サイト内検索

AI モデル 2119

• DeepSeek-V4.1-Flash-UNCENSORED-GGUF↗

  Adolphsson

  **Uncensored 552B MoE with 1M-token context, vision, and full tool/reasoning support — converted to GGUF for llama.cpp.** Built from `dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8` (permanent weight-level abliteration of `deepseek-ai/DeepSeek-V4.1-Flash`), converted to GGUF and requantized. **No guardrails: the model follows on prompts the base model refuses (verified, see Benchmarks).** > ## ✅ Update 2026-10-15 — corrected re-quants are live > > **The Q3_K_M and Q4_K_M files on the Hub have been replaced** with corrected re-quants built from the Q8_0 bridge using the corrected per-layer ramp (see below). If you downloaded Q3 or Q4 earlier, the files have changed — re-download. > > - **Q3_K_M:** now **352 GB (9 × ≤50 GB shards)** — 23 GB smaller than the previous build, identical measured quality at every benchmark we ran on both. > - **Q4_K_M:** now **426 GB (3 shards)** — routed experts are pure Q4_K as the tier name says (the previous build re-encoded the checkpoint-native MXFP4 experts into Q4_K/Q5_K, which is what the audit flagged). > - **Q2_K:** rebuilt (v3) — now pins the indexer/hyperconn layers per the recipe (the previous build left them at base precision). Same size class, files replaced on the Hub. The benchmark table below is measured on v3; the 1M NIAH tier on v3 is running. > - **Q8_0:** unchanged — still the reference bridge. > > Details: Per-group quantization & size · Benchmarks

• bert-base-arabertv02↗

  aubmindlab

  **AraBERT** is an Arabic pretrained language model based on Google's BERT architechture. AraBERT uses the same BERT-Base config. More details are available in the AraBERT Paper and in the AraBERT Meetup There are two versions of the model, AraBERTv0.1 and AraBERTv1, with the difference being that AraBERTv1 uses pre-segmented text where prefixes and suffixes were split using the Farasa Segmenter. We evaluate AraBERT models on different downstream tasks and compare them to mBERT), and other state of the art models (*To the extent of our knowledge*). The Tasks were Sentiment Analysis on 6 different datasets (HARD, ASTD-Balanced, ArsenTD-Lev, LABR), Named Entity Recognition with the ANERcorp, and Arabic Question Answering on Arabic-SQuAD and ARCD

• Kimi-K3-GGUF↗

  unsloth

  To run Kimi K3, use our llama.cpp PR fork or run in Unsloth Studio Full precision lossless = Q8 (UD-Q8_K_XL), which is 50GB bigger than Q4 (UD-Q4_K_XL). Has vision support! Kimi K3 has toggles for High and Max thinking in Unsloth Studio Read our Kimi K3 guide for analysis and instructions. Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date. It is a 2.8T-parameter model built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), with native vision capabilities and a 1-million-token context window. It is the world's first open 3T-class model, designed for frontier intelligence across long-horizon coding, knowledge work, and reasoning. - **New Architecture**: Kimi K3 is built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), and scales up MoE sparsity with a Stable LatentMoE framework that activates 16 out of 896 experts — yielding an approximate 2.5× improvement in overall scaling efficiency over Kimi K2. - **Long-Horizon Coding**: Operating with minimal human oversight, Kimi K3 sustains long engineering sessions, navigates massive repositories, and orchestrates terminal tools — from GPU kernel optimization and compiler development to vision-in-the-loop game dev, CAD, and even chip design. - **Agentic Knowledge Work**: Kimi K3 advances end-to-end knowledge work, producing deep research with interactive visualizations, widgets and dashboards, and motion design and video editing, powered by its native multimodal architecture. - **Native Multimodality & Long Context**: Kimi K3 understands text, images, and video within the same model, and supports a 1-million-token context window. - **Open Frontier Weights**: We release the full Kimi K3 model weights under the Kimi K3 License, making frontier intelligence openly available for research, deployment, and further innovation.

• Phi-4-reasoning-plus↗

  Microsoft

  > [!IMPORTANT] > To fully take advantage of the model's capabilities, inference must use `temperature=0.8`, `top_k=50`, `top_p=0.95`, and `do_sample=True`. For more complex queries, set `max_new_tokens=32768` to allow for longer chain-of-thought (CoT). *Phi-4-reasoning-plus has shown strong performance on reasoning-intensive tasks. In our experiments, we extended its maximum number of tokens to 64k, and it handled longer sequences with promising results, maintaining coherence and logical consistency over extended inputs. This makes it a compelling option to explore for tasks that require deep, multi-step reasoning or extensive context.* Given the nature of the training data, **always use** ChatML template with the **following system prompt** for inference:

• diffusiongemma-26B-A4B-it↗

  Google

  DiffusionGemma is a generative model built by Google DeepMind. Based on the 26B A4B Mixture-of-Experts (MoE) Gemma 4 architecture, DiffusionGemma generates tokens using discrete diffusion. This open-weights model is multimodal, handling text, image, and video inputs to generate text output. Built on a MoE foundation, DiffusionGemma is designed to improve generation speed (tokens per second) while remaining deployable across various hardware environments. DiffusionGemma builds upon the architectural and capability advancements of Gemma 4, introducing several core features: * **Discrete Text Diffusion** – Shifts from token-by-token autoregression to block-autoregressive multi-canvas sampling. It generates text by iteratively denoising blocks of tokens (a 'canvas') in parallel, significantly increasing decoding speed. * **Multimodal Input Processing** – Processes interleaved text, image (with variable aspect ratio and resolution support), and video inputs to generate text outputs. * **Encoder-Decoder Architecture** – Utilizes an autoregressive encoder to process and cache the prompt context, paired with a decoder that applies bidirectional attention over the generation canvas. * **Mixture-of-Experts (MoE) Efficiency** – Leverages a sparse MoE design (8 active experts out of 128 total) to provide strong reasoning capabilities while maintaining a low memory footprint suitable for local execution. * **Thinking Mode (Reasoning)** – Designed as a highly capable reasoner, with configurable thinking modes. * **Optimized for Small Batch Size Inference –** Specifically engineered for low-latency, high-speed generation on a single capable accelerator. * **Native System Prompt Support** – As with Gemma 4, it supports updating the `system` role, enabling more structured and controllable conversations.

• Gemma-4-12B-Hephaestus-GGUF↗

  thesamgodson

• Qwen-Image-2.1-Turbo-FP8↗

  unsloth

  This is an FP8 / INT8 quantized version of Qwen-Image-2.1-Turbo, the 8-step distilled checkpoint of Qwen-Image-2.1. - Each file replaces the 14.2 GB bf16 `transformer` with a 7.1 to 7.3 GB one. - Same-seed LPIPS vs the bf16 Turbo model (lower is better): 0.037 INT8-ConvRot, 0.089 INT8, 0.125 FP8. INT8-ConvRot is the recommended file. - Turbo shares its text encoder and VAE with Qwen-Image-2.1 (text encoder byte-identical, VAE identical in bf16), so the FP8 text encoder and bf16 VAE in unsloth/Qwen-Image-2.1-FP8 work with these files as is. Built from `Qwen/Qwen-Image-2.1-Turbo` at revision `d65dbc9a7e8f6b5479e33dee6030eaab2a906509` with the same recipe as unsloth/Qwen-Image-2.1-FP8: norms, modulation, timestep embeddings and (for INT8) `txt_in` stay bf16, every other linear is quantized. Scores are LPIPS (AlexNet) against the bf16 Turbo transformer at the card's settings (8 steps, CFG 1, the shipped sigma schedule, 1024x1024), 8 prompts x 2 seeds, with the same bf16 text encoder in every run. Everything here is safetensors rather than a pickle, so loading runs no arbitrary code. Needs a diffusers main build with pipeline-configured sampling sigmas (PR #14950).

• wav2vec2-large-xlsr-53-icelandic-ep30-967h↗

  language-and-voice-lab

  The "wav2vec2-large-xlsr-53-icelandic-ep30-967h" is an acoustic model suitable for Automatic Speech Recognition in Icelandic. It is the result of fine-tuning the model facebook/wav2vec2-large-xlsr-53 for 30 epochs with 967 hours of Icelandic data collected by the Language and Voice Laboratory through the platform Samrómur. The specific data that was used to fine-tune the model is the corpus Samrómur Milljón, which is the result of the automatic verification of 1 million of recordings comming from the corpus "Samromur Unverified 22.07". It has to be pointed out that this model was trained with different data than our previous model wav2vec2-large-xlsr-53-icelandic-ep10-1000h . The fine-tuning process was performed during July (2023) in the servers of the Language and Voice Laboratory (https://lvl.ru.is/) at Reykjavík University (Iceland) by Carlos Daniel Hernández Mena.

• opus-mt-en-zh↗

  Sams200

• sam3-original↗

  jesusoctavioas