diff --git a/README.md b/README.md index 093af03f2..4e749f2ab 100644 --- a/README.md +++ b/README.md @@ -439,6 +439,7 @@ You can refine your search by selecting the task you're interested in (e.g., [te 1. **Ultravox** (from Fixie.ai) released with the repository [fixie-ai/ultravox](https://github.com/fixie-ai/ultravox) by the Fixie.ai team. 1. **[UniSpeech](https://huggingface.co/docs/transformers/model_doc/unispeech)** (from Microsoft Research) released with the paper [UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data](https://huggingface.co/papers/2101.07597) by Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang. 1. **[UniSpeechSat](https://huggingface.co/docs/transformers/model_doc/unispeech-sat)** (from Microsoft Research) released with the paper [UNISPEECH-SAT: UNIVERSAL SPEECH REPRESENTATION LEARNING WITH SPEAKER AWARE PRE-TRAINING](https://huggingface.co/papers/2110.05752) by Sanyuan Chen, Yu Wu, Chengyi Wang, Zhengyang Chen, Zhuo Chen, Shujie Liu, Jian Wu, Yao Qian, Furu Wei, Jinyu Li, Xiangzhan Yu. +1. **[VaultGemma](https://huggingface.co/docs/transformers/main/model_doc/vaultgemma)** (from Google) released with the technical report [VaultGemma: A Differentially Private Gemma Model](https://services.google.com/fh/files/blogs/vaultgemma_tech_report.pdf) by the VaultGemma Google team. 1. **[Vision Transformer (ViT)](https://huggingface.co/docs/transformers/model_doc/vit)** (from Google AI) released with the paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://huggingface.co/papers/2010.11929) by Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby. 1. **[ViTMAE](https://huggingface.co/docs/transformers/model_doc/vit_mae)** (from Meta AI) released with the paper [Masked Autoencoders Are Scalable Vision Learners](https://huggingface.co/papers/2111.06377) by Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, Ross Girshick. 1. **[ViTMatte](https://huggingface.co/docs/transformers/model_doc/vitmatte)** (from HUST-VL) released with the paper [ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers](https://huggingface.co/papers/2305.15272) by Jingfeng Yao, Xinggang Wang, Shusheng Yang, Baoyuan Wang. diff --git a/docs/snippets/6_supported-models.snippet b/docs/snippets/6_supported-models.snippet index c098ee838..0aa76c28c 100644 --- a/docs/snippets/6_supported-models.snippet +++ b/docs/snippets/6_supported-models.snippet @@ -153,6 +153,7 @@ 1. **Ultravox** (from Fixie.ai) released with the repository [fixie-ai/ultravox](https://github.com/fixie-ai/ultravox) by the Fixie.ai team. 1. **[UniSpeech](https://huggingface.co/docs/transformers/model_doc/unispeech)** (from Microsoft Research) released with the paper [UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data](https://huggingface.co/papers/2101.07597) by Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang. 1. **[UniSpeechSat](https://huggingface.co/docs/transformers/model_doc/unispeech-sat)** (from Microsoft Research) released with the paper [UNISPEECH-SAT: UNIVERSAL SPEECH REPRESENTATION LEARNING WITH SPEAKER AWARE PRE-TRAINING](https://huggingface.co/papers/2110.05752) by Sanyuan Chen, Yu Wu, Chengyi Wang, Zhengyang Chen, Zhuo Chen, Shujie Liu, Jian Wu, Yao Qian, Furu Wei, Jinyu Li, Xiangzhan Yu. +1. **[VaultGemma](https://huggingface.co/docs/transformers/main/model_doc/vaultgemma)** (from Google) released with the technical report [VaultGemma: A Differentially Private Gemma Model](https://services.google.com/fh/files/blogs/vaultgemma_tech_report.pdf) by the VaultGemma Google team. 1. **[Vision Transformer (ViT)](https://huggingface.co/docs/transformers/model_doc/vit)** (from Google AI) released with the paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://huggingface.co/papers/2010.11929) by Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby. 1. **[ViTMAE](https://huggingface.co/docs/transformers/model_doc/vit_mae)** (from Meta AI) released with the paper [Masked Autoencoders Are Scalable Vision Learners](https://huggingface.co/papers/2111.06377) by Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, Ross Girshick. 1. **[ViTMatte](https://huggingface.co/docs/transformers/model_doc/vitmatte)** (from HUST-VL) released with the paper [ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers](https://huggingface.co/papers/2305.15272) by Jingfeng Yao, Xinggang Wang, Shusheng Yang, Baoyuan Wang. diff --git a/src/configs.js b/src/configs.js index 1b6258c5b..95cedadfb 100644 --- a/src/configs.js +++ b/src/configs.js @@ -137,6 +137,7 @@ function getNormalizedConfig(config) { case 'qwen3': case 'gemma': case 'gemma2': + case 'vaultgemma': case 'gemma3_text': case 'gemma3n_text': case 'glm': diff --git a/src/models.js b/src/models.js index c13b447f3..6cdf76845 100644 --- a/src/models.js +++ b/src/models.js @@ -4711,6 +4711,12 @@ export class Gemma2Model extends Gemma2PreTrainedModel { } export class Gemma2ForCausalLM extends Gemma2PreTrainedModel { } ////////////////////////////////////////////////// +////////////////////////////////////////////////// +// VaultGemma models +export class VaultGemmaPreTrainedModel extends PreTrainedModel { } +export class VaultGemmaModel extends VaultGemmaPreTrainedModel { } +export class VaultGemmaForCausalLM extends VaultGemmaPreTrainedModel { } +////////////////////////////////////////////////// ////////////////////////////////////////////////// // Gemma3 models @@ -7853,6 +7859,7 @@ const MODEL_MAPPING_NAMES_DECODER_ONLY = new Map([ ['cohere', ['CohereModel', CohereModel]], ['gemma', ['GemmaModel', GemmaModel]], ['gemma2', ['Gemma2Model', Gemma2Model]], + ['vaultgemma', ['VaultGemmaModel', VaultGemmaModel]], ['gemma3_text', ['Gemma3Model', Gemma3Model]], ['helium', ['HeliumModel', HeliumModel]], ['glm', ['GlmModel', GlmModel]], @@ -7962,6 +7969,7 @@ const MODEL_FOR_CAUSAL_LM_MAPPING_NAMES = new Map([ ['cohere', ['CohereForCausalLM', CohereForCausalLM]], ['gemma', ['GemmaForCausalLM', GemmaForCausalLM]], ['gemma2', ['Gemma2ForCausalLM', Gemma2ForCausalLM]], + ['vaultgemma', ['VaultGemmaForCausalLM', VaultGemmaForCausalLM]], ['gemma3_text', ['Gemma3ForCausalLM', Gemma3ForCausalLM]], ['helium', ['HeliumForCausalLM', HeliumForCausalLM]], ['glm', ['GlmForCausalLM', GlmForCausalLM]],