diff --git a/README.md b/README.md index aa68c7614..093af03f2 100644 --- a/README.md +++ b/README.md @@ -359,7 +359,9 @@ You can refine your search by selecting the task you're interested in (e.g., [te 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. **[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://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/XXX) 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. **[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. +1. **[Llama4](https://huggingface.co/docs/transformers/model_doc/llama4)** (from The FAIR team of Meta AI) released with the blog post [The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation](https://ai.meta.com/blog/llama-4-multimodal-intelligence/) by the Llama Team at Meta. 1. **[LLaVa](https://huggingface.co/docs/transformers/model_doc/llava)** (from Microsoft Research & University of Wisconsin-Madison) released with the paper [Visual Instruction Tuning](https://huggingface.co/papers/2304.08485) by Haotian Liu, Chunyuan Li, Yuheng Li and Yong Jae Lee. 1. **[LLaVA-OneVision](https://huggingface.co/docs/transformers/model_doc/llava_onevision)** (from ByteDance & NTU & CUHK & HKUST) released with the paper [LLaVA-OneVision: Easy Visual Task Transfer](https://huggingface.co/papers/2408.03326) by Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Yanwei Li, Ziwei Liu, Chunyuan Li 1. **[M2M100](https://huggingface.co/docs/transformers/model_doc/m2m_100)** (from Facebook) released with the paper [Beyond English-Centric Multilingual Machine Translation](https://huggingface.co/papers/2010.11125) by Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin. diff --git a/docs/snippets/6_supported-models.snippet b/docs/snippets/6_supported-models.snippet index 99dd529b0..c098ee838 100644 --- a/docs/snippets/6_supported-models.snippet +++ b/docs/snippets/6_supported-models.snippet @@ -73,7 +73,9 @@ 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. **[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://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/XXX) 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. **[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. +1. **[Llama4](https://huggingface.co/docs/transformers/model_doc/llama4)** (from The FAIR team of Meta AI) released with the blog post [The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation](https://ai.meta.com/blog/llama-4-multimodal-intelligence/) by the Llama Team at Meta. 1. **[LLaVa](https://huggingface.co/docs/transformers/model_doc/llava)** (from Microsoft Research & University of Wisconsin-Madison) released with the paper [Visual Instruction Tuning](https://huggingface.co/papers/2304.08485) by Haotian Liu, Chunyuan Li, Yuheng Li and Yong Jae Lee. 1. **[LLaVA-OneVision](https://huggingface.co/docs/transformers/model_doc/llava_onevision)** (from ByteDance & NTU & CUHK & HKUST) released with the paper [LLaVA-OneVision: Easy Visual Task Transfer](https://huggingface.co/papers/2408.03326) by Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Yanwei Li, Ziwei Liu, Chunyuan Li 1. **[M2M100](https://huggingface.co/docs/transformers/model_doc/m2m_100)** (from Facebook) released with the paper [Beyond English-Centric Multilingual Machine Translation](https://huggingface.co/papers/2010.11125) by Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin. diff --git a/src/configs.js b/src/configs.js index e32594fe6..1b6258c5b 100644 --- a/src/configs.js +++ b/src/configs.js @@ -111,6 +111,7 @@ function getNormalizedConfig(config) { mapping['hidden_size'] = 'hidden_size'; break; case 'llama': + case 'llama4_text': case 'arcee': case 'lfm2': case 'smollm3': diff --git a/src/models.js b/src/models.js index 013969def..c13b447f3 100644 --- a/src/models.js +++ b/src/models.js @@ -4588,6 +4588,13 @@ export class LlamaModel extends LlamaPreTrainedModel { } export class LlamaForCausalLM extends LlamaPreTrainedModel { } ////////////////////////////////////////////////// + +////////////////////////////////////////////////// +export class Llama4PreTrainedModel extends PreTrainedModel { } +export class Llama4ForCausalLM extends Llama4PreTrainedModel { } +////////////////////////////////////////////////// + + ////////////////////////////////////////////////// // Arcee models export class ArceePreTrainedModel extends PreTrainedModel { } @@ -7943,6 +7950,7 @@ const MODEL_FOR_CAUSAL_LM_MAPPING_NAMES = new Map([ ['gpt_neox', ['GPTNeoXForCausalLM', GPTNeoXForCausalLM]], ['codegen', ['CodeGenForCausalLM', CodeGenForCausalLM]], ['llama', ['LlamaForCausalLM', LlamaForCausalLM]], + ['llama4_text', ['Llama4ForCausalLM', Llama4ForCausalLM]], ['arcee', ['ArceeForCausalLM', ArceeForCausalLM]], ['lfm2', ['Lfm2ForCausalLM', Lfm2ForCausalLM]], ['smollm3', ['SmolLM3ForCausalLM', SmolLM3ForCausalLM]],