サイト内検索

AI モデル 2119

• 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.

• grug-27b-gguf↗

  ProCreations

  **2026-07-23: all rocks re-squeezed from v2.1 weights** (deep think on hard problems, stuck-loop escape, stop discipline - full changelog on grug-27b card). re-download if you grab rocks before. mmproj unchanged (vision tower untouched). this GGUF of grug-27b: Qwen3.6-27B that think in dense grug-speak inside ` `, answer in normal english. same reasoning depth, way fewer think token. full story on main model card. both parent grug hunt HumanEval and sanitized MBPP. number below come from big parent brain, NOT squeezed GGUF rock. grug not claim rock test it never get. number show pass@1 percent. bold grug win that hunt.

• samantha-mistral-instruct-7B-GGUF↗

  TheBloke

• Qwen-Image-2.1-Turbo-GGUF↗

  AtomicChat

  The 8-step Qwen-Image-2.1 as GGUF for stable-diffusion.cpp, built from the published BF16 weights with our own importance matrix. The renders and measurements behind this card are public. Generate images locally in Atomic Chat . It runs stable-diffusion.cpp, the engine these files were built and checked with. Turbo drifts from the original picture faster than you might expect at 4 bits and below. Our AD-Q4_K stays 21% closer to the BF16 image than the plain Q4_K , for 150 MB more. Turbo needs its own 8-step schedule at CFG 1. The exact settings are in Running it . Looking for uncensored? The open Qwen-Image pipeline has no content filter. Qwen-Image-2.1-Turbo-Uncensored-GGUF removes the refusal direction from its text encoder. On images that changed nothing we could measure, and the card shows why. Each file renders the same 48 prompts × 2 seeds from the same starting noise as the BF16 weights. We compare every image with the BF16 image of the same prompt and seed.

• kotoba-whisper-v2.0↗

  kotoba-tech

  _Kotoba-Whisper_ is a collection of distilled Whisper models for Japanese ASR, developed through the collaboration bewteen Asahi Ushio and Kotoba Technologies. Following the original work of distil-whisper (Robust Knowledge Distillation via Large-Scale Pseudo Labelling), we employ OpenAI's Whisper large-v3 as the teacher model, and the student model consists the full encoder of the teacher large-v3 model and the decoder with two layers initialized from the first and last layer of the large-v3 model. Kotoba-Whisper is **6.3x faster than large-v3**, while retaining as low error rate as the large-v3. As successor of our first model, kotoba-whisper-v1.0, we release ***kotoba-whisper-v2.0*** trained on the `all` subset of ReazonSpeech (the largest speech-transcription paired dataset in Japanese extracted from Japanese TV audio recordings), which amounts 7,203,957 audio clips (5 sec audio with 18 text tokens in average) after those transcriptions more than 10 WER are removed (see WER Filter for detail). The model was trained for 8 epochs with batch size 256 with sampling rate of 16kHz, and the training and evaluation code to reproduce kotoba-whisper is available at https://github.com/kotoba-tech/kotoba-whisper. Kotoba-whisper-v2.0 achieves better CER and WER than the openai/whisper-large-v3 in the in-domain held-out test set from ReazonSpeech, and achieves competitive CER and WER on the out-of-domain test sets including JSUT basic 5000 and the Japanese subset from CommonVoice 8.0 (see Evaluation for detail).

• nb-whisper-small↗

  NbAiLab

  Introducing the **_Norwegian NB-Whisper Small model_**, proudly developed by the National Library of Norway. NB-Whisper is a cutting-edge series of models designed for automatic speech recognition (ASR) and speech translation. These models are based on the work of OpenAI's Whisper. Each model in the series has been trained for 250,000 steps, utilizing a diverse dataset of 8 million samples. These samples consist of aligned audio clips, each 30 seconds long, culminating in a staggering 66,000 hours of speech. For an in-depth understanding of our training methodology and dataset composition, keep an eye out for our upcoming article. While the main models are suitable for most transcription task, we demonstrate how easy it is to change the output of the main model. The following models are trained 250 additional steps from the main models above, and might be suitable for more targetted use cases: - **Verbatim version**: This lower-cased variant is more literal and suitable for tasks requiring detailed transcription, such as linguistic analysis. You can try the models directly through the HuggingFace Inference API, accessible on the right side of this page. Be aware that initially, the model needs to load and will run on limited CPU capacity, which might be slow. To enhance your experience, we are temporarily hosting some models on TPUs for a few days, significantly boosting their performance. Explore these under the **Spaces** section on the Main Page.

• phi-1_5↗

  Microsoft

  The language model Phi-1.5 is a Transformer with **1.3 billion** parameters. It was trained using the same data sources as phi-1, augmented with a new data source that consists of various NLP synthetic texts. When assessed against benchmarks testing common sense, language understanding, and logical reasoning, Phi-1.5 demonstrates a nearly state-of-the-art performance among models with less than 10 billion parameters. We **did not** fine-tune Phi-1.5 either for **instruction following or through reinforcement learning from human feedback**. The intention behind crafting this open-source model is to provide the research community with a non-restricted small model to explore vital safety challenges, such as reducing toxicity, understanding societal biases, enhancing controllability, and more. For a safer model release, we exclude generic web-crawl data sources such as common-crawl from the training. This strategy prevents direct exposure to potentially harmful online content, enhancing the model's safety without RLHF. However, the model is still vulnerable to generating harmful content. We hope the model can help the research community to further study the safety of language models.

• qwen3-asr-1.7b-GGUF↗

  cstr

  Qwen3-ASR-1.7B is a multilingual speech recognition model supporting 30 languages + 22 Chinese dialects, with support for speech, singing voice, and songs with background music. Audio inputs up to 5 minutes. `qwen3-asr-1.7b-q4_k.gguf` was re-baked with the 24-layer **audio encoder kept at Q8_0** (previously Q4_K like the LLM body; ~0.15 GB larger). The earlier Q4_K export could emit an **empty transcript** (or, on longer audio, a repeated phrase) while still reporting success (CrispASR #240) — the same sub-8-bit encoder drift diagnosed in #218. Encoder-output cosine vs the F16 reference (jfk): **0.9632 → 0.9989** min, **0.9913 → 0.9998** mean — i.e. the tower is back to near-lossless and decode no longer degenerates. The Q8_0 and F16 files were never affected. On JFK speech sample (11s, English): - Q4_K: 0.2x realtime on CPU (4 threads) - Perfect transcription accuracy

• wav2vec2-large-xlsr-53-dutch↗

  jonatasgrosman

  Fine-tuned facebook/wav2vec2-large-xlsr-53 on Dutch using the train and validation splits of Common Voice 6.1 and CSS10. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud :) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint

• GLM-5.3-Flash-EXL3-4bpw-TensorFold↗

  Mia-AiLab

  Mia's AI Lab's own EXL3 quantization of zai-org/GLM-5.3-Flash, built for TensorFold and served by the GLM-5.3-Flash EXL3 TensorFold recipe for DGX Sparks. **Lower KL divergence than the widely used TR3-4bpw quant on all six test sets, at the same size, speed and memory, measured against Z.AI's official FP8 release.** Same format and bit width; only the calibration is new. KL divergence measures how far a quant's next-token probabilities drift from the reference's, Z.AI's FP8 release (lower is better). This quant lowers it on all six sets: by 11-27% with only the routed experts quantized, and by 2-18% as TensorFold actually serves it, with its own 4-bit dense weights on top.