Ai2

Model · Feature extraction

specter2_base

Ai2

SPECTER2 is the successor to SPECTER and is capable of generating task specific embeddings for scientific tasks when paired with adapters. This is the base model to be used along with the adapters. Given the combination of title and abstract of a scientific paper or a short texual query, the model can be used to generate effective embeddings to be used in downstream applications. Note:For general embedding purposes, please use allenai/specter2. To get the best performance on a downstream task type please load the associated adapter with the base model as in the example below. Model usage updated to be compatible with latest versions of transformers and adapters (newly released update to…

Model

longformer-base-4096

Ai2

Longformer is a transformer model for long documents. longformer-base-4096 is a BERT-like model started from the RoBERTa checkpoint and pretrained for MLM on long documents. It supports sequences of length up to 4,096. Longformer uses a combination of a sliding window (local) attention and global attention. Global attention is user-configured based on the task to allow the model to learn task-specific representations. Please refer to the examples in modelinglongformer.py and the paper for more details on how to set global attention. If you use Longformer in your research, please cite Longformer: The Long-Document Transformer. Longformer is an open-source project developed by the Allen…

Model · Text generation

OLMo-2-0425-1B

Ai2

We introduce OLMo 2 1B, the smallest model in the OLMo 2 family. OLMo 2 was pre-trained on OLMo-mix-1124 and uses Dolmino-mix-1124 for mid-training. OLMo 2 is the latest in a series of Open Language Models designed to enable the science of language models. We have released all code, checkpoints, logs, and associated training details on GitHub. The core models released in this batch include the following: OLMo 2 1B is supported in transformers v4.48 or higher: If using vLLM, you will need to install from the main branch until v0.7.4 is released. Please You can use OLMo with the standard HuggingFace transformers library: For faster performance, you can quantize the model using the following…

Model · Robotics

MolmoAct2

Ai2

MolmoAct2 is an open vision-language-action model for robot control. It builds on Molmo2-ER, an embodied-reasoning VLM backbone, and connects the autoregressive VLM to a flow-matching continuous action expert through per-layer KV (key-value) conditioning. This checkpoint is the post-trained, multi-embodiment MolmoAct2 model. It is intended as a foundation checkpoint for further robot fine-tuning rather than as a ready-to-run policy for a single deployment setting. Use this checkpoint for further fine-tuning on a target robot embodiment or benchmark. It contains the VLM and continuous action expert weights, plus normalization metadata for the post-training mixture in normstats.json. This…

Model · Robotics

MolmoAct2-Think

Ai2

MolmoAct2-Think extends MolmoAct2 with depth-token reasoning. Before producing an action, the model can predict a compact 10 x 10 discrete depth representation and condition the action expert on the resulting depth-aware VLM cache. This checkpoint is the post-trained, multi-embodiment depth-reasoning model. It is intended as a foundation checkpoint for further robot fine-tuning rather than as a ready-to-run policy for a single deployment setting. Use this checkpoint for further fine-tuning when the downstream policy should use depth reasoning. It contains the VLM, action expert, and depth-token weights, plus normalization metadata for the post-training mixture in normstats.json. This model…

Model · Robotics

MolmoAct2-Pretrain

Ai2

MolmoAct2-Pretrain adapts the Molmo2-ER vision-language backbone into a discrete autoregressive robot policy while keeping the Molmo2 token interface. Robot state is represented with discrete state tokens, and future one-second actions are represented with OpenFAST action tokens. This checkpoint is the pre-trained VLA backbone before the continuous flow-matching action expert is attached. It is intended for further post-training or fine-tuning, not direct continuous-control inference. Use this checkpoint for further MolmoAct2 training stages. It was converted with addactionexpert=false, so predictaction(...) is intentionally unavailable. Standard Transformers generation can still be used…

Model · Robotics

MolmoAct2-SO100_101

Ai2

MolmoAct2 is an open vision-language-action model for robot control. It builds on Molmo2-ER and attaches a flow-matching continuous action expert that conditions on the VLM key-value cache through a per-layer connection. This checkpoint is fine-tuned on the SO-100/101 mixture with absolute joint-pose control and annotated language instructions. It is intended for both further fine-tuning and SO-100/101 policy inference. Use this checkpoint for SO-100/101 inference or for further fine-tuning. Dataset normalization metadata is stored in normstats.json. pass normtag="so100so101molmoact2" at inference time. Continuous action prediction is the intended and recommended inference mode. Discrete…

Model · Robotics

MolmoAct2-LIBERO

Ai2

MolmoAct2 is an open vision-language-action model for robot control. It builds on Molmo2-ER and attaches a flow-matching continuous action expert that conditions on the VLM key-value cache through a per-layer connection. This checkpoint is fine-tuned on the full LIBERO training mixture, combining Spatial, Object, Goal, and Long suites. It is intended for both further fine-tuning and LIBERO policy inference. Use this checkpoint for LIBERO inference or for further fine-tuning. Dataset normalization metadata is stored in normstats.json. pass normtag="libero" at inference time. Continuous action prediction is the intended and recommended inference mode. Discrete action prediction is exposed for…

Model · Robotics

GraspMolmo

Ai2

[[Paper]](https://arxiv.org/pdf/2505.13441) [[arXiv]](https://arxiv.org/abs/2505.13441) [[Project Website]](https://abhaybd.github.io/GraspMolmo/) [[Data]](https://huggingface.co/datasets/allenai/PRISM) GraspMolmo is a generalizable open-vocabulary task-oriented grasping (TOG) model for robotic manipulation. Given an image and a task to complete (e.g. "Pour me some tea"), GraspMolmo will point to the most appropriate grasp location, which can then be matched to the closest stable grasp. Running the above code could result in the following output: To predict a grasp point and match it to one of the candidate grasps, refer to the GraspMolmo class. First, install graspmolmo with and then…

Model · Robotics

MolmoAct2-BimanualYAM

Ai2

MolmoAct2 is an open vision-language-action model for robot control. It builds on Molmo2-ER and attaches a flow-matching continuous action expert that conditions on the VLM key-value cache through a per-layer connection. This checkpoint is fine-tuned on the bimanual YAM mixture with absolute joint-pose control and annotated language instructions. It is intended for both further fine-tuning and bimanual YAM policy inference. Use this checkpoint for bimanual YAM inference or for further fine-tuning. Dataset normalization metadata is stored in normstats.json. pass normtag="yamdualmolmoact2" at inference time. Continuous action prediction is the intended and recommended inference mode. Discrete…

Dataset · Text generation

c4

Ai2

A colossal, cleaned version of Common Crawl's web crawl corpus. Based on Common Crawl dataset: "https://commoncrawl.org". This is the processed version of Google's C4 dataset We prepared five variants of the data: en, en.noclean, en.noblocklist, realnewslike, and multilingual (mC4). For reference, these are the sizes of the variants: - en.noclean: 2.3TB - en.noblocklist: 380GB - realnewslike: 15GB - multilingual (mC4): 9.7TB (108 subsets, one per language) The en.noblocklist variant is exactly the same as the en variant, except we turned off the so-called "badwords filter", which removes all documents that contain words from the lists at…

Dataset · Question answering

ai2_arc

Ai2

A new dataset of 7,787 genuine grade-school level, multiple-choice science questions, assembled to encourage research in advanced question-answering. The dataset is partitioned into a Challenge Set and an Easy Set, where the former contains only questions answered incorrectly by both a retrieval-based algorithm and a word co-occurrence algorithm. We are also including a corpus of over 14 million science sentences relevant to the task, and an implementation of three neural baseline models for this dataset. We pose ARC as a challenge to the community. An example of 'train' looks as follows. An example of 'train' looks as follows. The data fields are the same among all splits. - id: a string…

Dataset

objaverse

Ai2

Objaverse is a Massive Dataset with 800K+ Annotated 3D Objects. In the meantime, please see our paper and website for additional details. The use of the dataset as a whole is licensed under the ODC-By v1.0 license. Individual objects in Objaverse are all licensed as creative commons distributable objects, and may be under the following licenses: - CC-BY 4.0 - 721K objects - CC-BY-NC 4.0 - 25K objects - CC-BY-NC-SA 4.0 - 52K objects - CC-BY-SA 4.0 - 16K objects - CC0 1.0 - 3.5K objects The metadata will provide the license for each object. To cite Objaverse, please use the following BibTeX entry

Dataset · Question answering

openbookqa

Ai2

OpenBookQA aims to promote research in advanced question-answering, probing a deeper understanding of both the topic (with salient facts summarized as an open book, also provided with the dataset) and the language it is expressed in. In particular, it contains questions that require multi-step reasoning, use of additional common and commonsense knowledge, and rich text comprehension. OpenBookQA is a new kind of question-answering dataset modeled after open book exams for assessing human understanding of a subject. An example of 'train' looks as follows: An example of 'train' looks as follows: The data fields are the same among all splits. - id: a string feature. - questionstem: a string…

Dataset

winogrande

Ai2

WinoGrande is a new collection of 44k problems, inspired by Winograd Schema Challenge (Levesque, Davis, and Morgenstern 2011), but adjusted to improve the scale and robustness against the dataset-specific bias. Formulated as a fill-in-a-blank task with binary options, the goal is to choose the right option for a given sentence which requires commonsense reasoning. An example of 'train' looks as follows. An example of 'validation' looks as follows. An example of 'validation' looks as follows. An example of 'validation' looks as follows. An example of 'train' looks as follows. The data fields are the same among all splits. - sentence: a string feature. - option1: a string feature. - option2…

Dataset · Question answering

sciq

Ai2

The SciQ dataset contains 13,679 crowdsourced science exam questions about Physics, Chemistry and Biology, among others. The questions are in multiple-choice format with 4 answer options each. For the majority of the questions, an additional paragraph with supporting evidence for the correct answer is provided. An example of 'train' looks as follows. The data fields are the same among all splits. - question: a string feature. - distractor3: a string feature. - distractor1: a string feature. - distractor2: a string feature. - correctanswer: a string feature. - support: a string feature. The dataset is licensed under the Creative Commons Attribution-NonCommercial 3.0 Unported License. Thanks…

Dataset · Text classification

swag

Ai2

Given a partial description like "she opened the hood of the car," humans can reason about the situation and anticipate what might come next ("then, she examined the engine"). SWAG (Situations With Adversarial Generations) is a large-scale dataset for this task of grounded commonsense inference, unifying natural language inference and physically grounded reasoning. The dataset consists of 113k multiple choice questions about grounded situations (73k training, 20k validation, 20k test). Each question is a video caption from LSMDC or ActivityNet Captions, with four answer choices about what might happen next in the scene. The correct answer is the (real) video caption for the next event in…

Dataset · Question answering

quartz

Ai2

QuaRTz is a crowdsourced dataset of 3864 multiple-choice questions about open domain qualitative relationships. Each question is paired with one of 405 different background sentences (sometimes short paragraphs). The QuaRTz dataset V1 contains 3864 questions about open domain qualitative relationships. Each question is paired with one of 405 different background sentences (sometimes short paragraphs). The dataset is split into train (2696), dev (384) and test (784). A background sentence will only appear in a single split. An example of 'train' looks as follows. The data fields are the same among all splits. - id: a string feature. - question: a string feature. - choices: a dictionary…

Dataset · Question answering

qasc

Ai2

QASC is a question-answering dataset with a focus on sentence composition. It consists of 9,980 8-way multiple-choice questions about grade school science (8,134 train, 926 dev, 920 test), and comes with a corpus of 17M sentences. An example of 'validation' looks as follows. The data fields are the same among all splits. - id: a string feature. - question: a string feature. - choices: a dictionary feature containing: - text: a string feature. - label: a string feature. - answerKey: a string feature. - fact1: a string feature. - fact2: a string feature. - combinedfact: a string feature. - formattedquestion: a string feature. The dataset is released under CC BY 4.0 license. Thanks to…

Dataset

scitail

Ai2

The SciTail dataset is an entailment dataset created from multiple-choice science exams and web sentences. Each question and the correct answer choice are converted into an assertive statement to form the hypothesis. We use information retrieval to obtain relevant text from a large text corpus of web sentences, and use these sentences as a premise P. We crowdsource the annotation of such premise-hypothesis pair as supports (entails) or not (neutral), in order to create the SciTail dataset. The dataset contains 27,026 examples with 10,101 examples with entails label and 16,925 examples with neutral label An example of 'train' looks as follows. An example of 'validation' looks as follows. An…