저장한 도구도구 추천
FOXAI SEARCH

전체 검색

AI 모델 2119

  • LightOnOCR-3-1B↗

    lightonai

    **Same architecture as LightOnOCR-2-1B, new capabilities.** LightOnOCR-3-1B keeps the architecture of **LightOn's** previous LightOnOCR-2 models, so switching requires no change, and adds the new grounding, image description and chart extraction features. LightOnOCR-3 is a new family of highly performant lightweight OCR models. Compared to the previous generation, they bring significant improvements in speed and transcription quality and introduce new visual understanding features: the models now output bounding box coordinates with labels for all visual elements of a document, short descriptions of images, and the numerical data of figures and charts. With these capabilities, they offer a ready-to-use, easier-to-maintain alternative to complex document understanding pipelines. The models come in three sizes. The 1B keeps the LightOnOCR-2-1B architecture, while the 0.8B and 4B adopt the Qwen3.5 vision-language architecture, which simplifies integration with existing tools and brings a significant speed-up. All models are released under the Apache 2.0 license for research and commercial use.

  • hyenadna-small-32k-seqlen-hf↗

    LongSafari

    Welcome! HyenaDNA is a long-range genomic foundation model pretrained on context lengths of up to **1 million tokens** at **single nucleotide resolution**. You'll see models of different sizes and sequence lengths. There are also original weights-only versions of each model in the LongSafari organization, which are designed to be loaded with the original github repo. These models have identical outputs to the models in the collection above, just different interfaces. In this brief code sample we demonstrate fine-tuning HyenaDNA on a sequence classification task. This sample uses the `medium` checkpoint, with a maximum sequence length of 160k nucleotides. Note that training will fail if you use a sequence length longer than the maximum supported length for your chosen checkpoint.

  • tomoro-colqwen3-embed-4b↗

    TomoroAI

    **TomoroAI/tomoro-colqwen3-embed-4b** is a state-of-the-art ColPali-style multimodal embedding model. It maps text queries, visual documents (images, PDFs) or short videos into aligned multi-vector embeddings. Built by merging **Qwen/Qwen3-VL-4B-Instruct** with **Qwen/Qwen3-Embedding-4B**, this model inherits robust text retrieval capabilities while preserving a full vision stack. It has been fine-tuned on a curated mixture of VDR, ViDoRe-ColPali-Training, VisRAG-Ret-Train-Synthetic-data, and VisRAG-Ret-Train-In-domain-data. It achieves SOTA or competitive performance across **ViDoRe V1-V3** (English and Multilingual) while offering a significantly reduced embedding footprint compared to other full-dim Colpali model alternatives. ColQwen3 generalizes to short videos while learning from image-text retrieval task. This minimal example samples a clip with `torchvision`, encodes queries and frames, then pools frame embeddings with a per-dimension max before MaxSim scoring.

  • Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-Uncen-IQ1-332Exp-GGUF↗

    DatKurai

    > ⚠️ **Read this first — ignore the automatic "Use this model" panel.** It suggests a `:BF16` llama.cpp/Ollama launch that does not match this release. This GGUF runs with the **Strata** engine: follow the Quick start below (stock llama.cpp / Ollama / vLLM are not tested). **Swift-1.5 Uncensored (`Uncen`)** is an abliterated (refusal-reduced) build of Swift 1.5 — the uncensored line of the Qwen3.8-Flash-Next GSQ-RCO family. This release shrinks the MoE expert pool from **512 → 332 experts/layer** so it serves on consumer hardware (a single 16 GB GPU + 32 GB RAM with the Strata engine), while keeping as much coding, agent and tool-calling capability as possible. - **About the `IQ1` name — read first.** `IQ1` here does **not** mean 1-bit tensor quantization. It labels the **effective payload class** of the pruned release — ~60.65 GB (56.49 GiB) — the same naming convention and size class as the GSQ-RCO Coder `IQ1_M` release (58.4 GB; itself a pruned build). Every tensor in this release keeps its original quantization inherited from the source; nothing was re-quantized. Equal size class is **not** quantization equivalence: this release keeps the source's mixed `IQ3_XXS` tensor bytes, while the Coder's kept experts are stored at ~3.5 bpw — read neither name as a tensor-precision tier. - **Base:** `SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF` @ `46d8cfdd` (IQ3_XXS tier) — all weights, including every kept expert, come from this uncensored source. - **Experts:** 512 → **332 per layer** (≈ 64.8% of the pool), 48 layers, 10 routed experts/token. - **Payload:** 36.47 GB + 24.18 GB = **60.65 GB** (56.49 GiB) across 2 GGUF shards; the vision projector is included. - **Verified setup (author's experience):** Windows 11 · single **RX 6800 16 GB** + **32 GB system RAM** · Strata engine with `--resident-experts` and expert caching · KV int8 · MTP speculative decoding. Production-served at 144K–192K context; 256K context was verified at runtime (a ~251.5K-token prompt was recalled correctly in testing). Other hardware will vary. - **Multilingual:** inherits Qwen3.8-Flash-Next's language coverage. Smoke-tested in **eight languages** across Latin, CJK and Cyrillic scripts — arithmetic + explanation passed in all eight; free-form writing is shown for the languages that met the bar (see `i18n-smoke/`). - **Vision:** image-text input works with the included proje

  • Nemotron-3.5-Lightning-30B-A3B-Heretic-Uncensored-Q4_K_M-GGUF↗

    mlasli

    GGUF quantization of mlasli/Nemotron-3.5-Lightning-30B-A3B-Heretic-Uncensored-BF16 — NVIDIA-Nemotron-3.5-Lightning-30B-A3B (31.6B total / 3B active) with its refusal direction removed via Heretic. **What this is for:** the same abliterated hybrid Mamba-MoE model, quantized to 24.3 GB so it runs locally via llama.cpp. Independent eval of the merged BF16 model (50 harmful-behavior prompts). The automated Zou keyword detector false-positives on words like "illegal"/"unethical" appearing inside compliant answers; manual review found 0 genuine refusals.

  • NPO-SAM-WMDP-llama3-8b-instruct-GGUF↗

    mradermacher

  • LTX_2.3_Wild_West_Style_LoRa↗

    vrgamedevgirl84

    This LoRA creates a **cinematic realistic Wild West video** look. It is a grounded frontier-western style for **text-to-video generation**, not actual frames or footage from any movies, TV shows, games, or existing franchises. The workflow used to create the sample videos can be found HERE. Just swap out the LoRA and prompt. All sample videos are **text to video**. **NOT image to video.** Characters, environments, and motion read as grounded Wild West frontier footage. Scenes feature **weathered cowboys**, **outlaws**, **sheriffs**, **ranchers**, and **settlers**, with **period-authentic western clothing**, **worn leather gear**, **cowboy hats**, **dust-covered boots**, **wooden saloons**, **frontier towns**, **desert plains**, **barns**, **stables**, and **rugged natural landscapes**. The atmosphere is **dusty**, **sunbaked**, **dramatic**, and **cinematic**, with realistic textures and strong environmental storytelling. The result feels like a scene from a modern high-end western film with immersive frontier realism and grounded human tension.

  • Qwen3.8-Flash-Next-Gyro-Coder-GGUF↗

    agentionai

    Qwen3.8-Flash-Next is a 125B mixture-of-experts model, the kind that normally needs a workstation full of GPUs. Gyro-Coder brings it to a single RTX 3090, 4090 or 7900 XTX: 19.9 GiB of GPU memory. **New: Gyro-Coder-L for 32 GB cards.** The same experts at about 3.2 bits per weight: 27.5 GiB of GPU memory, and closer to the full model than Gyro-Coder on every set we measure. On C++ it is closer than Gyro-M, which keeps all 512 experts. **Updated 2026-10-29: Gyro-Coder-L v1.2** (`Qwen3.8-Flash-Next-Gyro-Coder-L-TQ3_0.gguf`, same name and size). Thanks to a detailed community report, three experts that matter for tool calls and symbols are back in the expert set, in place of three that did less. Tool calls no longer break under sampling: across 100 `<parameter=` sites in real agent sessions, v1.0 wrote a broken tag at 4 and v1.2 at none. Roman numerals are fixed too, and KLD is unchanged on every set. v1.2 replaces both v1.0 and the v1.1 preview.

  • 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.