Merge branch 'main' into patch-1

README.md

@@ -352,6 +352,7 @@ You can refine your search by selecting the task you're interested in (e.g., [te
 1. **[MMS](https://huggingface.co/docs/transformers/model_doc/mms)** (from Facebook) released with the paper [Scaling Speech Technology to 1,000+ Languages](https://arxiv.org/abs/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://arxiv.org/abs/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://arxiv.org/abs/2311.17049) by Pavan Kumar Anasosalu Vasu, Hadi Pouransari, Fartash Faghri, Raviteja Vemulapalli, Oncel Tuzel.
+1. **MobileLLM** (from Meta) released with the paper [MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases](https://arxiv.org/abs/2402.14905) by Zechun Liu, Changsheng Zhao, Forrest Iandola, Chen Lai, Yuandong Tian, Igor Fedorov, Yunyang Xiong, Ernie Chang, Yangyang Shi, Raghuraman Krishnamoorthi, Liangzhen Lai, Vikas Chandra.
 1. **[MobileNetV1](https://huggingface.co/docs/transformers/model_doc/mobilenet_v1)** (from Google Inc.) released with the paper [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://arxiv.org/abs/1704.04861) by Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam.
 1. **[MobileNetV2](https://huggingface.co/docs/transformers/model_doc/mobilenet_v2)** (from Google Inc.) released with the paper [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://arxiv.org/abs/1801.04381) by Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen.
 1. **MobileNetV3** (from Google Inc.) released with the paper [Searching for MobileNetV3](https://arxiv.org/abs/1905.02244) by Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan, Quoc V. Le, Hartwig Adam.

docs/snippets/6_supported-models.snippet

@@ -67,6 +67,7 @@
 1. **[MMS](https://huggingface.co/docs/transformers/model_doc/mms)** (from Facebook) released with the paper [Scaling Speech Technology to 1,000+ Languages](https://arxiv.org/abs/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://arxiv.org/abs/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://arxiv.org/abs/2311.17049) by Pavan Kumar Anasosalu Vasu, Hadi Pouransari, Fartash Faghri, Raviteja Vemulapalli, Oncel Tuzel.
+1. **MobileLLM** (from Meta) released with the paper [MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases](https://arxiv.org/abs/2402.14905) by Zechun Liu, Changsheng Zhao, Forrest Iandola, Chen Lai, Yuandong Tian, Igor Fedorov, Yunyang Xiong, Ernie Chang, Yangyang Shi, Raghuraman Krishnamoorthi, Liangzhen Lai, Vikas Chandra.
 1. **[MobileNetV1](https://huggingface.co/docs/transformers/model_doc/mobilenet_v1)** (from Google Inc.) released with the paper [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://arxiv.org/abs/1704.04861) by Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam.
 1. **[MobileNetV2](https://huggingface.co/docs/transformers/model_doc/mobilenet_v2)** (from Google Inc.) released with the paper [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://arxiv.org/abs/1801.04381) by Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen.
 1. **MobileNetV3** (from Google Inc.) released with the paper [Searching for MobileNetV3](https://arxiv.org/abs/1905.02244) by Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan, Quoc V. Le, Hartwig Adam.

scripts/convert.py

@@ -40,6 +40,7 @@
     'stablelm',
     'starcoder2',
     'openelm',
+    'mobilellm',
 
     # Encoder-decoder models
     'whisper',

src/configs.js

@@ -91,6 +91,7 @@ function getNormalizedConfig(config) {
             mapping['hidden_size'] = 'hidden_size';
             break;
         case 'llama':
+        case 'mobilellm':
         case 'granite':
         case 'cohere':
         case 'mistral':

src/models.js

@@ -3810,6 +3810,14 @@ export class LlamaForCausalLM extends LlamaPreTrainedModel { }
 //////////////////////////////////////////////////
 
 
+//////////////////////////////////////////////////
+// MobileLLM models
+export class MobileLLMPreTrainedModel extends PreTrainedModel { }
+export class MobileLLMModel extends MobileLLMPreTrainedModel { }
+export class MobileLLMForCausalLM extends MobileLLMPreTrainedModel { }
+//////////////////////////////////////////////////
+
+
 //////////////////////////////////////////////////
 // Granite models
 export class GranitePreTrainedModel extends PreTrainedModel { }
@@ -6125,6 +6133,7 @@ const MODEL_MAPPING_NAMES_DECODER_ONLY = new Map([
     ['gpt_neox', ['GPTNeoXModel', GPTNeoXModel]],
     ['codegen', ['CodeGenModel', CodeGenModel]],
     ['llama', ['LlamaModel', LlamaModel]],
+    ['mobilellm', ['MobileLLMModel', MobileLLMModel]],
     ['granite', ['GraniteModel', GraniteModel]],
     ['cohere', ['CohereModel', CohereModel]],
     ['gemma', ['GemmaModel', GemmaModel]],
@@ -6214,6 +6223,7 @@ const MODEL_FOR_CAUSAL_LM_MAPPING_NAMES = new Map([
     ['gpt_neox', ['GPTNeoXForCausalLM', GPTNeoXForCausalLM]],
     ['codegen', ['CodeGenForCausalLM', CodeGenForCausalLM]],
     ['llama', ['LlamaForCausalLM', LlamaForCausalLM]],
+    ['mobilellm', ['MobileLLMForCausalLM', MobileLLMForCausalLM]],
     ['granite', ['GraniteForCausalLM', GraniteForCausalLM]],
     ['cohere', ['CohereForCausalLM', CohereForCausalLM]],
     ['gemma', ['GemmaForCausalLM', GemmaForCausalLM]],