Faster Text Generation with Self-Speculative Decoding
•
59
AI & ML interests
None defined yet.
Recent Activity
Articles
A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann
-
facebook/vjepa2-vitl-fpc64-256
Video Classification • 0.3B • Updated • 21.5k • 131 -
facebook/vjepa2-vith-fpc64-256
Video Classification • 0.7B • Updated • 1.06k • 12 -
facebook/vjepa2-vitg-fpc64-256
Video Classification • 1B • Updated • 10.9k • 14 -
facebook/vjepa2-vitg-fpc64-384
Video Classification • 1B • Updated • 6.88k • 26
-
facebook/PE-Core-L14-336
Zero-Shot Image Classification • Updated • 22.5k • 36 -
facebook/PE-Core-G14-448
Zero-Shot Image Classification • Updated • 19.1k • 14 -
facebook/PE-Lang-L14-448
Image Feature Extraction • Updated • 1.28k • 6 -
facebook/PE-Lang-G14-448
Image Feature Extraction • Updated • 1.81k • 13
A collection of small (sub-1B) multilingual dense retrievers that generalize well across a number of tasks and languages.
Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905
-
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
Paper • 2402.14905 • Published • 132 -
facebook/MobileLLM-125M
Text Generation • Updated • 1.09k • 120 -
facebook/MobileLLM-350M
Text Generation • Updated • 509 • 35 -
facebook/MobileLLM-600M
Text Generation • Updated • 416 • 29
Models continually pretrained using LayerSkip - https://arxiv.org/abs/2404.16710
-
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Paper • 2404.16710 • Published • 80 -
facebook/layerskip-llama2-7B
Text Generation • 7B • Updated • 1.46k • 14 -
facebook/layerskip-llama2-13B
Text Generation • 13B • Updated • 145 • 5 -
facebook/layerskip-llama2-70B
Text Generation • 69B • Updated • 151 • 4
A significant step towards removing language barriers through expressive, fast and high-quality AI translation.
A collection for the first release of Wav2Vec 2.0, a speech encoder that learns powerful representations from unlabelled audio data.
-
facebook/wav2vec2-large-960h-lv60-self
Automatic Speech Recognition • Updated • 62.9k • 148 -
facebook/wav2vec2-large-960h
Automatic Speech Recognition • Updated • 105k • 31 -
facebook/wav2vec2-base-960h
Automatic Speech Recognition • 0.1B • Updated • 1.16M • 351 -
facebook/wav2vec2-base-100h
Automatic Speech Recognition • Updated • 1.25k • 6
A collection of multilingual Wav2Vec 2.0 checkpoints pre-trained on 53 languages and fine-tuned for CTC speech recognition.
-
facebook/wav2vec2-large-xlsr-53
Updated • 738k • 141 -
facebook/wav2vec2-xlsr-53-espeak-cv-ft
Automatic Speech Recognition • Updated • 201k • 33 -
facebook/wav2vec2-large-xlsr-53-dutch
Automatic Speech Recognition • Updated • 496 • 2 -
facebook/wav2vec2-large-xlsr-53-french
Automatic Speech Recognition • Updated • 30.4k • 13
A collection of "robust" Wav2Vec 2.0 checkpoints pre-trained on datasets from multiple domains.
-
facebook/wav2vec2-large-robust
Updated • 76.3k • 35 -
facebook/wav2vec2-large-robust-ft-libri-960h
Automatic Speech Recognition • 0.3B • Updated • 244k • 15 -
facebook/wav2vec2-large-robust-ft-swbd-300h
Automatic Speech Recognition • Updated • 6.13k • 20 -
Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training
Paper • 2104.01027 • Published • 1
A collection of checkpoints from the second VoxPopuli release.
-
VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation
Paper • 2101.00390 • Published • 1 -
facebook/wav2vec2-base-bg-voxpopuli-v2
Automatic Speech Recognition • Updated • 33 -
facebook/wav2vec2-base-cs-voxpopuli-v2
Automatic Speech Recognition • Updated • 22 • 1 -
facebook/wav2vec2-base-da-voxpopuli-v2
Automatic Speech Recognition • Updated • 25
Text-to-speech models from fairseq s^2
A collection of stereo music generation models as part of the v2 MusicGen release.
Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
OPT (Open Pretrained Transformer) is a series of open-sourced large causal language models which perform similar in performance to GPT3.
-
facebook/webssl-dino300m-full2b-224
Image Feature Extraction • 0.3B • Updated • 1.85k • 9 -
facebook/webssl-dino1b-full2b-224
Image Feature Extraction • 1B • Updated • 1.12k • 1 -
facebook/webssl-dino2b-full2b-224
Image Feature Extraction • 2B • Updated • 98 -
facebook/webssl-dino3b-full2b-224
Image Feature Extraction • 3B • Updated • 362
A first-of-its-kind behavioral foundation model to control a virtual physics-based humanoid agent for a wide range of whole-body tasks.
Models and datasets for Sparsh: Self-supervised touch representations for vision-based tactile sensing
MelodyFlow: High Fidelity Text-Guided Music Generation and Editing via Single-Stage Flow Matching
Masked Audio Generation using a Single Non-Autoregressive Transformer
SeamlessM4T is designed to provide high quality translation, allowing people from different linguistic communities to communicate effortlessly.
First release checkpoints for XLS-R, a large-scale model for cross-lingual speech representation learning based on wav2vec 2.0.
A collection of open-source artefacts (datasets + checkpoints) from the first VoxPopuli release.
-
facebook/voxpopuli
Updated • 8.63k • 123 -
VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation
Paper • 2101.00390 • Published • 1 -
facebook/wav2vec2-base-100k-voxpopuli
Automatic Speech Recognition • Updated • 8.41k • 4 -
facebook/wav2vec2-base-10k-voxpopuli-ft-cs
Automatic Speech Recognition • Updated • 22
A collection of checkpoints from the HuBERT release, a speech encoder that learns powerful representations from unlabelled audio data.
-
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
Paper • 2106.07447 • Published • 3 -
facebook/hubert-base-ls960
Feature Extraction • Updated • 282k • • 57 -
facebook/hubert-large-ll60k
Feature Extraction • Updated • 52.6k • 30 -
facebook/hubert-large-ls960-ft
Automatic Speech Recognition • Updated • 880k • 68
-
facebook/dinov2-small
Image Feature Extraction • 0.0B • Updated • 1.3M • 41 -
facebook/dinov2-base
Image Feature Extraction • 0.1B • Updated • 2.02M • 137 -
facebook/dinov2-large
Image Feature Extraction • 0.3B • Updated • 990k • 84 -
facebook/dinov2-giant
Image Feature Extraction • 1B • Updated • 107k • 46
Meta LLM Compiler is a state-of-the-art LLM that builds upon Code Llama with improved performance for code optimization and compiler reasoning.
Foundation models for human tasks. Code: https://github.com/facebookresearch/sapiens
A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann
-
facebook/vjepa2-vitl-fpc64-256
Video Classification • 0.3B • Updated • 21.5k • 131 -
facebook/vjepa2-vith-fpc64-256
Video Classification • 0.7B • Updated • 1.06k • 12 -
facebook/vjepa2-vitg-fpc64-256
Video Classification • 1B • Updated • 10.9k • 14 -
facebook/vjepa2-vitg-fpc64-384
Video Classification • 1B • Updated • 6.88k • 26
-
facebook/webssl-dino300m-full2b-224
Image Feature Extraction • 0.3B • Updated • 1.85k • 9 -
facebook/webssl-dino1b-full2b-224
Image Feature Extraction • 1B • Updated • 1.12k • 1 -
facebook/webssl-dino2b-full2b-224
Image Feature Extraction • 2B • Updated • 98 -
facebook/webssl-dino3b-full2b-224
Image Feature Extraction • 3B • Updated • 362
-
facebook/PE-Core-L14-336
Zero-Shot Image Classification • Updated • 22.5k • 36 -
facebook/PE-Core-G14-448
Zero-Shot Image Classification • Updated • 19.1k • 14 -
facebook/PE-Lang-L14-448
Image Feature Extraction • Updated • 1.28k • 6 -
facebook/PE-Lang-G14-448
Image Feature Extraction • Updated • 1.81k • 13
A collection of small (sub-1B) multilingual dense retrievers that generalize well across a number of tasks and languages.
A first-of-its-kind behavioral foundation model to control a virtual physics-based humanoid agent for a wide range of whole-body tasks.
Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905
-
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
Paper • 2402.14905 • Published • 132 -
facebook/MobileLLM-125M
Text Generation • Updated • 1.09k • 120 -
facebook/MobileLLM-350M
Text Generation • Updated • 509 • 35 -
facebook/MobileLLM-600M
Text Generation • Updated • 416 • 29
Models and datasets for Sparsh: Self-supervised touch representations for vision-based tactile sensing
Models continually pretrained using LayerSkip - https://arxiv.org/abs/2404.16710
-
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Paper • 2404.16710 • Published • 80 -
facebook/layerskip-llama2-7B
Text Generation • 7B • Updated • 1.46k • 14 -
facebook/layerskip-llama2-13B
Text Generation • 13B • Updated • 145 • 5 -
facebook/layerskip-llama2-70B
Text Generation • 69B • Updated • 151 • 4
MelodyFlow: High Fidelity Text-Guided Music Generation and Editing via Single-Stage Flow Matching
A significant step towards removing language barriers through expressive, fast and high-quality AI translation.
Masked Audio Generation using a Single Non-Autoregressive Transformer
A collection for the first release of Wav2Vec 2.0, a speech encoder that learns powerful representations from unlabelled audio data.
-
facebook/wav2vec2-large-960h-lv60-self
Automatic Speech Recognition • Updated • 62.9k • 148 -
facebook/wav2vec2-large-960h
Automatic Speech Recognition • Updated • 105k • 31 -
facebook/wav2vec2-base-960h
Automatic Speech Recognition • 0.1B • Updated • 1.16M • 351 -
facebook/wav2vec2-base-100h
Automatic Speech Recognition • Updated • 1.25k • 6
SeamlessM4T is designed to provide high quality translation, allowing people from different linguistic communities to communicate effortlessly.
A collection of multilingual Wav2Vec 2.0 checkpoints pre-trained on 53 languages and fine-tuned for CTC speech recognition.
-
facebook/wav2vec2-large-xlsr-53
Updated • 738k • 141 -
facebook/wav2vec2-xlsr-53-espeak-cv-ft
Automatic Speech Recognition • Updated • 201k • 33 -
facebook/wav2vec2-large-xlsr-53-dutch
Automatic Speech Recognition • Updated • 496 • 2 -
facebook/wav2vec2-large-xlsr-53-french
Automatic Speech Recognition • Updated • 30.4k • 13
First release checkpoints for XLS-R, a large-scale model for cross-lingual speech representation learning based on wav2vec 2.0.
A collection of "robust" Wav2Vec 2.0 checkpoints pre-trained on datasets from multiple domains.
-
facebook/wav2vec2-large-robust
Updated • 76.3k • 35 -
facebook/wav2vec2-large-robust-ft-libri-960h
Automatic Speech Recognition • 0.3B • Updated • 244k • 15 -
facebook/wav2vec2-large-robust-ft-swbd-300h
Automatic Speech Recognition • Updated • 6.13k • 20 -
Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training
Paper • 2104.01027 • Published • 1
A collection of open-source artefacts (datasets + checkpoints) from the first VoxPopuli release.
-
facebook/voxpopuli
Updated • 8.63k • 123 -
VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation
Paper • 2101.00390 • Published • 1 -
facebook/wav2vec2-base-100k-voxpopuli
Automatic Speech Recognition • Updated • 8.41k • 4 -
facebook/wav2vec2-base-10k-voxpopuli-ft-cs
Automatic Speech Recognition • Updated • 22
A collection of checkpoints from the second VoxPopuli release.
-
VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation
Paper • 2101.00390 • Published • 1 -
facebook/wav2vec2-base-bg-voxpopuli-v2
Automatic Speech Recognition • Updated • 33 -
facebook/wav2vec2-base-cs-voxpopuli-v2
Automatic Speech Recognition • Updated • 22 • 1 -
facebook/wav2vec2-base-da-voxpopuli-v2
Automatic Speech Recognition • Updated • 25
A collection of checkpoints from the HuBERT release, a speech encoder that learns powerful representations from unlabelled audio data.
-
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
Paper • 2106.07447 • Published • 3 -
facebook/hubert-base-ls960
Feature Extraction • Updated • 282k • • 57 -
facebook/hubert-large-ll60k
Feature Extraction • Updated • 52.6k • 30 -
facebook/hubert-large-ls960-ft
Automatic Speech Recognition • Updated • 880k • 68
Text-to-speech models from fairseq s^2
-
facebook/dinov2-small
Image Feature Extraction • 0.0B • Updated • 1.3M • 41 -
facebook/dinov2-base
Image Feature Extraction • 0.1B • Updated • 2.02M • 137 -
facebook/dinov2-large
Image Feature Extraction • 0.3B • Updated • 990k • 84 -
facebook/dinov2-giant
Image Feature Extraction • 1B • Updated • 107k • 46
A collection of stereo music generation models as part of the v2 MusicGen release.
Meta LLM Compiler is a state-of-the-art LLM that builds upon Code Llama with improved performance for code optimization and compiler reasoning.
Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
Foundation models for human tasks. Code: https://github.com/facebookresearch/sapiens
OPT (Open Pretrained Transformer) is a series of open-sourced large causal language models which perform similar in performance to GPT3.