전체 검색

AI 모델 2119

• Nemotron-3.5-Embed-1B-BF16↗

  NVIDIA

  **Nemotron-3.5-Embed-1B-BF16** is a versatile embedding model developed by NVIDIA for multimodal and multilingual question-answering retrieval. The model can embed a document page in the form of an image, text, or combined image–text input. Documents can be retrieved given a user query in text form. The model supports page images containing text, tables, charts, and infographics. For text retrieval, the model was evaluated across 34 languages: English, Arabic, Assamese, Bengali, Bulgarian, Chinese, Danish, Dutch, Finnish, French, German, Hindi, Hinglish, Indonesian, Italian, Japanese, Korean, Malay, Marathi, Nepali, Norwegian, Persian, Portuguese, Romanian, Russian, Spanish, Swahili, Swedish, Tamil, Telugu, Thai, Ukrainian, Urdu, and Vietnamese. For image retrieval, it was evaluated across 18 languages: Arabic, Bengali, Chinese, English, Persian, Finnish, French, German, Hindi, Indonesian, Japanese, Korean, Russian, Spanish, Swahili, Telugu, Thai, and Yoruba. The model may support additional languages beyond these evaluation sets. Among models of comparable size, Nemotron-3.5-Embed-1B-BF16 achieves state-of-the-art results across multiple multilingual and multimodal retrieval benchmarks. Read more details in our Blog Post. The **Nemotron-3.5-Embed-1B-BF16** is suitable for users who want to build a multimodal question-and-answer application over a large corpus, leveraging the latest dense retrieval technology. The input of the model is a text or a document image, and the output is a fixed-size embedding vector. The embedding model is a bi-encoder that supports context in textual format (e.g. the query or the OCR text of a page or a section of a document) or the image of a document page. Typically, the embedding model is used first to embed (vectorize) the whole corpus (document images or text chunks), and embeddings are stored in a vector database associated to its raw content (image or text). Then at inference time, the embedding model is used to embed the query. The model generates dense vector embeddings from text or image inputs, enabling multimodal retrieval, semantic search, and (agentic) RAG workflows.

• Cosmos-Predict1-7B-Video2World-Sample-AV-Single2MultiView↗

  NVIDIA

• Qwen3.8-27B-NVIDIA-NVFP4-NInferV3↗

  wallawalla47

  **A single-file NInfer V3 (`.ninfer`) artifact of nvidia/Qwen3.8-27B-NVFP4, built for an NVIDIA RTX 5090 (sm_120a), for Infernix (recommended) and NInfer. No conversion step at load time: point `infernix-serve` (or `ninfer-serve`) at the `.ninfer` file and run.** This repository is the NInfer form of the NVIDIA checkpoint above: the Model Optimizer mixed NVFP4/FP8 weights are carried over **bit-exactly** for every transformer linear except the language-model head, and two speculative-decoding components (DFlash2 draft model, indexed proposal head) are added so the artifact runs with the engines' fastest decode paths. **Recommended engine: Infernix**, my engine grown from NInfer, which replaces my earlier ninfer-custom fork. In an agentic coding replay on the 27B it served 90 % of prompt tokens from its prefix cache and reached the first token in about half NInfer's average time, and it prefills long prompts 1.3-1.5× faster, at the same quality (benchmarks, measured on NInfer's official 27B artifact). It also runs Qwen3.8-Flash-Next. The artifact still works with NInfer itself and with ninfer-custom.

• mms-tts-div-finetuned-md-f01↗

  alakxender

  This is a fine-tuned VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) model for Divehi speech synthesis. The model produces female voice audio from Thaana-scripted Divehi text. Fine-tuned from Meta’s MMS-TTS architecture using a curated dataset of synthetic Divehi speech. - **Model**: `alakxender/mms-tts-div-finetuned-md-f01` - **Evaluated Samples**: 3 - **Avg Estimated MOS (UTMOS)**: `2.349` - **Artifacts**: - 🎵 Audio: `outputs/audio/` - 📊 Spectrograms: `outputs/spectrograms/` - 📄 Report: `outputs/report.txt` - 📈 MOS Scores: `outputs/mos_scores.txt`

• wav2vec2-base-vi-vlsp2020↗

  nguyenvulebinh

  Our models use wav2vec2 architecture, pre-trained on 13k hours of Vietnamese youtube audio (un-label data) and fine-tuned on 250 hours labeled of VLSP ASR dataset on 16kHz sampled speech audio. You can find more description here The ASR model parameters are made available for non-commercial use only, under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license. You can find details at: https://creativecommons.org/licenses/by-nc/4.0/legalcode

• DeepSeek-V4-Flash-0731-reap-150b-gguf↗

  puwaer

  GGUF builds of puwaer/DeepSeek-V4-Flash-0731-reap-150b for llama.cpp — 132 routed experts per layer (down from the base model's 256) via router-weighted expert activation **pruning** (REAP). See that repo's card for the compression recipe and full benchmark discussion; this one covers what is specific to the GGUF files: what each one is, how it was quantized, and how to serve it. Unlike the 200b checkpoints, no `IQ1_M` rung is published for this size — the 132-expert checkpoint's baseline fits inside a single 96 GB GPU, so this ladder was only carried down to `Q2_K`. **`MXFP4_MOE` is not a quantization, it is the baseline.** DeepSeek ships this model's routed experts already in MXFP4 (`expert_dtype: fp4`); llama.cpp's converter repacks those values into ggml's MXFP4 block layout without changing a single one (`conversion/deepseek.py::_pack_mxfp4_blocks`, 17 bytes per 32 values either way). So this file is numerically identical to the safetensors checkpoint linked above — same weights, different container.

• resnet18.a1_in1k↗

  timm

  This model features: * ReLU activations * single layer 7x7 convolution with pooling * 1x1 convolution shortcut downsample Recipe details: * ResNet Strikes Back `A1` recipe * LAMB optimizer with BCE loss * Cosine LR schedule with warmup - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 11.7 - GMACs: 1.8 - Activations (M): 2.5 - Image size: train = 224 x 224, test = 288 x 288 - **Papers:** - ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476 - Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385 - **Original:** https://github.com/huggingface/pytorch-image-models

• security-8b↗

  bebrws

  An 8B cybersecurity agent (offense + defense) fine-tuned from `Qwen/Qwen3-8B` on **2197 verified agentic + Q&A traces**, distilled from GLM-5.2 (round 4) and Kimi K3/K2.6 (rounds 1–3). Trained to operate an autonomous security harness — plan, run bash, read observations, write files, finish — not just answer security questions. Pipeline per iteration: failure analysis on eval traces → parameterized, decontaminated seed factory → teacher best-of-3 rejection-sampled agentic transcripts (judged + artifact-checked) → full-FT SFT → multi-run attack/defend eval → next round. Run-to-run variance is significant at temperature 0.7; single-run scores are not meaningful for this suite. Known v4 gap: `atk-sqli` — the model prefers to start the staged vulnerable app and fuzz it over HTTP instead of reading the offline artifacts (trace-verified behavioral prior, targeted in round 5).

• stable-diffusion-v1-5↗

  botp

  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 blog. The **Stable-Diffusion-v1-5** checkpoint was initialized with the weights of the Stable-Diffusion-v1-2 checkpoint and subsequently fine-tuned on 595k steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10% dropping of the text-conditioning to improve classifier-free guidance sampling. You can use this both with the 🧨Diffusers library and the RunwayML GitHub repository.

• humanizer↗

  jialinyyzz

  **A 12B model that rewrites AI-written drafts (emails, essays, reports, forum posts; English and Chinese) so they read like a person wrote them.** It is trained to keep every number, unit, date, name and quote and to add nothing, and it runs locally. **Quick start:** get the app for **Mac (Apple silicon)** or **Windows**, open it and paste a draft; it works offline. Without the app: llama.cpp and other runtimes, or AGENTS.md for coding agents. Drafts from the held-out evaluation set. For each we generated 8 samples with the Q8_0 file (llama.cpp, the app's settings) and picked the one that reads best among those the fact judge passed; it is shown unedited, and all 8 samples are on GitHub. These are picks: across the whole set the judge flagged 44 of the 420 English rewrites, 135 problems in all, 125 of them a single word or phrase. Read the result before you send it, especially numbers, dates and names. Results over the whole set are below.