全站搜索

AI 模型 2119

• sam2.1-hiera-large-ONNX↗

  onnx-community

• chronos-bolt-mini↗

  autogluon

  🚀 **Update Feb 14, 2025**: Chronos-Bolt models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. Chronos-Bolt is a family of pretrained time series forecasting models which can be used for zero-shot forecasting. It is based on the T5 encoder-decoder architecture and has been trained on nearly 100 billion time series observations. It chunks the historical time series context into patches of multiple observations, which are then input into the encoder. The decoder then uses these representations to directly generate quantile forecasts across multiple future steps—a method known as direct multi-step forecasting. Chronos-Bolt models are **more accurate**, up to **250 times faster** and **20 times more memory-efficient** than the original Chronos models of the same size. The following plot compares the inference time of Chronos-Bolt against the original Chronos models for forecasting 1024 time series with a context length of 512 observations and a prediction horizon of 64 steps.

• mms-tts-kir↗

  facebook

  This model is part of Facebook's Massively Multilingual Speech project, aiming to provide speech technology across a diverse range of languages. You can find more details about the supported languages and their ISO 639-3 codes in the MMS Language Coverage Overview, and see all MMS-TTS checkpoints on the Hugging Face Hub: facebook/mms-tts. VITS (**V**ariational **I**nference with adversarial learning for end-to-end **T**ext-to-**S**peech) is an end-to-end speech synthesis model that predicts a speech waveform conditional on an input text sequence. It is a conditional variational autoencoder (VAE) comprised of a posterior encoder, decoder, and conditional prior. A set of spectrogram-based acoustic features are predicted by the flow-based module, which is formed of a Transformer-based text encoder and multiple coupling layers. The spectrogram is decoded using a stack of transposed convolutional layers, much in the same style as the HiFi-GAN vocoder. Motivated by the one-to-many nature of the TTS problem, where the same text input can be spoken in multiple ways, the model also includes a stochastic duration predictor, which allows the model to synthesise speech with different rhythms from the same input text.

• gemma-4-26B-A4B-it-qat-q4_0-unquantized↗

  Google

  > [!Note] > This model card is for the new versions of the Gemma 4 family optimized with Quantization-Aware Training (QAT), which allows preserving similar quality to bfloat16 while dramatically reducing the memory requirements to load the model. > Four versions of the QAT checkpoints are available: > * **Unquantized QAT checkpoints** (Q4_0): Half-precision weights extracted from the QAT pipeline, ideal for custom downstream compilation and research. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B, and their drafter models. > * **GGUF** (Q4_0): Ready-to-deploy formats for broad ecosystem compatibility. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B. > * **Mobile-optimized** (wNa8o8): A custom schema engineered explicitly for mobile hardware efficiency. It features targeted 2-bit decoding layers, optimized KV caches, and static activations to maximize VRAM savings. Available for Gemma 4 E2B and E4B. > * **Compressed Tensors** (w4a16): QAT checkpoints serialized in the compressed-tensors format for native, optimized inference with vLLM. Available for Gemma 4 E2B, E4B, 12B, and 31B. > * **Assistant Compatibility**: When using multi-token prediction (speculative decoding) with an assistant model alongside a QAT target model, the assistant model must also be a QAT checkpoint with the same precision to ensure compatibility. Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages. Featuring both Dense and Mixture-of-Experts (MoE) architectures, Gemma 4 is well-suited for tasks like text generation, coding, and reasoning. The models are available in five distinct sizes: **E2B**, **E4B**, **12B**, **26B A4B**, and **31B**. Their diverse sizes make them deployable in environments ranging from high-end phones to laptops and servers, democratizing access to state-of-the-art AI.

• ultratensor-models↗

  NagusameCS

• bigvgan_v2_24khz_100band_256x↗

  NVIDIA

  - **Jul 2024 (v2.3):** - General refactor and code improvements for improved readability. - Fully fused CUDA kernel of anti-alised activation (upsampling + activation + downsampling) with inference speed benchmark. - **Jul 2024 (v2.2):** The repository now includes an interactive local demo using gradio. - **Jul 2024 (v2.1):** BigVGAN is now integrated with 🤗 Hugging Face Hub with easy access to inference using pretrained checkpoints. We also provide an interactive demo on Hugging Face Spaces.

• NVIDIA-NemotronLabs-RE-USE-laughter↗

  NVIDIA

  NVIDIA NemotronLabs RE-USE-laughter is a 9.6-million-parameter **multilingual universal speech enhancement (USE)** model designed to restore speech quality across a wide range of real-world degradations while preserving speech fidelity. It has the following desirable properties: - **This model better preserves laughter while restoring the quality of the input speech.** - Robustness to **diverse degradations**, including additive noise, reverberation, clipping, bandwidth limitation, codec artifacts, packet loss and low-quality mics. - Support for **multiple input sampling rates**, including 8, 16, 22.05, 24, 32, 44.1, and 48 kHz. - Strong **language-agnostic** capability, enabling effective performance across different languages. (Note: For overlapping speech, this model is trained to preserve the main speaker while suppressing other speakers.) Comparison with other open-source USE models on the (subsets) of the URGENT 2025 non-blind test set, referenced against original anechoic clean speech.

• MiniCPM5-1B↗

  openbmb

  MiniCPM Tech Report | MiniCPM Wiki(Chinese) | GitHub Repo | UltraData | MiniCPM Desk Pet | Online Demo We are releasing **MiniCPM5-1B**, the first model in the **MiniCPM5** series. It is a dense 1B Transformer built for on-device, local deployment, and resource-constrained scenarios, reaching 1B-class open-source SOTA. 🏆 **1B-class open-source SOTA**: compared with strong open-source models in the same size class, MiniCPM5-1B reaches SOTA within this comparison set. Its advantage is most visible in agentic tool use, code generation, and difficult reasoning.

• Wuli-MiniMax-H3-Turbo-ComfyUI↗

  sandpies

  **Comparisons (same prompt and seed per row, euler / simple / 8 steps).** Left to right: hybrid, hybrid + Realism, FL2VA FlashGen. > **Update (Oct 16):** **F2** replaces the earlier `reflora100` hybrid as the recommended reference-to-video model. reflora100 baked in Kijai's Ref2VA reference LoRA, a low-rank approximation of the Ref2VA−FL2VA difference. F2 bakes in the full, uncompressed difference for blocks 25-49 instead, so it carries all of Ref2VA's reference behaviour in those blocks rather than a squeezed version, and it held up better than reflora100 in my tests. Same settings, same file size. ComfyUI-format conversions of **Wuli-Art's MiniMax-H3 Turbo** few-step audio+video distillations of MiniMax H3:

• Wan2.1-VAE-upscale2x↗

  spacepxl

  A decoder-only finetune of the Wan2.1 VAE, with 2x upscaling integrated directly into the decoder. The main purpose of this is to kill the dreaded wan speckles/polka dots/grain, but it's also convenient for highres fix workflows. The outputs of the 2x decoder are usually much better than what you would get by running the outputs of the original decoder through an image upscale model, and even better, it's effectively free, since the compute cost of decoding is virtually unchanged. If you don't want to use the extra resolution, a slight blur and downsample will give you an original resolution image with much higher quality than the original decoder can produce. In particular, this VAE improves skin details and hair very significantly. It is trained almost exclusively on real images, so it may struggle with anime/lineart and text. It would be possible to finetune on anime/lineart, but I'm not aware of a suitable dataset that's licensed correctly and not just full of scraped media with massive copyright violations. If you know of an appropriate datset for this that is sourced from cc-by materials or similar, let me know and I'd be happy to try training it. The first released version is trained on images only, and is compatible with both Wan and Qwen since they share the same latent space. A video version is planned, but video training is more complex than image training, so it will take some time.