全站搜索

AI 模型 2119

• Uncensored-Jordan-13B-GGUF↗

  TheBloke

  GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. The creator of the source model has listed its license as `cc-by-nc-nd-4.0`, and this quantization has therefore used that same license. As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.

• resnet101d.ra2_in1k↗

  timm

  This model features: * ReLU activations * 3-layer stem of 3x3 convolutions with pooling * 2x2 average pool + 1x1 convolution shortcut downsample Recipe details: * RandAugment `RA2` recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as `B` recipe in ResNet Strikes Back. * RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging * Step (exponential decay w/ staircase) LR schedule with warmup

• vibevoice-realtime-0.5b-GGUF↗

  cstr

  > The Q8_0/Q4_K files keep the diffusion prediction head, connectors and > EOS classifier at full precision (only the two Qwen2 backbones are > quantized). The head runs under classifier-free guidance over 20 solver > steps, so quantizing it could push the first frames onto a wrong > trajectory that decodes as a brief non-speech "music"/hum onset before > the voice; keeping it at full precision avoids that at a small size cost. A voice prompt is **required** for TTS. Each `.gguf` voice pack ships pre-computed KV caches that establish a fixed speaker identity (the realtime variant is *not* WAV-cloning — for runtime cloning, use `cstr/vibevoice-1.5b-GGUF` instead). This repo bundles all 25 demo voices from `microsoft/VibeVoice@main demo/voices/streaming_model/` — same MIT license as the model.

• TerraMind-1.0-large↗

  ibm-esa-geospatial

  TerraMind is the first multimodal any-to-any generative foundation model for Earth Observation jointly developed by IBM, ESA, and Forschungszentrum Jülich. TerraMind uses a dual-scale transformer-based encoder-decoder architecture, simultaneously processing pixel-level and token-level data. The model was pre-trained on 500B tokens from 9M spatiotemporally aligned multimodal samples from the TerraMesh dataset. Modality-specific patch embeddings allow direct processing of raw inputs, while modality-specific FSQ-VAEs are used for image tokenization. For sequence-like modalities such as coordinates, an adapted WordPiece tokenizer is employed. During pre-training, TerraMind leverages masked token reconstruction, learning complex cross-modal correlations to generate high-quality latent representations.

• sdxl-detector↗

  Organika

  This model was created by fine-tuning the umm-maybe AI art detector on a dataset of Wikimedia-SDXL image pairs, where the SDXL image is generated using a prompt based upon a BLIP-generated caption describing the Wikimedia image. This model demonstrates greatly improved performance over the umm-maybe detector on images generated by more recent diffusion models as well as non-artistic imagery (given the broader range of subjects depicted in the random sample drawn from Wikimedia). However, its performance may be lower for images generated using models other than SDXL. In particular, this model underperforms the original detector for images generated using older models (such as VQGAN+CLIP).

• ModernBERT-large-nli↗

  tasksource

  This model is ModernBERT multi-task fine-tuned on tasksource NLI tasks, including MNLI, ANLI, SICK, WANLI, doc-nli, LingNLI, FOLIO, FOL-NLI, LogicNLI, Label-NLI and all datasets in the below table). This is the equivalent of an "instruct" version. The model was trained for 200k steps on an Nvidia A30 GPU. It is very good at reasoning tasks (better than llama 3.1 8B Instruct on ANLI and FOLIO), long context reasoning, sentiment analysis and zero-shot classification with new labels. The following table shows model test accuracy. These are the scores for the same single transformer with different classification heads on top. Further gains can be obtained by fine-tuning on a single-task, e.g. SST, but it this checkpoint is great for zero-shot classification and natural language inference (contradiction/entailment/neutral classification).

• Ingot-X-27B-Q2↗

  dendriteholdings

  A public mirror of a model that won on Ingot, a Bittensor subnet where miners quantize a fixed teacher model and the validator crowns the copy that stays closest to it. It is Prism ML's Ternary Bonsai 2 27B, refined: the same ternary codes, with the per-block scales and the norm weights re-tuned by the miner to bring it closer to Qwen3.8-27B. The weights are the miner's upload, byte for byte. Credit belongs to the miner, and to Prism ML for Bonsai 2.

• granite-4.1-3b-base↗

  ibm-granite

  **Model Summary:** Granite‑4.1‑3B‑Base is a decoder‑only language model with long‑context capabilities, designed to support a broad range of general text‑to‑text generation tasks, as well as fill‑in‑the‑Middle (FIM) code completion. This model shares the same underlying architecture and weights as Granite 4.0 3B Micro, which is trained from scratch on approximately 15 trillion tokens following a four-stage training strategy: 10 trillion tokens in the first stage, 2 trillion in the second, another 2 trillion in the third, and 0.5 trillion in the final stage. An additional training phase is applied to expand the model’s context window to 512K tokens. **Supported Languages:** English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. Users may finetune Granite 4.1 models for languages beyond these languages. **Intended Use:** Prominent use cases of LLMs in text-to-text generation include summarization, text classification, extraction, question-answering, code-completion (including FIM), and long-context generation tasks. All Granite Base models are able to handle these tasks as they were trained on a large amount of data from various domains. Moreover, they can serve as baseline to create specialized models for specific application scenarios.

• MiniCPM-V-4.7-35B-A3B↗

  openbmb

  **MiniCPM-V 4.7** is the latest model in the MiniCPM-V series, available in a **35B-A3B** variant, with **35B-A3B being the first MoE model in the MiniCPM-V series**. It builds on the family's single-image, multi-image, and video understanding capabilities, combining stronger foundation capabilities with efficient visual encoding and on-device inference. Notable features of MiniCPM-V 4.7 include: - 📱 **The First Open-Source MoE Model with Lossless, Smooth On-Device Inference.** With our **Lookahead Expert Scheduling (LES)** technique introduced alongside MiniCPM-V 4.7, combined with fine-grained layer-wise quantization and DSpark speculative sampling integration, MiniCPM-V 4.7 35B-A3B becomes the **first open-source MoE model to run smoothly on-device without compromising performance**, achieving a decoding speed of **13+ tokens/s with just 3 GB of memory on iPhone 17 Pro Max**. - 🔥 **A New Pareto Frontier in Performance and Efficiency.** As model capabilities continue to advance, inference efficiency has become an important measure of a model's value. On resource-constrained devices, delivering the strongest possible capabilities within a limited resource budget calls for higher capability density. The **35B-A3B** variant of MiniCPM-V 4.7 advances the performance–efficiency Pareto frontier for MLLMs. In Instruct mode, 35B-A3B **achieves a higher overall score in less inference time than Qwen3.6 35B-A3B**. - 🚀 **Efficient Architecture.** Based on the intra-ViT early compression technique from LLaVA-UHD v4, MiniCPM-V 4.7 compresses visual tokens early within the vision encoder, reducing computation in subsequent encoder layers. It also supports **mixed 4x/16x visual token compression**, allowing developers to balance visual detail and inference cost across tasks. - 💻 **Broad Platform and Chip Support.** MiniCPM-V 4.7 supports **iOS, Android, and HarmonyOS**, together with open-source on-device deployment support. It also provides **day-0 support for chip platforms from Rockchip, Houmo, Intel, AMD, and Arm**, extending deployment options across mobile and local computing devices. - 🛠️ **Developer Friendly.** MiniCPM-V 4.7 supports inference frameworks including SGLang, vLLM, llama.cpp, and Ollama, along with fine-tuning frameworks including SWIFT and LLaMA-Factory. It provides GGUF, BNB, AWQ, and GPTQ quantized variants and adds **FP8 quantization support

• wav2vec2-xls-r-1b↗

  facebook

  XLS-R is Facebook AI's large-scale multilingual pretrained model for speech (the "XLM-R for Speech"). It is pretrained on 436k hours of unlabeled speech, including VoxPopuli, MLS, CommonVoice, BABEL, and VoxLingua107. It uses the wav2vec 2.0 objective, in 128 languages. When using the model make sure that your speech input is sampled at 16kHz. **Note**: This model should be fine-tuned on a downstream task, like Automatic Speech Recognition, Translation, or Classification. Check out **this blog** for more information about ASR. **Abstract** This paper presents XLS-R, a large-scale model for cross-lingual speech representation learning based on wav2vec 2.0. We train models with up to 2B parameters on 436K hours of publicly available speech audio in 128 languages, an order of magnitude more public data than the largest known prior work. Our evaluation covers a wide range of tasks, domains, data regimes and languages, both high and low-resource. On the CoVoST-2 speech translation benchmark, we improve the previous state of the art by an average of 7.4 BLEU over 21 translation directions into English. For speech recognition, XLS-R improves over the best known prior work on BABEL, MLS, CommonVoice as well as VoxPopuli, lowering error rates by 20%-33% relative on average. XLS-R also sets a new state of the art on VoxLingua107 language identification. Moreover, we show that with sufficient model size, cross-lingual pretraining can outperform English-only pretraining when translating English speech into other languages, a setting which favors monolingual pretraining. We hope XLS-R can help to improve speech processing tasks for many more languages of the world.