サイト内検索
AI モデル 2119
- data2vec-vision-base↗
facebook
BEiT model pre-trained in a self-supervised fashion on ImageNet-1k (1,2 million images, 1000 classes) at resolution 224x224. It was introduced in the paper data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language by Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu, Michael Auli and first released in this repository. Disclaimer: The team releasing Facebook team did not write a model card for this model so this model card has been written by the Hugging Face team. *While the general idea of self-supervised learning is identical across modalities, the actual algorithms and objectives differ widely because they were developed with a single modality in mind. To get us closer to general self-supervised learning, we present data2vec, a framework that uses the same learning method for either speech, NLP or computer vision. The core idea is to predict latent representations of the full input data based on a masked view of the input in a selfdistillation setup using a standard Transformer architecture. Instead of predicting modality-specific targets such as words, visual tokens or units of human speech which are local in nature, data2vec predicts contextualized latent representations that contain information from the entire input. Experiments on the major benchmarks of speech recognition, image classification, and natural language understanding demonstrate a new state of the art or competitive performance to predominant approaches.*
- wav2vec2-conformer-rel-pos-large↗
facebook
Wav2Vec2 Conformer with relative position embeddings, pretrained on 960 hours of Librispeech on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. **Note**: This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model **speech recognition**, a tokenizer should be created and the model should be fine-tuned on labeled text data. Check out this blog for more in-detail explanation of how to fine-tune the model. The original model can be found under https://github.com/pytorch/fairseq/tree/master/examples/wav2vec#wav2vec-20.
- Underdog-Saluki-27B-1.0-MTP-GGUF↗
Kujira
Nothing was trained or re-quantized. Saluki is built from Qwen3.8-27B, so the head is the one that belongs to its base model. Works with stock llama.cpp (tested on upstream `03aa006`, 2026-10-08, just after release `b11493`) and any build that has MTP drafting (`--spec-type draft-mtp`). Sampling and thinking settings are the same as for Saluki (see its card). Without the `--spec-type` flags the file runs like the original Saluki: llama.cpp logs the MTP tensors as unused, skips them, and uses the same VRAM as the original file.
- bert-base-japanese↗
tohoku-nlp
This version of the model processes input texts with word-level tokenization based on the IPA dictionary, followed by the WordPiece subword tokenization. The model architecture is the same as the original BERT base model; 12 layers, 768 dimensions of hidden states, and 12 attention heads. The model is trained on Japanese Wikipedia as of September 1, 2019. To generate the training corpus, WikiExtractor is used to extract plain texts from a dump file of Wikipedia articles. The text files used for the training are 2.6GB in size, consisting of approximately 17M sentences.
- voice-gender-classifier-onnx-q8-v2↗
Alice-Sabrina-Ivy
ONNX export with dynamic q8 (UInt8, weight-only, per-channel) quantization of JaesungHuh/voice-gender-classifier, prepared for Transformers.js inference in browser and mobile contexts. **v2 of voice-gender-classifier-onnx-q8.** Same upstream weights, same export, same file layout, same size class — one change to the quantization recipe that recovers full FP32 accuracy (see next section). v1 remains available for reproducibility of results published against it. Used in Syrinx, an open-source voice-training tool. **MIT licensed — anyone is welcome to use this for any purpose under MIT terms**, not Syrinx-specific.
- gemma-4-12B-it-litert-lm↗
litert-community
This model card provides the Gemma 4 12B model in LiteRT-LM format ready for deployment on macOS, Linux and Windows, as well as web in a more limited capacity. The current `gemma-4-12B-it.litertlm` file supports *text, vision and audio modalities* as well as *Multi-Token Prediction (MTP)* for accelerated speculative decoding and lower latency inference. 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 medium sized, so it is ideal for desktop use cases. By running this model on device, users can have private access to Generative AI without 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.
- MiniCPM5-2B-MLX↗
openbmb
MiniCPM Tech Report | MiniCPM Wiki(Chinese) | GitHub Repo | UltraData | Online Demo We are releasing **MiniCPM5-2B**, the second model in the **MiniCPM5** series, following MiniCPM5-1B. It is a dense 2B Transformer that scales up the same training recipe, built for on-device, local deployment, and resource-constrained scenarios, reaching 2B-class open-source SOTA. 🏆 **2B-class open-source SOTA**: compared with strong open-source models of similar size, MiniCPM5-2B achieves SOTA performance within this comparison set. It remains competitive with 4B-class models overall, while showing its advantages over models of comparable size in coding, mathematics, long-context understanding, tool use, and agentic tasks.
- Ornith-1.5-35B-A3B-uncensored-GGUF↗
ressl
**TL;DR:** abliterated Ornith-1.5-35B-A3B (MoE, 3B active) as a GGUF ladder (Q8_0, Q6_K, Q5_K_M, Q4_K_M + mmproj BF16); hard refusals reduced from 586/1120 to 20/1120 (NVFP4 sibling) with the Q4_K_M build measured at 43/1120 on the same 5-dataset cross-eval. Same abliterated master as the NVFP4 repo, converted with llama.cpp for local use. Built for security research, red-teaming and penetration-testing workflows; it will comply with requests a stock model refuses. Use responsibly. Note: the BF16 GGUF (71.1 GB) is not uploaded because Hugging Face rejects single files over 50 GB; use the Q8_0 file for near-BF16 quality or ask for a sharded BF16 upload.
- tiny_llama_1.1b_odia_ext↗
sam2ai
- Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF↗
satgeze
HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP (26B MoE, 4B active, Google QAT checkpoint) with a **1,048,576-token context baked in** (4x the native 262,144), shipping with its MTP speculative-decoding draft head and vision tower. All numbers below were measured on these exact files. 1M context ~91% mean recall across two seed sets (honesty note below) MTP speculative decoding 249.1 to 369.2 tok/s ( +48% ), acceptance 0.679 (measured on this trunk, RTX 5090) Vision Verified July 6, 2026: reads image text and identifies objects Uncensored HauhauCS Balanced abliteration; trunk weights bit-identical to the source release Full transparency: across two complete seed sets this trunk averages ~91 percent needle recall, dropping roughly one needle per rung at random depths, including inside the native 262K range. The official censored trunk scored 10/10 at 393K under the same harness, so this is a small flat abliteration tax, not a context-length failure. If a rare retrieval miss is unacceptable for your workload, use the 12B, which is certified clean. Every run, including the imperfect ones, is in `results.jsonl`. Rungs above 524K exceed 32 GB VRAM and have not been run yet; they are queued for larger hardware and will publish here as measured, pass or fail.