diff --git a/README.md b/README.md index 7185dbfe8..9df7970c3 100644 --- a/README.md +++ b/README.md @@ -365,6 +365,7 @@ You can refine your search by selecting the task you're interested in (e.g., [te 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://arxiv.org/abs/2010.11934) by Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, Colin Raffel. 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://arxiv.org/abs/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://arxiv.org/abs/2308.13418) by Lukas Blecher, Guillem Cucurull, Thomas Scialom, Robert Stojnic. +1. **[OLMo](https://huggingface.co/docs/transformers/master/model_doc/olmo)** (from AI2) released with the paper [OLMo: Accelerating the Science of Language Models](https://arxiv.org/abs/2402.00838) by Dirk Groeneveld, Iz Beltagy, Pete Walsh, Akshita Bhagia, Rodney Kinney, Oyvind Tafjord, Ananya Harsh Jha, Hamish Ivison, Ian Magnusson, Yizhong Wang, Shane Arora, David Atkinson, Russell Authur, Khyathi Raghavi Chandu, Arman Cohan, Jennifer Dumas, Yanai Elazar, Yuling Gu, Jack Hessel, Tushar Khot, William Merrill, Jacob Morrison, Niklas Muennighoff, Aakanksha Naik, Crystal Nam, Matthew E. Peters, Valentina Pyatkin, Abhilasha Ravichander, Dustin Schwenk, Saurabh Shah, Will Smith, Emma Strubell, Nishant Subramani, Mitchell Wortsman, Pradeep Dasigi, Nathan Lambert, Kyle Richardson, Luke Zettlemoyer, Jesse Dodge, Kyle Lo, Luca Soldaini, Noah A. Smith, Hannaneh Hajishirzi. 1. **OpenELM** (from Apple) released with the paper [OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework](https://arxiv.org/abs/2404.14619) by Sachin Mehta, Mohammad Hossein Sekhavat, Qingqing Cao, Maxwell Horton, Yanzi Jin, Chenfan Sun, Iman Mirzadeh, Mahyar Najibi, Dmitry Belenko, Peter Zatloukal, Mohammad Rastegari. 1. **[OPT](https://huggingface.co/docs/transformers/master/model_doc/opt)** (from Meta AI) released with the paper [OPT: Open Pre-trained Transformer Language Models](https://arxiv.org/abs/2205.01068) by Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen et al. 1. **[OWL-ViT](https://huggingface.co/docs/transformers/model_doc/owlvit)** (from Google AI) released with the paper [Simple Open-Vocabulary Object Detection with Vision Transformers](https://arxiv.org/abs/2205.06230) by Matthias Minderer, Alexey Gritsenko, Austin Stone, Maxim Neumann, Dirk Weissenborn, Alexey Dosovitskiy, Aravindh Mahendran, Anurag Arnab, Mostafa Dehghani, Zhuoran Shen, Xiao Wang, Xiaohua Zhai, Thomas Kipf, and Neil Houlsby. diff --git a/docs/snippets/6_supported-models.snippet b/docs/snippets/6_supported-models.snippet index 8e97152c7..d94bd0221 100644 --- a/docs/snippets/6_supported-models.snippet +++ b/docs/snippets/6_supported-models.snippet @@ -80,6 +80,7 @@ 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://arxiv.org/abs/2010.11934) by Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, Colin Raffel. 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://arxiv.org/abs/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://arxiv.org/abs/2308.13418) by Lukas Blecher, Guillem Cucurull, Thomas Scialom, Robert Stojnic. +1. **[OLMo](https://huggingface.co/docs/transformers/master/model_doc/olmo)** (from AI2) released with the paper [OLMo: Accelerating the Science of Language Models](https://arxiv.org/abs/2402.00838) by Dirk Groeneveld, Iz Beltagy, Pete Walsh, Akshita Bhagia, Rodney Kinney, Oyvind Tafjord, Ananya Harsh Jha, Hamish Ivison, Ian Magnusson, Yizhong Wang, Shane Arora, David Atkinson, Russell Authur, Khyathi Raghavi Chandu, Arman Cohan, Jennifer Dumas, Yanai Elazar, Yuling Gu, Jack Hessel, Tushar Khot, William Merrill, Jacob Morrison, Niklas Muennighoff, Aakanksha Naik, Crystal Nam, Matthew E. Peters, Valentina Pyatkin, Abhilasha Ravichander, Dustin Schwenk, Saurabh Shah, Will Smith, Emma Strubell, Nishant Subramani, Mitchell Wortsman, Pradeep Dasigi, Nathan Lambert, Kyle Richardson, Luke Zettlemoyer, Jesse Dodge, Kyle Lo, Luca Soldaini, Noah A. Smith, Hannaneh Hajishirzi. 1. **OpenELM** (from Apple) released with the paper [OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework](https://arxiv.org/abs/2404.14619) by Sachin Mehta, Mohammad Hossein Sekhavat, Qingqing Cao, Maxwell Horton, Yanzi Jin, Chenfan Sun, Iman Mirzadeh, Mahyar Najibi, Dmitry Belenko, Peter Zatloukal, Mohammad Rastegari. 1. **[OPT](https://huggingface.co/docs/transformers/master/model_doc/opt)** (from Meta AI) released with the paper [OPT: Open Pre-trained Transformer Language Models](https://arxiv.org/abs/2205.01068) by Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen et al. 1. **[OWL-ViT](https://huggingface.co/docs/transformers/model_doc/owlvit)** (from Google AI) released with the paper [Simple Open-Vocabulary Object Detection with Vision Transformers](https://arxiv.org/abs/2205.06230) by Matthias Minderer, Alexey Gritsenko, Austin Stone, Maxim Neumann, Dirk Weissenborn, Alexey Dosovitskiy, Aravindh Mahendran, Anurag Arnab, Mostafa Dehghani, Zhuoran Shen, Xiao Wang, Xiaohua Zhai, Thomas Kipf, and Neil Houlsby. diff --git a/scripts/convert.py b/scripts/convert.py index 5b3f3f5cf..ee4f413dd 100644 --- a/scripts/convert.py +++ b/scripts/convert.py @@ -41,6 +41,7 @@ 'starcoder2', 'openelm', 'mobilellm', + 'olmo', # Encoder-decoder models 'whisper', diff --git a/src/configs.js b/src/configs.js index 1a15af4c1..6329cc137 100644 --- a/src/configs.js +++ b/src/configs.js @@ -91,6 +91,7 @@ function getNormalizedConfig(config) { mapping['hidden_size'] = 'hidden_size'; break; case 'llama': + case 'olmo': case 'mobilellm': case 'granite': case 'cohere': diff --git a/src/models.js b/src/models.js index eca48dbd0..031b85f01 100644 --- a/src/models.js +++ b/src/models.js @@ -3818,6 +3818,14 @@ export class MobileLLMForCausalLM extends MobileLLMPreTrainedModel { } ////////////////////////////////////////////////// +////////////////////////////////////////////////// +// OLMo models +export class OlmoPreTrainedModel extends PreTrainedModel { } +export class OlmoModel extends OlmoPreTrainedModel { } +export class OlmoForCausalLM extends OlmoPreTrainedModel { } +////////////////////////////////////////////////// + + ////////////////////////////////////////////////// // Granite models export class GranitePreTrainedModel extends PreTrainedModel { } @@ -6133,6 +6141,7 @@ const MODEL_MAPPING_NAMES_DECODER_ONLY = new Map([ ['gpt_neox', ['GPTNeoXModel', GPTNeoXModel]], ['codegen', ['CodeGenModel', CodeGenModel]], ['llama', ['LlamaModel', LlamaModel]], + ['olmo', ['OlmoModel', OlmoModel]], ['mobilellm', ['MobileLLMModel', MobileLLMModel]], ['granite', ['GraniteModel', GraniteModel]], ['cohere', ['CohereModel', CohereModel]], @@ -6223,6 +6232,7 @@ const MODEL_FOR_CAUSAL_LM_MAPPING_NAMES = new Map([ ['gpt_neox', ['GPTNeoXForCausalLM', GPTNeoXForCausalLM]], ['codegen', ['CodeGenForCausalLM', CodeGenForCausalLM]], ['llama', ['LlamaForCausalLM', LlamaForCausalLM]], + ['olmo', ['OlmoForCausalLM', OlmoForCausalLM]], ['mobilellm', ['MobileLLMForCausalLM', MobileLLMForCausalLM]], ['granite', ['GraniteForCausalLM', GraniteForCausalLM]], ['cohere', ['CohereForCausalLM', CohereForCausalLM]], diff --git a/tests/tiny_random.test.js b/tests/tiny_random.test.js index 634924f32..33413ecfd 100644 --- a/tests/tiny_random.test.js +++ b/tests/tiny_random.test.js @@ -23,6 +23,7 @@ import { // Models LlamaForCausalLM, + OlmoForCausalLM, GraniteForCausalLM, CohereModel, CohereForCausalLM, @@ -1033,6 +1034,57 @@ describe("Tiny random models", () => { }); }); + describe("olmo", () => { + describe("OlmoForCausalLM", () => { + const model_id = "onnx-community/tiny-random-olmo-hf"; + /** @type {OlmoForCausalLM} */ + let model; + /** @type {GPTNeoXTokenizer} */ + let tokenizer; + beforeAll(async () => { + model = await OlmoForCausalLM.from_pretrained(model_id, { + // TODO move to config + ...DEFAULT_MODEL_OPTIONS, + }); + tokenizer = await GPTNeoXTokenizer.from_pretrained(model_id); + tokenizer.padding_side = "left"; + }, MAX_MODEL_LOAD_TIME); + + it( + "batch_size=1", + async () => { + const inputs = tokenizer("hello"); + const outputs = await model.generate({ + ...inputs, + max_length: 10, + }); + expect(outputs.tolist()).toEqual([[25521n, 10886n, 44936n, 38777n, 33038n, 18557n, 1810n, 33853n, 9517n, 28892n]]); + }, + MAX_TEST_EXECUTION_TIME, + ); + + it( + "batch_size>1", + async () => { + const inputs = tokenizer(["hello", "hello world"], { padding: true }); + const outputs = await model.generate({ + ...inputs, + max_length: 10, + }); + expect(outputs.tolist()).toEqual([ + [1n, 25521n, 10886n, 44936n, 38777n, 33038n, 18557n, 1810n, 33853n, 9517n], + [25521n, 1533n, 37199n, 27362n, 30594n, 39261n, 8824n, 19175n, 8545n, 29335n], + ]); + }, + MAX_TEST_EXECUTION_TIME, + ); + + afterAll(async () => { + await model?.dispose(); + }, MAX_MODEL_DISPOSE_TIME); + }); + }); + describe("granite", () => { describe("GraniteForCausalLM", () => { const model_id = "hf-internal-testing/tiny-random-GraniteForCausalLM";