全站搜索

AI 模型 56

• gemma-3-12b-it-heretic-v2↗

  DreamFast

  An abliterated version of Google's Gemma 3 12B IT created using Heretic v1.3.0. This model has reduced refusals while maintaining model quality, making it suitable as an uncensored text encoder for video generation models like LTX-2. Available in five quantization formats for ComfyUI - FP8, INT8 (ConvRot row-wise), INT4 (W4A4 ConvRot), NVFP4, and MXFP8 - all produced with SVD-guided learned rounding for maximum fidelity, covering everything from Ada GPUs to Blackwell. You can see the docker, scripts and configurations used to make these files on Heretic Docker Github.

• chronos-2↗

  amazon

  **更新于 2026 年 6 月 5 日：** ☁️ 使用 AutoGluon-Cloud 在 AWS 上部署 Chronos-2。只需三行代码即可实现实时、无服务器或批处理推理——输入 pandas DataFrame，输出预测结果。请查看新的部署指南。**Chronos-2** 是一款拥有 1.2 亿参数的纯编码器时间序列基础模型，适用于零样本预测。它在单一架构内支持**单变量**、**多变量**以及**协变量感知**任务。受 T5 编码器启发，Chronos-2 能生成多步前瞻分位数预测，并采用组注意力机制，以高效的方式在相关序列和协变量间进行上下文学习。该模型基于真实世界数据与大规模合成数据集的组合进行训练，在 **fev-bench**、**GIFT-Eval** 和 **Chronos Benchmark II** 上的公开模型中达到了**最先进的零样本精度**。Chronos-2 还具有**极高的效率**，单张 A10G GPU 每秒可完成超过 300 个时间序列的预测，并同时支持**GPU 和 CPU 推理**。🧩 Chronos 和 Chronos-Bolt 本身不支持未来协变量，但可与外部协变量回归器结合使用（参见 AutoGluon 教程）。这种方式仅建模逐时间步的影响，而非跨时间的影响。相比之下，Chronos-2 原生支持所有类型的协变量。

• DeepSeek-V4.1-Flash-1017-GGUF↗

  unsloth

  Run on a 128GB+ RAM device for the smallest 1-bit, 3-bit on 256GB or full precision on 320GB. Read Guide To run, please use our llama.cpp PR or the Unsloth Desktop app. Get up to 3x faster inference with Unsloth vs other ngram/CPU/VRAM repos./ **DeepSeek-V4.1-Flash-1017** is a minor update to **DeepSeek-V4.1-Flash**, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks. Alongside these gains, the model reduces task execution time and output length, enabling users to complete tasks faster and at lower cost and advancing the performance–cost Pareto frontier across multiple agent harnesses. *† denotes the text-only subset of HLE. We use the Claude Code harness for Terminal-Bench 4.0 and the Mini-SWE-V2 harness for DeepSWE v1.1.*

• sam-3d-body-dinov3↗

  jetjodh

  **SAM 3D Body (3DB)** is a promptable model for single-image full-body 3D human mesh recovery (HMR). Our method demonstrates state-of-the-art performance, with strong generalization and consistent accuracy in diverse in-the-wild conditions. 3DB estimates the human pose of the body, feet, and hands based on the Momentum Human Rig (MHR), a new parametric mesh representation that decouples skeletal structure and surface shape for improved accuracy and interpretability. 3DB employs an encoder-decoder architecture and supports auxiliary prompts, including 2D keypoints and masks, enabling user-guided inference similar to the SAM family of models. Our model is trained on high-quality annotations from a multi-stage annotation pipeline using differentiable optimization, multi-view geometry, dense keypoint detection, and a data engine to collect and annotated data covering both common and rare poses across a wide range of viewpoints. If you use SAM 3D Body or the SAM 3D Body dataset in your research, please use the following BibTeX entry.

• musicgen-melody↗

  facebook

  Audiocraft provides the code and models for MusicGen, a simple and controllable model for music generation. MusicGen is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz. Unlike existing methods like MusicLM, MusicGen doesn't not require a self-supervised semantic representation, and it generates all 4 codebooks in one pass. By introducing a small delay between the codebooks, we show we can predict them in parallel, thus having only 50 auto-regressive steps per second of audio. MusicGen was published in Simple and Controllable Music Generation by *Jade Copet, Felix Kreuk, Itai Gat, Tal Remez, David Kant, Gabriel Synnaeve, Yossi Adi, Alexandre Défossez*. **Model type:** MusicGen consists of an EnCodec model for audio tokenization, an auto-regressive language model based on the transformer architecture for music modeling. The model comes in different sizes: 300M, 1.5B and 3.3B parameters ; and two variants: a model trained for text-to-music generation task and a model trained for melody-guided music generation.

• siglip2-x256-explicit-content↗

  prithivMLmods

  > **siglip2-x256-explicit-content** is a vision-language encoder model fine-tuned from **siglip2-base-patch16-256** for **multi-class image classification**. Built on the **SiglipForImageClassification** architecture, the model is trained to identify and categorize content types in images, especially for **explicit, suggestive, or safe media filtering**. > [!note] *SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features* https://arxiv.org/pdf/2502.14786 - **Content Moderation**: Automatically detect NSFW or suggestive content. - **Parental Controls**: Enable AI-based filtering for safe media browsing. - **Dataset Preprocessing**: Clean and categorize image datasets for research or deployment. - **Online Platforms**: Help enforce content guidelines for uploads and user-generated media.

• gemma-4-12b↗

  unsloth

  Gemma 4 12B can now be run and fine-tuned in Unsloth Studio . Read our guide . See all versions of Gemma 4 (GGUF, 16-bit etc.) in our collection . Example of Gemma 4 E4B (4-bit GGUF) running in Unsloth Studio with tool-calling: > [!Note] > This model card is for the Gemma 4 12B Unified model, which is part of the Gemma 4 family of open models. Built with the same multimodal functionality as Gemma 4 E2B and E4B (text, audio, image, and video inputs), it brings native audio and vision understanding directly to local environments without the need for separate encoders. This unified approach to multimodality makes the model encoder-free, offering a deployment size that is perfect for consumer devices and streamlined local execution. 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.

• Qwen3.6-35B-A3B-heretic-NVFP4↗

  AEON-7

  > ✅ **Validated on the unified AEON vLLM Ultimate image `ghcr.io/aeon-7/aeon-vllm-ultimate:latest`** (= `:2026-06-18-v0.23.0-dflashfix`; rollback `:2026-06-11-pr41703`) — vLLM 0.23.0 built from source for GB10 / sm_121a + the AEON DFlash stack. Loads + serves cleanly (compressed-tensors MoE) — **including working multimodal image understanding** (a vision tensor-prefix bug was fixed 2026-06-18 — see the **Vision fix** section below) — and with DFlash `num_speculative_tokens: 11` now scales to **c=64** with **up to ~740 tok/s aggregate** and **no concurrency crash**. This single image supersedes the older `vllm-spark-omni-q36:v1.2` container. **Recommended container base.** > **🚀 PRODUCTION DEPLOYMENT GUIDE: github.com/AEON-7/Qwen3.6-35B-A3B-heretic-NVFP4-DFlash** > > The GitHub repo is the **definitive turn-key setup** for DGX Spark — end-to-end > deployment guide, validated OpenClaw config, and a concurrency-sweep benchmark harness. > > - Image: `ghcr.io/aeon-7/aeon-vllm-ultimate:latest` (vLLM 0.23.0 source-built for sm_121a + the AEON speculative-decoding stack — see What we fixed for the DGX Spark) > - Pairs with `z-lab/Qwen3.6-35B-A3B-DFlash` drafter (must be **post 2026-04-19** revision) > - **Production-stable** under sustained chat load and concurrent agent fleets up to c=64 on DGX Spark v1 of this checkpoint had `model.language_model.layers.X.*` keys remapped to `model.layers.X.*` so vLLM's text-only `Qwen3_5MoeForCausalLM` loader would pick them up. That layout was unstable in production — intermittent NaN/crash in the prefix-strip codepath during real chat sessions.

• orpheus-3b-0.1-ft↗

  unsloth

  **03/18/2025** – We are releasing our 3B Orpheus TTS model with additional finetunes. Code is available on GitHub: CanopyAI/Orpheus-TTS Orpheus TTS is a state-of-the-art, Llama-based Speech-LLM designed for high-quality, empathetic text-to-speech generation. This model has been finetuned to deliver human-level speech synthesis, achieving exceptional clarity, expressiveness, and real-time streaming performances. - **Human-Like Speech**: Natural intonation, emotion, and rhythm that is superior to SOTA closed source models - **Zero-Shot Voice Cloning**: Clone voices without prior fine-tuning - **Guided Emotion and Intonation**: Control speech and emotion characteristics with simple tags - **Low Latency**: ~200ms streaming latency for realtime applications, reducible to ~100ms with input streaming

• gemma-4-12b-it-NVFP4↗

  unsloth

  Gemma 4 12B can now be run and fine-tuned in Unsloth Studio . Read our guide . See all versions of Gemma 4 (GGUF, 16-bit etc.) in our collection . Example of Gemma 4 E4B (4-bit GGUF) running in Unsloth Studio with tool-calling: > [!Note] > This model card is for the Gemma 4 12B Unified model, which is part of the Gemma 4 family of open models. Built with the same multimodal functionality as Gemma 4 E2B and E4B (text, audio, image, and video inputs), it brings native audio and vision understanding directly to local environments without the need for separate encoders. This unified approach to multimodality makes the model encoder-free, offering a deployment size that is perfect for consumer devices and streamlined local execution. 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.