Search FoxAI

AI Models 2119

• ukr-paraphrase-multilingual-mpnet-base↗

  lang-uk

  This is a sentence-transformers model fine-tuned for Ukrainian language: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. The original model used for fine-tuning is `sentence-transformers/paraphrase-multilingual-mpnet-base-v2`. See our paper Contextual Embeddings for Ukrainian: A Large Language Model Approach to Word Sense Disambiguation for details. Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

• MiniMax-H3-TextEncoder-16GB-GGUF↗

  pottokao

  > ⚠️ **Not a general-purpose LLM.** These files are the **text encoder of MiniMax-H3** and nothing else: cut to the > 50 layers H3 uses, with **no LM head** — they cannot chat or generate text. They exist so H3's 32B encoder fits a > **16 GB GPU in ComfyUI**. Built from the **official** MiniMax-H3 encoder (`MiniMaxAI/MiniMax-H3` → `text_encoder/`, revision `42ed227e`; Qwen3-VL-32B). Not abliterated. For comparison, on the same test: the earlier `MiniMax-H3-TextEncoder-Qwen3VL-32B-abliterated-GGUF` Q3_K_S (11.46 GB text part) scores 14.4% / 14.7%, and a stock llama.cpp Q3_K_S of the official weights 11.8% / 12.0%.

• Qwen3-Omni-30B-A3B-Captioner-GGUF↗

  presencesw

  GGUF conversion of Qwen/Qwen3-Omni-30B-A3B-Captioner for experimental audio captioning with llama.cpp. The Q4_K_M model and BF16 multimodal projector were tested together with `llama-mtmd-cli` on an audio sample. The audio encoder processed all five chunks and generated a caption. Audio support in llama.cpp remains experimental. Captioner is designed for one audio input and text output.

• bert-base-japanese-char↗

  tohoku-nlp

  This version of the model processes input texts with word-level tokenization based on the IPA dictionary, followed by character-level 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.

• dfine-small-coco↗

  ustc-community

  The D-FINE model was proposed in D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement by Yansong Peng, Hebei Li, Peixi Wu, Yueyi Zhang, Xiaoyan Sun, Feng Wu D-FINE, a powerful real-time object detector that achieves outstanding localization precision by redefining the bounding box regression task in DETR models. D-FINE comprises two key components: Fine-grained Distribution Refinement (FDR) and Global Optimal Localization Self-Distillation (GO-LSD). D-FINE is trained on COCO (Lin et al. [2014]) train2017 and validated on COCO val2017 dataset. We report the standard AP metrics (averaged over uniformly sampled IoU thresholds ranging from 0.50 − 0.95 with a step size of 0.05), and APval5000 commonly used in real scenarios.

• GigaAM-v3↗

  ai-sage

  GigaAM-v3 is a Conformer-based foundation model with 220–240M parameters, pretrained on diverse Russian speech data using the HuBERT-CTC objective. It is the third generation of the GigaAM family and provides state-of-the-art performance on Russian ASR across a wide range of domains. GigaAM-v3 includes the following model variants: - `ssl` — self-supervised HuBERT–CTC encoder pre-trained on 700,000 hours of Russian speech - `ctc` — ASR model fine-tuned with a CTC decoder - `rnnt` — ASR model fine-tuned with an RNN-T decoder - `e2e_ctc` — end-to-end CTC model with punctuation and text normalization - `e2e_rnnt` — end-to-end RNN-T model with punctuation and text normalization `GigaAM-v3` training incorporates new internal datasets: callcenter conversations, speech with background music, natural speech, and speech with atypical characteristics. the models perform on average **30%** better on these new domains, while maintaining the same quality as previous GigaAM generations on public benchmarks.

• DenseOn↗

  lightonai

  > 🎯 **TL;DR**: A 149M-parameter dense (single-vector) retrieval model achieving **56.20 nDCG@10 on BEIR**, the first sub-150M dense model to break the 56 mark, **topping all base-size dense models** and outperforming several models **4× larger**. State-of-the-art retrieval is increasingly dominated by closed models, either hidden behind APIs or trained on undisclosed data. This blocks reproducibility, prevents study of possible data leakage, and gatekeeps progress to a handful of private labs. We thus decided to gather and curate a large amount of data and explore various mixtures. We release all the data used in our explorations: - Gathered pre-training data, 1.4B query-documents pairs alongside annotations used for non-destructive filtering (structural filtering, deduplication, cross-encoder pair relevancy) - Best pre-training mixture found with already applied filters - Fine-tuning datasets with query, positive and 2048 mined documents alongside their scores for 1.88M samples. Based on our findings, we trained LateOn (multi-vector/ColBERT) and DenseOn (single vector/dense) models on a proprietary Apache 2.0-compatible training dataset and release those models as well. Both are built on the ModernBERT backbone at 149M parameters, a size we believe sits at the sweet spot: large enough to handle real-world queries and documents, small enough to serve at high throughput in latency-sensitive production systems. For more information, please read our blogpost.

• bart-large-cnn-samsum↗

  philschmid

  > If you want to use the model you should try a newer fine-tuned FLAN-T5 version philschmid/flan-t5-base-samsum out socring the BART version with `+6` on `ROGUE1` achieving `47.24`. This model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container. For more information look at: - 🤗 Transformers Documentation: Amazon SageMaker - Example Notebooks - Amazon SageMaker documentation for Hugging Face - Python SDK SageMaker documentation for Hugging Face - Deep Learning Container

• samai-8b-M8↗

  tchbcb

• whisper-large-v3-turbo-gguf↗

  xkeyC

  Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford et al. from OpenAI. Trained on >5M hours of labeled data, Whisper demonstrates a strong ability to generalise to many datasets and domains in a zero-shot setting. Whisper large-v3-turbo is a finetuned version of a pruned Whisper large-v3. In other words, it's the exact same model, except that the number of decoding layers have reduced from 32 to 4. As a result, the model is way faster, at the expense of a minor quality degradation. You can find more details about it in this GitHub discussion. **Disclaimer**: Content for this model card has partly been written by the 🤗 Hugging Face team, and partly copied and pasted from the original model card.