Ob,r:Pb,c:Qb,ib:Rb,y:Sb,M:Tb,D:Ub,m:Vb,t:Wb,jb:Xb,I:Yb,S:Zb,j:$b,u:ac,q:bc,l:cc,Ma:dc,Na:ec,Oa:fc,Ka:gc,La:hc,ua:ic,eb:jc,bb:kc,v:lc,aa:mc,ga:nc,ab:oc,V:pc,_a:qc,Ba:rc,F:sc,U:tc,la:uc,za:vc,gb:wc,fb:xc,Ta:yc,Ua:zc,Ha:Ac,$:Bc,ja:Cc,Qa:Dc,ia:Ec,
 lb:Fc,na:Gc,mb:Hc,oa:Ic,G:Jc,d:Kc,s:Lc,w:Mc,B:Nc,pb:Oc,K:Pc,x:Qc,pa:Rc,X:Sc,ba:Tc,nb:Uc,ob:Vc,ra:Wc,qa:Xc,qb:Yc,N:Zc,Y:$c,e:ad,A:bd,k:cd,kb:dd,p:ed,z:fd,C:gd,E:hd,L:jd,rb:kd,Q:ld,ca:md,W:nd,sb:od,sa:pd,P:qd,i:rd,a:x,db:sd};return{a:Xa}}
 async function Ca(){function a(c,e){var g=G=c.exports;c={};for(let [k,l]of Object.entries(g))"function"==typeof l?(g=td(l),c[k]=g):c[k]=l;G=c;G=ud();vd.push(G.$b);c=G;wd=c.ub;Ia=c.vb;f._OrtInit=c.wb;f._OrtGetLastError=c.xb;f._OrtCreateSessionOptions=c.yb;f._OrtAppendExecutionProvider=c.zb;f._OrtAddFreeDimensionOverride=c.Ab;f._OrtAddSessionConfigEntry=c.Bb;f._OrtReleaseSessionOptions=c.Cb;f._OrtCreateSession=c.Db;f._OrtReleaseSession=c.Eb;f._OrtGetInputOutputCount=c.Fb;f._OrtGetInputOutputMetadata=
 c.Gb;f._OrtFree=c.Hb;f._OrtCreateTensor=c.Ib;f._OrtGetTensorData=c.Jb;f._OrtReleaseTensor=c.Kb;f._OrtCreateRunOptions=c.Lb;f._OrtAddRunConfigEntry=c.Mb;f._OrtReleaseRunOptions=c.Nb;f._OrtCreateBinding=c.Ob;f._OrtBindInput=c.Pb;f._OrtBindOutput=c.Qb;f._OrtClearBoundOutputs=c.Rb;f._OrtReleaseBinding=c.Sb;f._OrtRunWithBinding=c.Tb;f._OrtRun=c.Ub;f._OrtEndProfiling=c.Vb;f._JsepOutput=c.Wb;f._JsepGetNodeName=c.Xb;xd=c.Yb;I=f._free=c.Zb;yd=f._malloc=c._b;Fa=c.bc;La=c.cc;zd=c.dc;Ad=c.ec;Bd=c.fc;Cd=c.gc;
@@ -68,31 +68,31 @@ function zc(a,b){if(m)return P(20,1,a,b);a>>>=0;b>>>=0;var d=Vf();(u(),D)[a>>>2>
 function Ec(a,b,d,c){if(m)return P(24,1,a,b,d,c);b>>>=0;d>>>=0;c>>>=0;for(var e=0,g=0;g<d;g++){var k=(u(),D)[b>>>2>>>0],l=(u(),D)[b+4>>>2>>>0];b+=8;for(var n=0;n<l;n++){var p=a,v=(u(),B)[k+n>>>0],w=Wf[p];0===v||10===v?((1===p?sa:r)(Te(w)),w.length=0):w.push(v)}e+=l}(u(),D)[c>>>2>>>0]=e;return 0}function rd(a){return a>>>0}m||Ge();m||(x=new WebAssembly.Memory({initial:256,maximum:65536,shared:!0}),wa());f.wasmBinary&&(ta=f.wasmBinary);f.stackSave=()=>L();f.stackRestore=a=>K(a);f.stackAlloc=a=>Gd(a);
 f.setValue=function(a,b,d="i8"){d.endsWith("*")&&(d="*");switch(d){case "i1":(u(),A)[a>>>0]=b;break;case "i8":(u(),A)[a>>>0]=b;break;case "i16":(u(),Ma)[a>>>1>>>0]=b;break;case "i32":(u(),C)[a>>>2>>>0]=b;break;case "i64":(u(),F)[a>>>3>>>0]=BigInt(b);break;case "float":(u(),Oa)[a>>>2>>>0]=b;break;case "double":(u(),E)[a>>>3>>>0]=b;break;case "*":(u(),D)[a>>>2>>>0]=b;break;default:H(`invalid type for setValue: ${d}`)}};
 f.getValue=function(a,b="i8"){b.endsWith("*")&&(b="*");switch(b){case "i1":return(u(),A)[a>>>0];case "i8":return(u(),A)[a>>>0];case "i16":return(u(),Ma)[a>>>1>>>0];case "i32":return(u(),C)[a>>>2>>>0];case "i64":return(u(),F)[a>>>3>>>0];case "float":return(u(),Oa)[a>>>2>>>0];case "double":return(u(),E)[a>>>3>>>0];case "*":return(u(),D)[a>>>2>>>0];default:H(`invalid type for getValue: ${b}`)}};f.UTF8ToString=R;f.stringToUTF8=Y;f.lengthBytesUTF8=df;
-var pf=[sd,Fe,Qe,jb,mb,nb,ob,pb,qb,rb,sb,tb,ub,vb,wb,xb,gc,hc,ic,yc,zc,Bc,Cc,Dc,Ec],of={934668:(a,b,d,c,e)=>{if("undefined"==typeof f||!f.Zc)return 1;a=R(Number(a>>>0));a.startsWith("./")&&(a=a.substring(2));a=f.Zc.get(a);if(!a)return 2;b=Number(b>>>0);d=Number(d>>>0);c=Number(c>>>0);if(b+d>a.byteLength)return 3;try{const g=a.subarray(b,b+d);switch(e){case 0:(u(),B).set(g,c>>>0);break;case 1:f.Xd?f.Xd(c,g):f.Ld(c,g);break;default:return 4}return 0}catch{return 4}},935492:(a,b,d)=>{f.wd(a,(u(),B).subarray(b>>>
-0,b+d>>>0))},935556:()=>f.Zd(),935598:a=>{f.vd(a)},935635:()=>{f.Ed()},935666:()=>{f.Fd()},935695:()=>{f.Jd()},935720:a=>f.Dd(a),935753:a=>f.Hd(a),935785:(a,b,d)=>{f.jd(Number(a),Number(b),Number(d),!0)},935848:(a,b,d)=>{f.jd(Number(a),Number(b),Number(d))},935905:()=>"undefined"!==typeof wasmOffsetConverter,935962:a=>{f.ac("Abs",a,void 0)},936013:a=>{f.ac("Neg",a,void 0)},936064:a=>{f.ac("Floor",a,void 0)},936117:a=>{f.ac("Ceil",a,void 0)},936169:a=>{f.ac("Reciprocal",a,void 0)},936227:a=>{f.ac("Sqrt",
-a,void 0)},936279:a=>{f.ac("Exp",a,void 0)},936330:a=>{f.ac("Erf",a,void 0)},936381:a=>{f.ac("Sigmoid",a,void 0)},936436:(a,b,d)=>{f.ac("HardSigmoid",a,{alpha:b,beta:d})},936515:a=>{f.ac("Log",a,void 0)},936566:a=>{f.ac("Sin",a,void 0)},936617:a=>{f.ac("Cos",a,void 0)},936668:a=>{f.ac("Tan",a,void 0)},936719:a=>{f.ac("Asin",a,void 0)},936771:a=>{f.ac("Acos",a,void 0)},936823:a=>{f.ac("Atan",a,void 0)},936875:a=>{f.ac("Sinh",a,void 0)},936927:a=>{f.ac("Cosh",a,void 0)},936979:a=>{f.ac("Asinh",a,void 0)},
-937032:a=>{f.ac("Acosh",a,void 0)},937085:a=>{f.ac("Atanh",a,void 0)},937138:a=>{f.ac("Tanh",a,void 0)},937190:a=>{f.ac("Not",a,void 0)},937241:(a,b,d)=>{f.ac("Clip",a,{min:b,max:d})},937310:a=>{f.ac("Clip",a,void 0)},937362:(a,b)=>{f.ac("Elu",a,{alpha:b})},937420:a=>{f.ac("Gelu",a,void 0)},937472:a=>{f.ac("Relu",a,void 0)},937524:(a,b)=>{f.ac("LeakyRelu",a,{alpha:b})},937588:(a,b)=>{f.ac("ThresholdedRelu",a,{alpha:b})},937658:(a,b)=>{f.ac("Cast",a,{to:b})},937716:a=>{f.ac("Add",a,void 0)},937767:a=>
-{f.ac("Sub",a,void 0)},937818:a=>{f.ac("Mul",a,void 0)},937869:a=>{f.ac("Div",a,void 0)},937920:a=>{f.ac("Pow",a,void 0)},937971:a=>{f.ac("Equal",a,void 0)},938024:a=>{f.ac("Greater",a,void 0)},938079:a=>{f.ac("GreaterOrEqual",a,void 0)},938141:a=>{f.ac("Less",a,void 0)},938193:a=>{f.ac("LessOrEqual",a,void 0)},938252:(a,b,d,c,e)=>{f.ac("ReduceMean",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},938427:(a,b,d,c,e)=>{f.ac("ReduceMax",a,
-{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},938601:(a,b,d,c,e)=>{f.ac("ReduceMin",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},938775:(a,b,d,c,e)=>{f.ac("ReduceProd",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},938950:(a,b,d,c,e)=>{f.ac("ReduceSum",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),
-C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},939124:(a,b,d,c,e)=>{f.ac("ReduceL1",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},939297:(a,b,d,c,e)=>{f.ac("ReduceL2",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},939470:(a,b,d,c,e)=>{f.ac("ReduceLogSum",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},939647:(a,b,
-d,c,e)=>{f.ac("ReduceSumSquare",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},939827:(a,b,d,c,e)=>{f.ac("ReduceLogSumExp",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},940007:a=>{f.ac("Where",a,void 0)},940060:(a,b,d)=>{f.ac("Transpose",a,{perm:b?Array.from((u(),C).subarray(Number(b)>>>0,Number(d)>>>0)):[]})},940184:(a,b,d,c)=>{f.ac("DepthToSpace",a,{blocksize:b,mode:R(d),
-format:c?"NHWC":"NCHW"})},940317:(a,b,d,c)=>{f.ac("DepthToSpace",a,{blocksize:b,mode:R(d),format:c?"NHWC":"NCHW"})},940450:(a,b,d,c,e,g,k,l,n,p,v,w,y,z,W)=>{f.ac("ConvTranspose",a,{format:n?"NHWC":"NCHW",autoPad:b,dilations:[d],group:c,kernelShape:[e],pads:[g,k],strides:[l],wIsConst:()=>!!(u(),A)[p>>>0],outputPadding:v?Array.from((u(),C).subarray(Number(v)>>>0,Number(w)>>>0)):[],outputShape:y?Array.from((u(),C).subarray(Number(y)>>>0,Number(z)>>>0)):[],activation:R(W)})},940883:(a,b,d,c,e,g,k,l,n,
+var pf=[sd,Fe,Qe,jb,mb,nb,ob,pb,qb,rb,sb,tb,ub,vb,wb,xb,gc,hc,ic,yc,zc,Bc,Cc,Dc,Ec],of={937996:(a,b,d,c,e)=>{if("undefined"==typeof f||!f.Zc)return 1;a=R(Number(a>>>0));a.startsWith("./")&&(a=a.substring(2));a=f.Zc.get(a);if(!a)return 2;b=Number(b>>>0);d=Number(d>>>0);c=Number(c>>>0);if(b+d>a.byteLength)return 3;try{const g=a.subarray(b,b+d);switch(e){case 0:(u(),B).set(g,c>>>0);break;case 1:f.Xd?f.Xd(c,g):f.Ld(c,g);break;default:return 4}return 0}catch{return 4}},938820:(a,b,d)=>{f.wd(a,(u(),B).subarray(b>>>
+0,b+d>>>0))},938884:()=>f.Zd(),938926:a=>{f.vd(a)},938963:()=>{f.Ed()},938994:()=>{f.Fd()},939023:()=>{f.Jd()},939048:a=>f.Dd(a),939081:a=>f.Hd(a),939113:(a,b,d)=>{f.jd(Number(a),Number(b),Number(d),!0)},939176:(a,b,d)=>{f.jd(Number(a),Number(b),Number(d))},939233:()=>"undefined"!==typeof wasmOffsetConverter,939290:a=>{f.ac("Abs",a,void 0)},939341:a=>{f.ac("Neg",a,void 0)},939392:a=>{f.ac("Floor",a,void 0)},939445:a=>{f.ac("Ceil",a,void 0)},939497:a=>{f.ac("Reciprocal",a,void 0)},939555:a=>{f.ac("Sqrt",
+a,void 0)},939607:a=>{f.ac("Exp",a,void 0)},939658:a=>{f.ac("Erf",a,void 0)},939709:a=>{f.ac("Sigmoid",a,void 0)},939764:(a,b,d)=>{f.ac("HardSigmoid",a,{alpha:b,beta:d})},939843:a=>{f.ac("Log",a,void 0)},939894:a=>{f.ac("Sin",a,void 0)},939945:a=>{f.ac("Cos",a,void 0)},939996:a=>{f.ac("Tan",a,void 0)},940047:a=>{f.ac("Asin",a,void 0)},940099:a=>{f.ac("Acos",a,void 0)},940151:a=>{f.ac("Atan",a,void 0)},940203:a=>{f.ac("Sinh",a,void 0)},940255:a=>{f.ac("Cosh",a,void 0)},940307:a=>{f.ac("Asinh",a,void 0)},
+940360:a=>{f.ac("Acosh",a,void 0)},940413:a=>{f.ac("Atanh",a,void 0)},940466:a=>{f.ac("Tanh",a,void 0)},940518:a=>{f.ac("Not",a,void 0)},940569:(a,b,d)=>{f.ac("Clip",a,{min:b,max:d})},940638:a=>{f.ac("Clip",a,void 0)},940690:(a,b)=>{f.ac("Elu",a,{alpha:b})},940748:a=>{f.ac("Gelu",a,void 0)},940800:a=>{f.ac("Relu",a,void 0)},940852:(a,b)=>{f.ac("LeakyRelu",a,{alpha:b})},940916:(a,b)=>{f.ac("ThresholdedRelu",a,{alpha:b})},940986:(a,b)=>{f.ac("Cast",a,{to:b})},941044:a=>{f.ac("Add",a,void 0)},941095:a=>
+{f.ac("Sub",a,void 0)},941146:a=>{f.ac("Mul",a,void 0)},941197:a=>{f.ac("Div",a,void 0)},941248:a=>{f.ac("Pow",a,void 0)},941299:a=>{f.ac("Equal",a,void 0)},941352:a=>{f.ac("Greater",a,void 0)},941407:a=>{f.ac("GreaterOrEqual",a,void 0)},941469:a=>{f.ac("Less",a,void 0)},941521:a=>{f.ac("LessOrEqual",a,void 0)},941580:(a,b,d,c,e)=>{f.ac("ReduceMean",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},941755:(a,b,d,c,e)=>{f.ac("ReduceMax",a,
+{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},941929:(a,b,d,c,e)=>{f.ac("ReduceMin",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},942103:(a,b,d,c,e)=>{f.ac("ReduceProd",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},942278:(a,b,d,c,e)=>{f.ac("ReduceSum",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),
+C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},942452:(a,b,d,c,e)=>{f.ac("ReduceL1",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},942625:(a,b,d,c,e)=>{f.ac("ReduceL2",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},942798:(a,b,d,c,e)=>{f.ac("ReduceLogSum",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},942975:(a,b,
+d,c,e)=>{f.ac("ReduceSumSquare",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},943155:(a,b,d,c,e)=>{f.ac("ReduceLogSumExp",a,{keepDims:!!b,noopWithEmptyAxes:!!d,axes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},943335:a=>{f.ac("Where",a,void 0)},943388:(a,b,d)=>{f.ac("Transpose",a,{perm:b?Array.from((u(),C).subarray(Number(b)>>>0,Number(d)>>>0)):[]})},943512:(a,b,d,c)=>{f.ac("DepthToSpace",a,{blocksize:b,mode:R(d),
+format:c?"NHWC":"NCHW"})},943645:(a,b,d,c)=>{f.ac("DepthToSpace",a,{blocksize:b,mode:R(d),format:c?"NHWC":"NCHW"})},943778:(a,b,d,c,e,g,k,l,n,p,v,w,y,z,W)=>{f.ac("ConvTranspose",a,{format:n?"NHWC":"NCHW",autoPad:b,dilations:[d],group:c,kernelShape:[e],pads:[g,k],strides:[l],wIsConst:()=>!!(u(),A)[p>>>0],outputPadding:v?Array.from((u(),C).subarray(Number(v)>>>0,Number(w)>>>0)):[],outputShape:y?Array.from((u(),C).subarray(Number(y)>>>0,Number(z)>>>0)):[],activation:R(W)})},944211:(a,b,d,c,e,g,k,l,n,
 p,v,w,y,z)=>{f.ac("ConvTranspose",a,{format:l?"NHWC":"NCHW",autoPad:b,dilations:Array.from((u(),C).subarray(Number(d)>>>0,(Number(d)>>>0)+2>>>0)),group:c,kernelShape:Array.from((u(),C).subarray(Number(e)>>>0,(Number(e)>>>0)+2>>>0)),pads:Array.from((u(),C).subarray(Number(g)>>>0,(Number(g)>>>0)+4>>>0)),strides:Array.from((u(),C).subarray(Number(k)>>>0,(Number(k)>>>0)+2>>>0)),wIsConst:()=>!!(u(),A)[n>>>0],outputPadding:p?Array.from((u(),C).subarray(Number(p)>>>0,Number(v)>>>0)):[],outputShape:w?Array.from((u(),
-C).subarray(Number(w)>>>0,Number(y)>>>0)):[],activation:R(z)})},941544:(a,b,d,c,e,g,k,l,n,p,v,w,y,z,W)=>{f.ac("ConvTranspose",a,{format:n?"NHWC":"NCHW",autoPad:b,dilations:[d],group:c,kernelShape:[e],pads:[g,k],strides:[l],wIsConst:()=>!!(u(),A)[p>>>0],outputPadding:v?Array.from((u(),C).subarray(Number(v)>>>0,Number(w)>>>0)):[],outputShape:y?Array.from((u(),C).subarray(Number(y)>>>0,Number(z)>>>0)):[],activation:R(W)})},941977:(a,b,d,c,e,g,k,l,n,p,v,w,y,z)=>{f.ac("ConvTranspose",a,{format:l?"NHWC":
+C).subarray(Number(w)>>>0,Number(y)>>>0)):[],activation:R(z)})},944872:(a,b,d,c,e,g,k,l,n,p,v,w,y,z,W)=>{f.ac("ConvTranspose",a,{format:n?"NHWC":"NCHW",autoPad:b,dilations:[d],group:c,kernelShape:[e],pads:[g,k],strides:[l],wIsConst:()=>!!(u(),A)[p>>>0],outputPadding:v?Array.from((u(),C).subarray(Number(v)>>>0,Number(w)>>>0)):[],outputShape:y?Array.from((u(),C).subarray(Number(y)>>>0,Number(z)>>>0)):[],activation:R(W)})},945305:(a,b,d,c,e,g,k,l,n,p,v,w,y,z)=>{f.ac("ConvTranspose",a,{format:l?"NHWC":
 "NCHW",autoPad:b,dilations:Array.from((u(),C).subarray(Number(d)>>>0,(Number(d)>>>0)+2>>>0)),group:c,kernelShape:Array.from((u(),C).subarray(Number(e)>>>0,(Number(e)>>>0)+2>>>0)),pads:Array.from((u(),C).subarray(Number(g)>>>0,(Number(g)>>>0)+4>>>0)),strides:Array.from((u(),C).subarray(Number(k)>>>0,(Number(k)>>>0)+2>>>0)),wIsConst:()=>!!(u(),A)[n>>>0],outputPadding:p?Array.from((u(),C).subarray(Number(p)>>>0,Number(v)>>>0)):[],outputShape:w?Array.from((u(),C).subarray(Number(w)>>>0,Number(y)>>>0)):
-[],activation:R(z)})},942638:(a,b)=>{f.ac("GlobalAveragePool",a,{format:b?"NHWC":"NCHW"})},942729:(a,b,d,c,e,g,k,l,n,p,v,w,y,z)=>{f.ac("AveragePool",a,{format:z?"NHWC":"NCHW",auto_pad:b,ceil_mode:d,count_include_pad:c,storage_order:e,dilations:g?Array.from((u(),C).subarray(Number(g)>>>0,Number(k)>>>0)):[],kernel_shape:l?Array.from((u(),C).subarray(Number(l)>>>0,Number(n)>>>0)):[],pads:p?Array.from((u(),C).subarray(Number(p)>>>0,Number(v)>>>0)):[],strides:w?Array.from((u(),C).subarray(Number(w)>>>
-0,Number(y)>>>0)):[]})},943208:(a,b)=>{f.ac("GlobalAveragePool",a,{format:b?"NHWC":"NCHW"})},943299:(a,b,d,c,e,g,k,l,n,p,v,w,y,z)=>{f.ac("AveragePool",a,{format:z?"NHWC":"NCHW",auto_pad:b,ceil_mode:d,count_include_pad:c,storage_order:e,dilations:g?Array.from((u(),C).subarray(Number(g)>>>0,Number(k)>>>0)):[],kernel_shape:l?Array.from((u(),C).subarray(Number(l)>>>0,Number(n)>>>0)):[],pads:p?Array.from((u(),C).subarray(Number(p)>>>0,Number(v)>>>0)):[],strides:w?Array.from((u(),C).subarray(Number(w)>>>
-0,Number(y)>>>0)):[]})},943778:(a,b)=>{f.ac("GlobalMaxPool",a,{format:b?"NHWC":"NCHW"})},943865:(a,b,d,c,e,g,k,l,n,p,v,w,y,z)=>{f.ac("MaxPool",a,{format:z?"NHWC":"NCHW",auto_pad:b,ceil_mode:d,count_include_pad:c,storage_order:e,dilations:g?Array.from((u(),C).subarray(Number(g)>>>0,Number(k)>>>0)):[],kernel_shape:l?Array.from((u(),C).subarray(Number(l)>>>0,Number(n)>>>0)):[],pads:p?Array.from((u(),C).subarray(Number(p)>>>0,Number(v)>>>0)):[],strides:w?Array.from((u(),C).subarray(Number(w)>>>0,Number(y)>>>
-0)):[]})},944340:(a,b)=>{f.ac("GlobalMaxPool",a,{format:b?"NHWC":"NCHW"})},944427:(a,b,d,c,e,g,k,l,n,p,v,w,y,z)=>{f.ac("MaxPool",a,{format:z?"NHWC":"NCHW",auto_pad:b,ceil_mode:d,count_include_pad:c,storage_order:e,dilations:g?Array.from((u(),C).subarray(Number(g)>>>0,Number(k)>>>0)):[],kernel_shape:l?Array.from((u(),C).subarray(Number(l)>>>0,Number(n)>>>0)):[],pads:p?Array.from((u(),C).subarray(Number(p)>>>0,Number(v)>>>0)):[],strides:w?Array.from((u(),C).subarray(Number(w)>>>0,Number(y)>>>0)):[]})},
-944902:(a,b,d,c,e)=>{f.ac("Gemm",a,{alpha:b,beta:d,transA:c,transB:e})},945006:a=>{f.ac("MatMul",a,void 0)},945060:(a,b,d,c)=>{f.ac("ArgMax",a,{keepDims:!!b,selectLastIndex:!!d,axis:c})},945168:(a,b,d,c)=>{f.ac("ArgMin",a,{keepDims:!!b,selectLastIndex:!!d,axis:c})},945276:(a,b)=>{f.ac("Softmax",a,{axis:b})},945339:(a,b)=>{f.ac("Concat",a,{axis:b})},945399:(a,b,d,c,e)=>{f.ac("Split",a,{axis:b,numOutputs:d,splitSizes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},945555:a=>{f.ac("Expand",
-a,void 0)},945609:(a,b)=>{f.ac("Gather",a,{axis:Number(b)})},945680:(a,b)=>{f.ac("GatherElements",a,{axis:Number(b)})},945759:(a,b)=>{f.ac("GatherND",a,{batch_dims:Number(b)})},945838:(a,b,d,c,e,g,k,l,n,p,v)=>{f.ac("Resize",a,{antialias:b,axes:d?Array.from((u(),C).subarray(Number(d)>>>0,Number(c)>>>0)):[],coordinateTransformMode:R(e),cubicCoeffA:g,excludeOutside:k,extrapolationValue:l,keepAspectRatioPolicy:R(n),mode:R(p),nearestMode:R(v)})},946200:(a,b,d,c,e,g,k)=>{f.ac("Slice",a,{starts:b?Array.from((u(),
-C).subarray(Number(b)>>>0,Number(d)>>>0)):[],ends:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[],axes:g?Array.from((u(),C).subarray(Number(g)>>>0,Number(k)>>>0)):[]})},946464:a=>{f.ac("Tile",a,void 0)},946516:(a,b,d)=>{f.ac("InstanceNormalization",a,{epsilon:b,format:d?"NHWC":"NCHW"})},946630:(a,b,d)=>{f.ac("InstanceNormalization",a,{epsilon:b,format:d?"NHWC":"NCHW"})},946744:a=>{f.ac("Range",a,void 0)},946797:(a,b)=>{f.ac("Einsum",a,{equation:R(b)})},946878:(a,b,d,c,e)=>{f.ac("Pad",
-a,{mode:b,value:d,pads:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},947021:(a,b,d,c,e,g)=>{f.ac("BatchNormalization",a,{epsilon:b,momentum:d,spatial:!!e,trainingMode:!!c,format:g?"NHWC":"NCHW"})},947190:(a,b,d,c,e,g)=>{f.ac("BatchNormalization",a,{epsilon:b,momentum:d,spatial:!!e,trainingMode:!!c,format:g?"NHWC":"NCHW"})},947359:(a,b,d)=>{f.ac("CumSum",a,{exclusive:Number(b),reverse:Number(d)})},947456:(a,b,d)=>{f.ac("DequantizeLinear",a,{axis:b,blockSize:d})},947546:(a,b,d,c,
-e)=>{f.ac("GridSample",a,{align_corners:b,mode:R(d),padding_mode:R(c),format:e?"NHWC":"NCHW"})},947716:(a,b,d,c,e)=>{f.ac("GridSample",a,{align_corners:b,mode:R(d),padding_mode:R(c),format:e?"NHWC":"NCHW"})},947886:(a,b)=>{f.ac("ScatterND",a,{reduction:R(b)})},947971:(a,b,d,c,e,g,k,l,n)=>{f.ac("Attention",a,{numHeads:b,isUnidirectional:d,maskFilterValue:c,scale:e,doRotary:g,qkvHiddenSizes:k?Array.from((u(),C).subarray(Number(l)>>>0,Number(l)+k>>>0)):[],pastPresentShareBuffer:!!n})},948243:a=>{f.ac("BiasAdd",
-a,void 0)},948298:a=>{f.ac("BiasSplitGelu",a,void 0)},948359:a=>{f.ac("FastGelu",a,void 0)},948415:(a,b,d,c,e,g,k,l,n,p,v,w,y,z,W,kb)=>{f.ac("Conv",a,{format:w?"NHWC":"NCHW",auto_pad:b,dilations:d?Array.from((u(),C).subarray(Number(d)>>>0,Number(c)>>>0)):[],group:e,kernel_shape:g?Array.from((u(),C).subarray(Number(g)>>>0,Number(k)>>>0)):[],pads:l?Array.from((u(),C).subarray(Number(l)>>>0,Number(n)>>>0)):[],strides:p?Array.from((u(),C).subarray(Number(p)>>>0,Number(v)>>>0)):[],w_is_const:()=>!!(u(),
-A)[Number(y)>>>0],activation:R(z),activation_params:W?Array.from((u(),Oa).subarray(Number(W)>>>0,Number(kb)>>>0)):[]})},948999:a=>{f.ac("Gelu",a,void 0)},949051:(a,b,d,c,e,g,k,l,n)=>{f.ac("GroupQueryAttention",a,{numHeads:b,kvNumHeads:d,scale:c,softcap:e,doRotary:g,rotaryInterleaved:k,smoothSoftmax:l,localWindowSize:n})},949268:(a,b,d,c)=>{f.ac("LayerNormalization",a,{axis:b,epsilon:d,simplified:!!c})},949379:(a,b,d,c)=>{f.ac("LayerNormalization",a,{axis:b,epsilon:d,simplified:!!c})},949490:(a,b,
-d,c,e,g)=>{f.ac("MatMulNBits",a,{k:b,n:d,accuracyLevel:c,bits:e,blockSize:g})},949617:(a,b,d,c,e,g)=>{f.ac("MultiHeadAttention",a,{numHeads:b,isUnidirectional:d,maskFilterValue:c,scale:e,doRotary:g})},949776:(a,b)=>{f.ac("QuickGelu",a,{alpha:b})},949840:(a,b,d,c,e)=>{f.ac("RotaryEmbedding",a,{interleaved:!!b,numHeads:d,rotaryEmbeddingDim:c,scale:e})},949979:(a,b,d)=>{f.ac("SkipLayerNormalization",a,{epsilon:b,simplified:!!d})},950081:(a,b,d)=>{f.ac("SkipLayerNormalization",a,{epsilon:b,simplified:!!d})},
-950183:(a,b,d,c)=>{f.ac("GatherBlockQuantized",a,{gatherAxis:b,quantizeAxis:d,blockSize:c})},950304:a=>{f.Id(a)},950338:(a,b)=>f.Kd(Number(a),Number(b),f.$c.Nd,f.$c.errors)};function Za(a,b,d){return Cf(async()=>{await f.Gd(Number(a),Number(b),Number(d))})}function Ya(){return"undefined"!==typeof wasmOffsetConverter}
+[],activation:R(z)})},945966:(a,b)=>{f.ac("GlobalAveragePool",a,{format:b?"NHWC":"NCHW"})},946057:(a,b,d,c,e,g,k,l,n,p,v,w,y,z)=>{f.ac("AveragePool",a,{format:z?"NHWC":"NCHW",auto_pad:b,ceil_mode:d,count_include_pad:c,storage_order:e,dilations:g?Array.from((u(),C).subarray(Number(g)>>>0,Number(k)>>>0)):[],kernel_shape:l?Array.from((u(),C).subarray(Number(l)>>>0,Number(n)>>>0)):[],pads:p?Array.from((u(),C).subarray(Number(p)>>>0,Number(v)>>>0)):[],strides:w?Array.from((u(),C).subarray(Number(w)>>>
+0,Number(y)>>>0)):[]})},946536:(a,b)=>{f.ac("GlobalAveragePool",a,{format:b?"NHWC":"NCHW"})},946627:(a,b,d,c,e,g,k,l,n,p,v,w,y,z)=>{f.ac("AveragePool",a,{format:z?"NHWC":"NCHW",auto_pad:b,ceil_mode:d,count_include_pad:c,storage_order:e,dilations:g?Array.from((u(),C).subarray(Number(g)>>>0,Number(k)>>>0)):[],kernel_shape:l?Array.from((u(),C).subarray(Number(l)>>>0,Number(n)>>>0)):[],pads:p?Array.from((u(),C).subarray(Number(p)>>>0,Number(v)>>>0)):[],strides:w?Array.from((u(),C).subarray(Number(w)>>>
+0,Number(y)>>>0)):[]})},947106:(a,b)=>{f.ac("GlobalMaxPool",a,{format:b?"NHWC":"NCHW"})},947193:(a,b,d,c,e,g,k,l,n,p,v,w,y,z)=>{f.ac("MaxPool",a,{format:z?"NHWC":"NCHW",auto_pad:b,ceil_mode:d,count_include_pad:c,storage_order:e,dilations:g?Array.from((u(),C).subarray(Number(g)>>>0,Number(k)>>>0)):[],kernel_shape:l?Array.from((u(),C).subarray(Number(l)>>>0,Number(n)>>>0)):[],pads:p?Array.from((u(),C).subarray(Number(p)>>>0,Number(v)>>>0)):[],strides:w?Array.from((u(),C).subarray(Number(w)>>>0,Number(y)>>>
+0)):[]})},947668:(a,b)=>{f.ac("GlobalMaxPool",a,{format:b?"NHWC":"NCHW"})},947755:(a,b,d,c,e,g,k,l,n,p,v,w,y,z)=>{f.ac("MaxPool",a,{format:z?"NHWC":"NCHW",auto_pad:b,ceil_mode:d,count_include_pad:c,storage_order:e,dilations:g?Array.from((u(),C).subarray(Number(g)>>>0,Number(k)>>>0)):[],kernel_shape:l?Array.from((u(),C).subarray(Number(l)>>>0,Number(n)>>>0)):[],pads:p?Array.from((u(),C).subarray(Number(p)>>>0,Number(v)>>>0)):[],strides:w?Array.from((u(),C).subarray(Number(w)>>>0,Number(y)>>>0)):[]})},
+948230:(a,b,d,c,e)=>{f.ac("Gemm",a,{alpha:b,beta:d,transA:c,transB:e})},948334:a=>{f.ac("MatMul",a,void 0)},948388:(a,b,d,c)=>{f.ac("ArgMax",a,{keepDims:!!b,selectLastIndex:!!d,axis:c})},948496:(a,b,d,c)=>{f.ac("ArgMin",a,{keepDims:!!b,selectLastIndex:!!d,axis:c})},948604:(a,b)=>{f.ac("Softmax",a,{axis:b})},948667:(a,b)=>{f.ac("Concat",a,{axis:b})},948727:(a,b,d,c,e)=>{f.ac("Split",a,{axis:b,numOutputs:d,splitSizes:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},948883:a=>{f.ac("Expand",
+a,void 0)},948937:(a,b)=>{f.ac("Gather",a,{axis:Number(b)})},949008:(a,b)=>{f.ac("GatherElements",a,{axis:Number(b)})},949087:(a,b)=>{f.ac("GatherND",a,{batch_dims:Number(b)})},949166:(a,b,d,c,e,g,k,l,n,p,v)=>{f.ac("Resize",a,{antialias:b,axes:d?Array.from((u(),C).subarray(Number(d)>>>0,Number(c)>>>0)):[],coordinateTransformMode:R(e),cubicCoeffA:g,excludeOutside:k,extrapolationValue:l,keepAspectRatioPolicy:R(n),mode:R(p),nearestMode:R(v)})},949528:(a,b,d,c,e,g,k)=>{f.ac("Slice",a,{starts:b?Array.from((u(),
+C).subarray(Number(b)>>>0,Number(d)>>>0)):[],ends:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[],axes:g?Array.from((u(),C).subarray(Number(g)>>>0,Number(k)>>>0)):[]})},949792:a=>{f.ac("Tile",a,void 0)},949844:(a,b,d)=>{f.ac("InstanceNormalization",a,{epsilon:b,format:d?"NHWC":"NCHW"})},949958:(a,b,d)=>{f.ac("InstanceNormalization",a,{epsilon:b,format:d?"NHWC":"NCHW"})},950072:a=>{f.ac("Range",a,void 0)},950125:(a,b)=>{f.ac("Einsum",a,{equation:R(b)})},950206:(a,b,d,c,e)=>{f.ac("Pad",
+a,{mode:b,value:d,pads:c?Array.from((u(),C).subarray(Number(c)>>>0,Number(e)>>>0)):[]})},950349:(a,b,d,c,e,g)=>{f.ac("BatchNormalization",a,{epsilon:b,momentum:d,spatial:!!e,trainingMode:!!c,format:g?"NHWC":"NCHW"})},950518:(a,b,d,c,e,g)=>{f.ac("BatchNormalization",a,{epsilon:b,momentum:d,spatial:!!e,trainingMode:!!c,format:g?"NHWC":"NCHW"})},950687:(a,b,d)=>{f.ac("CumSum",a,{exclusive:Number(b),reverse:Number(d)})},950784:(a,b,d)=>{f.ac("DequantizeLinear",a,{axis:b,blockSize:d})},950874:(a,b,d,c,
+e)=>{f.ac("GridSample",a,{align_corners:b,mode:R(d),padding_mode:R(c),format:e?"NHWC":"NCHW"})},951044:(a,b,d,c,e)=>{f.ac("GridSample",a,{align_corners:b,mode:R(d),padding_mode:R(c),format:e?"NHWC":"NCHW"})},951214:(a,b)=>{f.ac("ScatterND",a,{reduction:R(b)})},951299:(a,b,d,c,e,g,k,l,n)=>{f.ac("Attention",a,{numHeads:b,isUnidirectional:d,maskFilterValue:c,scale:e,doRotary:g,qkvHiddenSizes:k?Array.from((u(),C).subarray(Number(l)>>>0,Number(l)+k>>>0)):[],pastPresentShareBuffer:!!n})},951571:a=>{f.ac("BiasAdd",
+a,void 0)},951626:a=>{f.ac("BiasSplitGelu",a,void 0)},951687:a=>{f.ac("FastGelu",a,void 0)},951743:(a,b,d,c,e,g,k,l,n,p,v,w,y,z,W,kb)=>{f.ac("Conv",a,{format:w?"NHWC":"NCHW",auto_pad:b,dilations:d?Array.from((u(),C).subarray(Number(d)>>>0,Number(c)>>>0)):[],group:e,kernel_shape:g?Array.from((u(),C).subarray(Number(g)>>>0,Number(k)>>>0)):[],pads:l?Array.from((u(),C).subarray(Number(l)>>>0,Number(n)>>>0)):[],strides:p?Array.from((u(),C).subarray(Number(p)>>>0,Number(v)>>>0)):[],w_is_const:()=>!!(u(),
+A)[Number(y)>>>0],activation:R(z),activation_params:W?Array.from((u(),Oa).subarray(Number(W)>>>0,Number(kb)>>>0)):[]})},952327:a=>{f.ac("Gelu",a,void 0)},952379:(a,b,d,c,e,g,k,l,n)=>{f.ac("GroupQueryAttention",a,{numHeads:b,kvNumHeads:d,scale:c,softcap:e,doRotary:g,rotaryInterleaved:k,smoothSoftmax:l,localWindowSize:n})},952596:(a,b,d,c)=>{f.ac("LayerNormalization",a,{axis:b,epsilon:d,simplified:!!c})},952707:(a,b,d,c)=>{f.ac("LayerNormalization",a,{axis:b,epsilon:d,simplified:!!c})},952818:(a,b,
+d,c,e,g)=>{f.ac("MatMulNBits",a,{k:b,n:d,accuracyLevel:c,bits:e,blockSize:g})},952945:(a,b,d,c,e,g)=>{f.ac("MultiHeadAttention",a,{numHeads:b,isUnidirectional:d,maskFilterValue:c,scale:e,doRotary:g})},953104:(a,b)=>{f.ac("QuickGelu",a,{alpha:b})},953168:(a,b,d,c,e)=>{f.ac("RotaryEmbedding",a,{interleaved:!!b,numHeads:d,rotaryEmbeddingDim:c,scale:e})},953307:(a,b,d)=>{f.ac("SkipLayerNormalization",a,{epsilon:b,simplified:!!d})},953409:(a,b,d)=>{f.ac("SkipLayerNormalization",a,{epsilon:b,simplified:!!d})},
+953511:(a,b,d,c)=>{f.ac("GatherBlockQuantized",a,{gatherAxis:b,quantizeAxis:d,blockSize:c})},953632:a=>{f.Id(a)},953666:(a,b)=>f.Kd(Number(a),Number(b),f.$c.Nd,f.$c.errors)};function Za(a,b,d){return Cf(async()=>{await f.Gd(Number(a),Number(b),Number(d))})}function Ya(){return"undefined"!==typeof wasmOffsetConverter}
 var wd,Ia,xd,I,yd,Fa,La,zd,Ad,Bd,Cd,Dd,J,Ed,Fd,K,Gd,L,Hd,Id,Jd,Kd,dynCall_vii,Ld,dynCall_v,Md,Nd,dynCall_iii,Od,Pd,Qd,Rd,dynCall_vi,Sd,Td,Ud,Vd,Wd,Xd,Yd,Zd,$d,ae,be,ce,de,ee,fe,ge,he,ie,je,ke,le,me,ne,oe,pe,qe,re,se,te,ue,ve,Xa;function Mc(a,b,d,c){var e=L();try{return Rd(a,b,d,c)}catch(g){K(e);if(g!==g+0)throw g;J(1,0)}}function Lc(a,b,d){var c=L();try{return dynCall_iii(a,b,d)}catch(e){K(c);if(e!==e+0)throw e;J(1,0)}}
 function cd(a,b,d){var c=L();try{dynCall_vii(a,b,d)}catch(e){K(c);if(e!==e+0)throw e;J(1,0)}}function Kc(a,b){var d=L();try{return Ld(a,b)}catch(c){K(d);if(c!==c+0)throw c;J(1,0)}}function ad(a){var b=L();try{dynCall_v(a)}catch(d){K(b);if(d!==d+0)throw d;J(1,0)}}function Qc(a,b,d,c,e,g,k){var l=L();try{return Pd(a,b,d,c,e,g,k)}catch(n){K(l);if(n!==n+0)throw n;J(1,0)}}function bd(a,b){var d=L();try{dynCall_vi(a,b)}catch(c){K(d);if(c!==c+0)throw c;J(1,0)}}
 function gd(a,b,d,c,e,g){var k=L();try{Md(a,b,d,c,e,g)}catch(l){K(k);if(l!==l+0)throw l;J(1,0)}}function ed(a,b,d,c){var e=L();try{Qd(a,b,d,c)}catch(g){K(e);if(g!==g+0)throw g;J(1,0)}}function fd(a,b,d,c,e){var g=L();try{Nd(a,b,d,c,e)}catch(k){K(g);if(k!==k+0)throw k;J(1,0)}}function hd(a,b,d,c,e,g,k){var l=L();try{Td(a,b,d,c,e,g,k)}catch(n){K(l);if(n!==n+0)throw n;J(1,0)}}function pd(a,b,d,c,e,g,k){var l=L();try{Ud(a,b,d,c,e,g,k)}catch(n){K(l);if(n!==n+0)throw n;J(1,0)}}