Search FoxAI

AI Models 2119

• stable-diffusion-v1-4↗

  CompVis

  Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input. For more information about how Stable Diffusion functions, please have a look at 🤗's Stable Diffusion with 🧨Diffusers blog. The **Stable-Diffusion-v1-4** checkpoint was initialized with the weights of the Stable-Diffusion-v1-2 checkpoint and subsequently fine-tuned on 225k steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10% dropping of the text-conditioning to improve classifier-free guidance sampling. This weights here are intended to be used with the 🧨 Diffusers library. If you are looking for the weights to be loaded into the CompVis Stable Diffusion codebase, come here

• TerraMind-1.0-base↗

  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.

• Samsung_Qwen2512↗

  Danrisi

• PolDense-400M↗

  OPI-PIB

  PolDense is a family of Polish embedding models optimized for dense retrieval. The models are built on top of the ettin-encoders, which use the ModernBERT architecture, and are designed to provide high-quality text representations for Polish search, retrieval, and RAG applications. The family consists of six models, ranging from 17M to 1B parameters. This makes it possible to choose between lightweight, low-latency deployments and larger models aimed at maximum retrieval quality. PolDense models were trained in a three-stage pipeline with two knowledge distillation stages and one fine-tuning stage. The main teacher embedding model was BGE-Multilingual-Gemma2, while the final retrieval fine-tuning stage used relevance scores produced by BGE-Reranker-v2.5-Gemma2-Lightweight. 1. The first stage adapted the original English ettin-encoder models to Polish using multilingual knowledge distillation. This stage follows the approach introduced in Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. The core idea is to use a strong teacher model to define a shared semantic embedding space. For each parallel sentence pair, the teacher encodes the source-language sentence, and the student is trained to produce a similar embedding for the translated sentence. In practice, this teaches the student to map Polish and English texts with the same meaning to nearby locations in the vector space, while preserving the retrieval-oriented structure learned by the teacher. In this stage, BGE-Multilingual-Gemma2 was used as the teacher model. Training was performed on a Polish-English parallel corpus containing approximately 20 million text pairs. Each model was trained for 5 epochs with a batch size of 64.

• samantha-1.1-llama-7b-i1-GGUF↗

  mradermacher

• opensearch-neural-sparse-encoding-doc-v3-distill↗

  opensearch-project

  The model should be selected considering search relevance, model inference and retrieval efficiency(FLOPS). We benchmark models' performance on a subset of BEIR benchmark: TrecCovid,NFCorpus,NQ,HotpotQA,FiQA,ArguAna,Touche,DBPedia,SCIDOCS,FEVER,Climate FEVER,SciFact,Quora. Overall, the v3 series of models have better search relevance, efficiency and inference speed than the v1 and v2 series. The specific advantages and disadvantages may vary across different datasets. - **Paper**: Exploring $\ell_0$ Sparsification for Inference-free Sparse Retrievers - **Codes**: opensearch-sparse-model-tuning-sample

• eomt-dinov3-coco-panoptic-large-640↗

  tue-mps

  This is the **large** variant of the EoMT-DINOv3 model trained for **panoptic segmentation** on COCO at **640×640** resolution. **EoMT (Encoder-only Mask Transformer)** is a Vision Transformer (ViT) architecture designed for high-quality and efficient image segmentation. It was introduced in the CVPR 2025 highlight paper: **Your ViT is Secretly an Image Segmentation Model** > **Key Insight**: Given sufficient scale and pretraining, a plain ViT along with a few additional parameters can perform segmentation without the need for task-specific decoders or pixel fusion modules. The same model backbone supports semantic, instance, and panoptic segmentation with different post-processing.

• Qwen3.8-27B-Unleashed-GGUF↗

  outsourc-e

  > ### ✅ All 9 tiers verified and live (2026-08-21) > > `UD-IQ1_M` and `UD-IQ2_S` were briefly published broken, then withdrawn, and are now > **rebuilt, load-tested, and back**. If you downloaded either before 2026-08-21 22:00 UTC, > re-download. No other tier was ever affected. > > **If you are quantizing this model yourself, this is the part worth reading.** Upstream > builds low-bit tiers with a *different architecture*, not just different bit widths: > > | | Q3_K_XL and above | IQ1_M / IQ2_S | > |---|---|---| > | tensors | 506 | 498 | > | highest block | 64 (MTP head at `q6_k`) | 63 (MTP pruned) | > | `block_count` | 65 | **64** | > | `nextn_predict_layers` | 1 | **0** | > > Their imatrix has 496 entries because it matches that pruned topology. Quantizing a > 65-block f16 against it fails with > `Missing importance matrix for tensor blk.64.attn_k.weight`. > > `--prune-layers 64` alone is **not** enough — it removes the tensors but leaves the model > declaring an MTP head, so loading dies on `blk.63.nextn.eh_proj.weight not found`: a > structurally valid file containing an unloadable model. You also have to rewrite the > metadata: > > > > Every file here is now gated on exit code → magic bytes → **an actual load test** before > upload. Header checks alone let two broken builds through; only loading the model catches it. Most uncensored GGUFs are uniform quants — every layer gets the same treatment. These use a **per-tensor type map**, so sensitive tensors keep precision while tolerant ones compress hard. The result: a **Q3 that outperforms a Q4 3.3 GB larger**, with full 250k-token retrieval. > **Provenance, stated plainly.** The per-tensor quant map was **extracted from > unsloth/Qwen3.8-27B-GGUF** > (Unsloth Dynamic 3.0) by reading the > tensor-type table from their published files, then applied to > JonathanColetti/Qwen3.8-27B-Uncensored > weights with that repo's imatrix. **The recipe is Unsloth's work, not ours** — we did not > independently derive it. All upstream projects are Apache 2.0. See Credits.

• hubert-base-ls960↗

  facebook

  The base model pretrained 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. Authors: Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, Abdelrahman Mohamed

• Qwen3.8-27B-VAL-APEX-I-MiniPlus-V3-GGUF↗

  IsValorum

  If you consider these releases to be of high quality and they help you in your day-to-day workflow, consider supporting on Ko-fi. Every contribution directly sustains future cloud compute hours and helps support my university studies. Official **VAL-APEX-I MiniPlus V3** quantization of **Qwen/Qwen3.8-27B**. This edition quantizes the original Qwen checkpoint without applying Huihui abliteration or EfficientThink fine-tuning. **Integrated Multi-Token Prediction (MTP):** This GGUF includes one MTP block (`blk.64.*`, 15 tensors) in the same file as the main language model. Its eight matrices use `Q4_0` ×6, `Q4_1` ×1 and `Q6_K` ×1; its seven normalization tensors remain `F32`. MTP speculative decoding depends on support and configuration in the inference backend.