全站搜索

AI 模型 2119

• Qwen3.8-27B-nvfp4full-dflash2-NInfer-v3↗

  kaushikvira

  The same bytes you know from kaushikvira/Qwen3.8-27B-nvfp4full-dflash2-NInfer (v2), migrated to the **NInfer v3 artifact container** (upstream `f76e19c0`, model/weight decoupling). Weight tensors are **bit-preserved** — this is a packaging upgrade, not a re-quantization. > ## 🔑 No engine patch needed anymore > > The v2 artifact required a *forked* NInfer engine: the `qwen3.8-27b/nvfp4full` > weights profile had to be registered in C++ (4 files: profile enum, resolver, > binder, workspace cases). **NInfer v3's loader is data-driven** — every weight > binds from the artifact's own logical bindings and per-tensor formats — so > this artifact needs **no model-support patch of any kind**. Any NInfer engine > at upstream v3 (`Neroued/ninfer` master ≥ `f76e19c0`, 2026-09-13) loads and > serves it. Our previous fork's C++ registration commits were deleted during > the v3 rebase and the model still passes the full quality gate (see below), > which is the proof: the engine path in our build *is* upstream's. > > The only fork-local piece left is one allow-list line in the *offline upgrade > tool* (to produce v3 files like this one) — not in the engine, not needed to > serve. Input must match SHA-256 `373dab08…937de1`; output must match `74d2fc17742537defa6897583caaabcc9adfc99bdfbea402ec5e8facd0d5fdfc`.

• nomic-embed-multimodal-3b↗

  nomic-ai

  `nomic-embed-multimodal-3b` is a dense state-of-the-art multimodal embedding model that excels at visual document retrieval tasks: Nomic Embed Multimodal 3B seamlessly integrates with Retrieval Augmented Generation (RAG) workflows: 1. **Direct Document Embedding**: Skip OCR and complex processing by directly embedding document page images 2. **Faster Processing**: Eliminate preprocessing steps for quicker indexing 3. **More Complete Information**: Capture both textual and visual cues in a single embedding 4. **Simple Implementation**: Use the same API for both text and images

• falcon-40b-tiny-testing↗

  BlackSamorez

• Qwen3-4b-Z-Image-Turbo-AbliteratedV1↗

  BennyDaBall

  This is the **abliterated** version of the Z-Image-Turbo text encoder. I took the **p-e-w heretic method** and hammered it through **1000 trials**, specifically targeting **BOTH** image generation refusals and those peskier general refusals. The result? - **KL Divergence:** A tiny `0.0004` (basically no lobotomy! 🧠✨) - **Refusal Rate:** Only `4/100` in my torture tests. Brought to you by the same chaotic good energy behind: - Z-Image-Engineer-V2.5 - The original Z-Image-Engineer

• muscriptor-medium↗

  cocktailpeanut

  **MuScriptor** is an open-weight model for **general-purpose, multi-instrument automatic music transcription (AMT)**: it converts a music recording (any genre, multiple simultaneous instruments) into a stream of notes played. This repository hosts the **medium** variant (≈300M parameters), the default checkpoint downloaded by the `muscriptor` library. `muscriptor-medium` balances quality and footprint. For the best transcription quality use `muscriptor-large` (≈1.3B); for the smallest/fastest option use `muscriptor-small` (≈100M). `load_model` accepts a size keyword (`"small"`/`"medium"`/`"large"`), a local `.safetensors` path, or an `hf://` / `https://` URL. Weights loaded by size keyword (or any `hf://` URL) are cached in the standard Hugging Face cache (`~/.cache/huggingface/hub`, configurable via `HF_HOME`); weights fetched from a plain `http(s)://` URL are cached under `~/.cache/muscriptor/`. Input audio can be WAV or any format `libsndfile` reads (mp3, flac, ogg, m4a, …); it is resampled to 16 kHz mono internally.

• jina-embeddings-v2-base-code↗

  jinaai

  The easiest way to starting using `jina-embeddings-v2-base-code` is to use Jina AI's Embedding API. `jina-embeddings-v2-base-code` is an multilingual **embedding model** speaks **English and 30 widely used programming languages**. Same as other jina-embeddings-v2 series, it supports **8192** sequence length. `jina-embeddings-v2-base-code` is based on a Bert architecture (JinaBert) that supports the symmetric bidirectional variant of ALiBi to allow longer sequence length. The backbone `jina-bert-v2-base-code` is pretrained on the github-code dataset. The model is further trained on Jina AI's collection of more than 150 millions of coding question answer and docstring source code pairs. These pairs were obtained from various domains and were carefully selected through a thorough cleaning process.

• Qwen3.8-27B-GGUF↗

  KikoCis

  Quants of Qwen/Qwen3.8-27B. What this repo adds over the other GGUF builds of the same model is not the files: it is a measured answer to *how far down you can quantize before an agent stops working*, and the honesty about how noisy that measurement is. The two top rungs sit above the 3.40-bpw build that scores 40/40, but they were not put through the benchmark themselves — "not measured" here means exactly that, not "assumed fine". `IQ1_M-compact` is the build that Elffuss Claw loads on WebGPU — one tab, one machine, no install and no sharding across devices — through Elffuss Engine (Apache-2.0), which reads a **standard GGUF over HTTP** by range requests and dequantises inside the shader. It is slow and the first load is several gigabytes; it answers, it does not feel instant. Note the row above: at 1.94 bpw this build is for text, not for driving tools.

• Cosmos-Predict1-7B-Text2World-Sample-AV-Multiview↗

  NVIDIA

• sbert-cased-finnish-paraphrase↗

  TurkuNLP

  Finnish Sentence BERT trained from FinBERT. A demo on retrieving the most similar sentences from a dataset of 400 million sentences can be found here. The same as in the HuggingFace documentation of the English Sentence Transformer. Either through `SentenceTransformer` or `HuggingFace Transformers`

• deepseek-vl-7b-chat↗

  deepseek-community

  This is the transformers version of Deepseek-VL-Hybrid, a foundation model for Visual Language Modeling. Deepseek-VL-Hybrid was introduced by the DeepSeek AI team. It is a vision-language model (VLM) designed to process both text and images for generating contextually relevant responses. The model leverages LLaMA as its text encoder, while SigLip is used for encoding low-resolution images and SAM (Segment Anything Model) is incorporated to handle high-resolution image encoding, enhancing the model’s ability to process fine-grained visual details. Deepseek-VL-Hybrid is a variant of Deepseek-VL that uses SAM (Segment Anything Model) to handle high-resolution image encoding. > We present DeepSeek-VL, an open-source Vision-Language (VL) Model designed for real-world vision and language understanding applications. Our approach is structured around three key dimensions: We strive to ensure our data is diverse, scalable, and extensively covers real-world scenarios including web screenshots, PDFs, OCR, charts, and knowledge-based content, aiming for a comprehensive representation of practical contexts. Further, we create a use case taxonomy from real user scenarios and construct an instruction tuning dataset accordingly. The fine-tuning with this dataset substantially improves the model's user experience in practical applications. Considering efficiency and the demands of most real-world scenarios, DeepSeek-VL incorporates a hybrid vision encoder that efficiently processes high-resolution images (1024 x 1024), while maintaining a relatively low computational overhead. This design choice ensures the model's ability to capture critical semantic and detailed information across various visual tasks. We posit that a proficient Vision-Language Model should, foremost, possess strong language abilities. To ensure the preservation of LLM capabilities during pretraining, we investigate an effective VL pretraining strategy by integrating LLM training from the beginning and carefully managing the competitive dynamics observed between vision and language modalities. The DeepSeek-VL family (both 1.3B and 7B models) showcases superior user experiences as a vision-language chatbot in r