Search Results for "decoder"
Sort By:
Showing 21 open source projects for "decoder"
View related business solutions-
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
1
Step1X-Edit
A SOTA open-source image editing model
Step1X-Edit is a state-of-the-art open-source image editing model/framework that uses a multimodal large language model (LLM) together with a diffusion-based image decoder to let users edit images simply via natural-language instructions plus a reference image. You supply an existing image and a textual command — e.g. “add a ruby pendant on the girl’s neck” or “make the background a sunset over mountains” — and the model interprets the instruction, computes a latent embedding combining the image content and user intent, then decodes a new image implementing the edit. ... -
2
Granite Code Models
A Family of Open Foundation Models for Code Intelligence
Granite Code Models are IBM’s open-source, decoder-only models tailored for code tasks such as fixing bugs, explaining and documenting code, and modernizing codebases. Trained on code from 116 programming languages, the family targets strong performance across diverse benchmarks while remaining accessible to the community. The repository introduces the model lineup, intended uses, and evaluation highlights, and it complements IBM’s broader Granite initiative spanning multiple modalities. ... -
3
Miso TTS
Miso TTS is an 8 billion, highly emotive text-to-speech model
Miso TTS is an advanced 8-billion-parameter text-to-speech model developed by Miso Labs for generating highly expressive and natural-sounding conversational speech. Built on an RVQ Transformer architecture inspired by Sesame CSM, it combines a powerful Llama-based backbone with an autoregressive audio decoder to produce high-quality audio from text. The model supports both standard speech synthesis and voice-conditioned generation using optional audio prompts for voice cloning. Miso TTS generates Mimi audio codes and can leverage conversation history to create more contextually aware and realistic dialogue. Designed for local deployment, it offers watermarking by default to help promote responsible use of generated audio. ... -
4
IndexTTS2
Industrial-level controllable zero-shot text-to-speech system
...It builds on state-of-the-art models such as XTTS and other modern neural TTS backbones, improving them with a conformer-based speech conditional encoder and upgrading the decoder to a high-quality vocoder (BigVGAN2), leading to clearer and more natural audio output. The system supports zero-shot voice cloning — meaning it can mimic a target speaker’s voice from a short reference sample — making it versatile for multi-voice uses. Compared to many open-source TTS tools, IndexTTS emphasizes efficiency and controllability: it offers faster inference, simpler training pipelines, and controllable speech parameters (like duration, pitch, and prosody), which is critical for production use. -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
5
TimesFM
Pretrained time-series foundation model developed by Google Research
TimesFM is a pretrained time-series foundation model from Google Research built for forecasting tasks, designed to generalize across many domains without requiring extensive per-dataset retraining. It provides a decoder-only model approach to forecasting, aiming for strong performance even in zero-shot or low-data settings where traditional models often struggle. The project includes code and an inference API intended to make it practical to run forecasts programmatically, with options to use different backends such as Torch or Flax depending on your environment and performance needs. ... -
6
h3-metal
MiniMax H3 inference engine for Mac computers
...It supports prompt-to-video and prompt-to-audio workflows as well as first-frame, last-frame, image, video, and audio references. An interactive terminal session keeps prompt conditioning, the diffusion transformer, and the video decoder in memory for faster repeated generations. Users can trade speed, quality, and memory through denoising steps, layer counts, reuse modes, token reduction, internal render size, and SSD streaming. Optional terminal previews show intermediate and final frames during generation. The engine uses the original BF16 checkpoint and provides profiling tools for timing, Metal execution, tensor memory, allocations, and dispatch counts. -
7
GLM-OCR
Accurate × Fast × Comprehensive
GLM-OCR is an open-source multimodal optical character recognition (OCR) model built on a GLM-V encoder–decoder foundation that brings robust, accurate document understanding to complex real-world layouts and modalities. Designed to handle text recognition, table parsing, formula extraction, and general information retrieval from documents containing mixed content, GLM-OCR excels across major benchmarks while remaining highly efficient with a relatively compact parameter size (~0.9B), enabling deployment in high-concurrency services and edge environments. ... -
8
FireRedASR
Open-source industrial-grade ASR models
...The project includes multiple model variants to meet different application needs, such as high-accuracy end-to-end interaction using an encoder-adapter-LLM framework and efficient real-time recognition using attention-based encoder-decoder architectures, giving developers flexibility in balancing performance and resource constraints. FireRedASR not only excels in traditional speech recognition tasks but also demonstrates strong capability in challenging scenarios like singing lyrics recognition, where accurate transcription is often difficult for conventional models. -
9
Step3-VL-10B
Multimodal model achieving SOTA performance
...It achieves this efficiency and strong performance through unified pre-training on a massive 1.2 trillion-token multimodal corpus that jointly optimizes a language-aligned perception encoder with a powerful decoder, creating deep synergy between image processing and text understanding. -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
10
CSM (Conversational Speech Model)
A Conversational Speech Generation Model
The CSM (Conversational Speech Model) is a speech generation model developed by Sesame AI that creates RVQ audio codes from text and audio inputs. It uses a Llama backbone and a smaller audio decoder to produce audio codes for realistic speech synthesis. The model has been fine-tuned for interactive voice demos and is hosted on platforms like Hugging Face for testing. CSM offers a flexible setup and is compatible with CUDA-enabled GPUs for efficient execution. -
11
DeepSeek LLM
DeepSeek LLM: Let there be answers
...The model is trained from scratch, reportedly on a vast multilingual + code + reasoning dataset, and competes with other open or open-weight models. The architecture mirrors established decoder-only transformer families: pre-norm structure, rotational embeddings (RoPE), grouped query attention (GQA), and mixing in languages and tasks. It supports both “Base” (foundation model) and “Chat” (instruction / conversation tuned) variants. -
12
LaMDA-pytorch
Open-source pre-training implementation of Google's LaMDA in PyTorch
Open-source pre-training implementation of Google's LaMDA research paper in PyTorch. The totally not sentient AI. This repository will cover the 2B parameter implementation of the pre-training architecture as that is likely what most can afford to train. You can review Google's latest blog post from 2022 which details LaMDA here. You can also view their previous blog post from 2021 on the model. -
13
Mask2Former
Code release for "Masked-attention Mask Transformer
Mask2Former is a unified segmentation architecture that handles semantic, instance, and panoptic segmentation with one model and one training recipe. Its core idea is to cast segmentation as mask classification: a transformer decoder predicts a set of mask queries, each with an associated class score, eliminating the need for task-specific heads. A pixel decoder fuses multi-scale features and feeds masked attention in the transformer so each query focuses computation on its current spatial support. This leads to accurate masks with sharp boundaries and strong small-object performance while remaining efficient on high-resolution inputs. ... -
14
MAE (Masked Autoencoders)
PyTorch implementation of MAE
...It trains a Vision Transformer (ViT) by randomly masking a high percentage of image patches (typically 75%) and reconstructing the missing content from the remaining visible patches. This forces the model to learn semantic structure and global context without supervision. The encoder processes only the visible patches, while a lightweight decoder reconstructs the full image—making pretraining computationally efficient. After pretraining, the encoder serves as a powerful backbone for downstream tasks like image classification, segmentation, and detection, achieving top performance with minimal fine-tuning. The repository provides pretrained models, fine-tuning scripts, evaluation protocols, and visualization tools for reconstruction quality and learned features. -
15
fairseq-lua
Facebook AI Research Sequence-to-Sequence Toolkit
fairseq-lua is the original Lua/Torch7 version of Facebook AI Research’s sequence modeling toolkit, designed for neural machine translation (NMT) and sequence generation. It introduced early attention-based architectures and training pipelines that later evolved into the modern PyTorch-based fairseq. The framework implements sequence-to-sequence models with attention, beam search decoding, and distributed training, providing a research platform for exploring translation, summarization, and... -
16
Denoiser
Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)
Denoiser is a real-time speech enhancement model operating directly on raw waveforms, designed to clean noisy audio while running efficiently on CPU. It uses a causal encoder-decoder architecture with skip connections, optimized with losses defined both in the time domain and frequency domain to better suppress noise while preserving speech. Unlike models that operate on spectrograms alone, this design enables lower latency and coherent waveform output. The implementation includes data augmentation techniques applied to the raw waveforms (e.g. noise mixing, reverberation) to improve model robustness and generalization to diverse noise types. ... -
17
MiMo-V2.6-Flash
Efficient 309B omnimodal MoE for coding, agents, vision, and audio
...Training uses a unified mixed RL process rather than separate domain-specific runs, alongside asynchronous GRPO and groupwise agentic grading that rewards higher-quality and more efficient solutions. Its architecture combines sliding-window and global attention with a 681M-parameter vision encoder and dedicated audio encoders. A five-layer speculative decoder predicts multiple subsequent tokens to accelerate inference. -
18
MiMo-V2.6-Pro
1T omnimodal MoE model for coding, agents, and long-horizon reasoning
...Its architecture combines sliding-window and global attention, a 681M-parameter vision encoder, dedicated audio encoders, and a five-layer multi-token speculative decoder. It targets coding, general and visual agents, tool use, cybersecurity, long-horizon reasoning, etc. -
19
t5-base
Flexible text-to-text transformer model for multilingual NLP tasks
t5-base is a pre-trained transformer model from Google’s T5 (Text-To-Text Transfer Transformer) family that reframes all NLP tasks into a unified text-to-text format. With 220 million parameters, it can handle a wide range of tasks, including translation, summarization, question answering, and classification. Unlike traditional models like BERT, which output class labels or spans, T5 always generates text outputs. It was trained on the C4 dataset, along with a variety of supervised NLP... -
20
bart-large-cnn
Summarization model fine-tuned on CNN/DailyMail articles
facebook/bart-large-cnn is a large-scale sequence-to-sequence transformer model developed by Meta AI and fine-tuned specifically for abstractive text summarization. It uses the BART architecture, which combines a bidirectional encoder (like BERT) with an autoregressive decoder (like GPT). Pre-trained on corrupted text reconstruction, the model was further trained on the CNN/DailyMail dataset—a collection of news articles paired with human-written summaries. It performs particularly well in generating concise, coherent, and human-readable summaries from longer texts. Its architecture allows it to model both language understanding and generation tasks effectively. ... -
21
Inkling-Small
Efficient multimodal MoE model for coding, tools, and reasoning
...The model uses a sparse Mixture-of-Experts architecture with 276B total parameters and 12B active per token, enabling strong performance with lower inference cost than a fully dense model of similar scale. Its 42-layer decoder routes each token through six of 256 specialized experts plus two shared experts, while hybrid local and global attention supports efficient processing. Inkling-Small performs strongly across software engineering, tool use, mathematics, vision, and audio benchmarks, including 80.2% on SWE-Bench Verified and 95.5% on AIME 2026.
- Previous
- You're on page 1
- Next
