サイト内検索

AI モデル 2119

• mask2former-swin-tiny-cityscapes-panoptic↗

  facebook

  Mask2Former model trained on Cityscapes panoptic segmentation (tiny-sized version, Swin backbone). It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation and first released in this repository. Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team. Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outperforms the previous SOTA, MaskFormer both in terms of performance an efficiency by (i) replacing the pixel decoder with a more advanced multi-scale deformable attention Transformer, (ii) adopting a Transformer decoder with masked attention to boost performance without without introducing additional computation and (iii) improving training efficiency by calculating the loss on subsampled points instead of whole masks.

• gemma-4-31B-it-litert-lm↗

  litert-community

  This model card provides the Gemma 4 31B model in LiteRT-LM format that is ready for deployment on web and desktop. Please check back here regularly for updates on wider platform support and further functionality improvements. The current LiteRT-LM version supports text; audio, image, and multitoken prediction support will be available in a future update. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. This particular Gemma 4 model is a medium size so it is ideal for desktop use cases. By running this model on device, users can have private access to Generative AI technology without even requiring an internet connection. These models are provided in the `.litertlm` format for use with the LiteRT-LM framework. LiteRT-LM is a specialized orchestration layer built directly on top of LiteRT, Google’s high-performance multi-platform runtime trusted by millions of Android and edge developers. LiteRT provides the foundational hardware acceleration via XNNPack for CPU and ML Drift for GPU. LiteRT-LM adds the specialized GenAI libraries and APIs, such as KV-cache management, prompt templating, and function calling. This integrated stack is the same technology powering the Google AI Edge Gallery showcase app.

• Cosmos-Tokenize1-CV8x8x8-720p↗

  NVIDIA

  **Cosmos-Tokenize1** is a suite of visual tokenizers for images and videos that delivers various compression rates while maintaining high reconstruction quality. Cosmos Tokenizer can serve as an effective and efficient building block in both diffusion-based and autoregressive models for image and video generation. This model is ready for commercial use. Our tokenizers come in two types: **Continuous** (C) and **Discrete** (D), each with **Image** (I) and **Video** (V) variants: * Continuous tokenizers encode visual data into continuous latent embeddings, as shown in latent diffusion models like Stable Diffusion. These embeddings are suitable for models that generate data by sampling from continuous distributions. * Discrete tokenizers encode visual data into discrete latent codes, mapping them into quantized indices, as seen in autoregressive transformers such as VideoPoet. This discretization is required for models that generate data by optimizing the cross-entropy loss, such as the GPT models. **Model**: Cosmos-Tokenize1-CV8x8x8-360p, a continuous video tokenizer with 8x temporal compression, and 8x8 spatial compression rate.

• stable-video-diffusion-img2vid-xt↗

  Stability AI

  (SVD) Image-to-Video is a latent diffusion model trained to generate short video clips from an image conditioning. This model was trained to generate 25 frames at resolution 576x1024 given a context frame of the same size, finetuned from [SVD Image-to-Video [14 frames]](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid). We also finetune the widely used f8-decoder for temporal consistency. For convenience, we additionally provide the model with the standard frame-wise decoder here. - **Developed by:** Stability AI - **Funded by:** Stability AI - **Model type:** Generative image-to-video model - **Finetuned from model:** SVD Image-to-Video [14 frames] For research purposes, we recommend our `generative-models` Github repository (https://github.com/Stability-AI/generative-models), which implements the most popular diffusion frameworks (both training and inference).

• Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix-GGUF↗

  agentionai

  A 180 B model that runs **entirely on the GPU** of a 128 GB unified-memory box — 87.06 GiB at 4.23 bpw, within 2.5% perplexity of the unquantized model. Sized for the 96 GiB VRAM carve-out of a Strix Halo (Ryzen AI MAX+ 395 / Radeon 8060S). *Throughput against context depth, against our closest mainline-compatible quant run on both this fork and stock llama.cpp — numbers and discussion under Holding up at long context.* - **Everything stays on the GPU.** Not the experts, not the 51.2 B-parameter n-gram table. No host-RAM fallback, no CPU compute in the hot path. - **Fast prefill that holds at depth** — 423 t/s at 512 tokens, 357 t/s at 8k, still 245 t/s at 32k and 138 t/s at 128k. Prefill is compute-bound and the ROCmFP4 types are cheaper to dequantize. Matters most for long prompts, agentic loops, and anything that re-reads a large context. - **Better perplexity than that same mainline tier**, by about two standard errors, and better than AesSedai's IQ4_XS and IQ3_S at 20–30 GB smaller. - **Vision included** — the model's own tower, at f16, losslessly converted. - **Speculative decoding included** — the model's own MTP head. Up to **40 tok/s generation** observed on a Strix Halo with adaptive drafting; acceptance is content-dependent, so the rate moves with what you are generating. - **imatrix-calibrated** on 1540 chunks from two corpora, so the low-bit tensors are fitted to real activations rather than assumed.

• GIST-small-Embedding-v0↗

  avsolatorio

  *GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning* The model is fine-tuned on top of the BAAI/bge-small-en-v1.5 using the MEDI dataset augmented with mined triplets from the MTEB Classification training dataset (excluding data from the Amazon Polarity Classification task). The model does not require any instruction for generating embeddings. This means that queries for retrieval tasks can be directly encoded without crafting instructions.

• DeepSeek-V4.1-Flash-GSQ-Uncensored↗

  IndrasMirror

  Runs on **Xolotl** (formerly Strata-DSV4.1), an engine built for exactly this model and this class of machine, on top of Strata. > **Update 2026-10-17:** the engine is now **Xolotl** (Strata-DSV4.1 renamed; > old links redirect) - one tree that also serves GLM-5.3-Flash and the Qwen3.8 models. Measured through the server > with thinking on (32K budget): **HumanEval 21/21, tool calls 10/10, agentic 3/3, decode 26.8 tok/s**. Agent turns got > cheaper: small-turn prefill -12% (bit-identical logits) and a **conversation-adaptive expert arena** (on by default) > that moves the conversation's NVMe experts into RAM between turns: -21..-30% NVMe reads, a +180-token turn on a 6K > context 8.5 -> 7.6 s. Build with `build-xolotl` (below). > **Update 2026-10-15:** the engine's defaults are now the **coding-safe route bias ×0.5** (HumanEval 20/21 and tool calls > 10/10, vs 16/21 at the old full bias) with DSpark speculative decoding **in the server** (exact speculative sampling), > a confidence-gated verify (prose 9.5 → 17.3, code 18.8 → 25.5, python 26.6 → 29.1 tok/s), a **bit-exact 4-bit KV cache** > (`--kv-fp4`, +1.1 GiB VRAM at 512K) and ~2× faster conversational turns (+1000-token turn 40 → 20 s at 512K). > Details: the repo README "Latest".

• Juggernaut-XL-v8↗

  RunDiffusion

  > Juggernaut XL v8 is the final release in the **RunDiffusion Photo v1** generation of the Juggernaut SDXL line — the version directly before the v9 jump to Photo v2. Useful if you have workflows or LoRAs tuned against the v8 aesthetic, or want the predecessor's slightly softer photographic feel. v8, v9, X, XI, Z, and Pro Flux — all pre-loaded. Switch in two clicks. No installs. No model downloads. One-click access inside ComfyUI, Forge, Automatic1111, Fooocus, InvokeAI, or SwarmUI. **Free trial included**, plus access to every other Juggernaut model on the same account.

• NVIDIA-NemotronLabs-RE-USE↗

  NVIDIA

  NVIDIA NemotronLabs RE-USE 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: - 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. - If better laughter preservation is desired, please use: NVIDIA-NemotronLabs-RE-USE-laughter. (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.

• aoi_clip_clean_new_sampler_fomula_clean↗

  sharkMeow