전체 검색

AI 모델 2119

• Srijith-rkr_-_deepseek_base_1e-3_NO_cot_only_failed_samples_100_ckpt-gguf↗

  RichardErkhov

• meiki.text.detect.v0↗

  rtr46

  --- **Official GitHub Repository:** meikiocr This model is a core component of the `meikiocr` pipeline. For the full implementation, command-line script, and documentation, please see the official GitHub repository. meiki.text.detect.v0.1 is an update to meiki.text.detect.v0 (see below): - meiki.text.detect.v0.1 is a new state-of-the-art, open weight text detection model for video games beating text detection models like PaddleOCR - while it is still based on D-FINE detector, it uses mobilenet v4 small as backbone instead of hgnet v2 - v0.1 comes in 2 variants: v0.1.960x544 and v0.1.320x192. unlike v0 both v0.1 variants share the same architecture, but are trained on different resolutions - v0.1 models increase focus on video game text detection and are limited to 64 detected boxes, increasing efficency for this use case (making them less suitable for manga text detection out of the box) - v0.1.960x544 and v0.1.320x192 have better accuracy and lower latency than small.v0 and tiny.v0 respectively

• Ternary-Bonsai-2-27B-Abliterated-GGUF↗

  Hikari07jp

  > **🚧 PREVIEW RELEASE (v0.1) — feedback wanted.** > This is an early preview of a quant-native abliteration of the Bonsai 2 pack. The > numbers below are from my own small harness, so I would rather have the community > poke at it than call it finished. Please open a **Discussion** in the Community tab > with anything you find — good or bad. **Status: preview (v0.1) — not a final release.** A refusal-reduced build of **`prism-ml/Ternary-Bonsai-2-27B-gguf`** (PQ2_0, 2.13 bpw, 7.21 GB). The pack is edited **in its own deployed quantization format**: there is no BF16 dequantization anywhere in the pipeline and no re-quantization. The official pack's stored 2-bit codes were updated directly, in place, so the shipped artifact *is* the edited pack: same geometry, same size, same kernel path, no runtime hook, no adapter. A full-precision refusal-free reference of the same base family was used only to define *what* to change; that change was then written onto the pack's existing quantization lattice with an **unbiased** code-rounding schedule, so that the *expected* weight movement equals the intended edit even though each individual code can only move in whole lattice steps. The edit was amplitude-swept and selected on measured behaviour.

• moonshine-tiny↗

  litert-community

  Moonshine Tiny is a 27M-parameter encoder-decoder speech-recognition model from Moonshine AI (formerly Useful Sensors), introduced in Moonshine: Speech Recognition for Live Transcription and Voice Commands. It transcribes English speech and is designed for fast on-device inference. This repository packages the model for LiteRT: a float32 model, an int8 model (dynamic-range-quantized decoder with a float32 encoder), and ahead-of-time compiled variants for a range of MediaTek and Qualcomm SoCs so the model can run on the device NPU. For an on-device Android demo that runs Moonshine (and other ASR models) with hardware acceleration, see the LiteRT speech recognition sample.

• sd-vae-ft-ema↗

  Stability AI

  These weights are intended to be used with the 🧨 diffusers library. If you are looking for the model to use with the original CompVis Stable Diffusion codebase, come here. You can integrate this fine-tuned VAE decoder to your existing `diffusers` workflows, by including a `vae` argument to the `StableDiffusionPipeline` We publish two kl-f8 autoencoder versions, finetuned from the original kl-f8 autoencoder on a 1:1 ratio of LAION-Aesthetics and LAION-Humans, an unreleased subset containing only SFW images of humans. The intent was to fine-tune on the Stable Diffusion training set (the autoencoder was originally trained on OpenImages) but also enrich the dataset with images of humans to improve the reconstruction of faces. The first, _ft-EMA_, was resumed from the original checkpoint, trained for 313198 steps and uses EMA weights. It uses the same loss configuration as the original checkpoint (L1 + LPIPS). The second, _ft-MSE_, was resumed from _ft-EMA_ and uses EMA weights and was trained for another 280k steps using a different loss, with more emphasis on MSE reconstruction (MSE + 0.1 * LPIPS). It produces somewhat ``smoother'' outputs. The batch size for both versions was 192 (16 A100s, batch size 12 per GPU). To keep compatibility with existing models, only the decoder part was finetuned; the checkpoints can be used as a drop-in replacement for the existing autoencoder.

• sam2_hiera_large.fb_r1024↗

  timm

• ddpm-cifar10-32-dot.in.name↗

  akasharidas

  *We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding. On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46 and a state-of-the-art FID score of 3.17. On 256x256 LSUN, we obtain sample quality similar to ProgressiveGAN.* for inference. Note that while the *ddpm* scheduler yields the highest quality, it also takes the longest. For a good trade-off between quality and inference speed you might want to consider the *ddim* or *pndm* schedulers instead.

• EleutherAI_gpt-neo-125M-stablediffionprompts↗

  cedpsam

• LTX_2.3_Fantasy_Anime_Style_LoRa↗

  vrgamedevgirl84

  This LoRA creates a **cinematic fantasy anime cel-shaded illustration** look. **The dataset used to create this LoRA did not use any IP.** It is a **grounded high-fantasy anime illustration style**, not actual frames or images from any movies, TV shows, or existing franchises. The workflow used to create the sample videos can be found HERE. All sample videos are **text-to-video**, not image-to-video. Characters and environments appear as stylized fantasy anime illustrations. Scenes feature **hand-drawn linework**, **painted shading**, **expressive faces**, **stylized fantasy costumes**, **magical creatures**, **vivid atmospheric effects**, and **cinematic composition**. The result feels like a scene from a modern high-end fantasy anime film with immersive worlds and story-driven character moments.

• bert_uncased_L-4_H-256_A-4↗

  Google

  This is the set of 24 BERT models referenced in Well-Read Students Learn Better: On the Importance of Pre-training Compact Models (English only, uncased, trained with WordPiece masking). We have shown that the standard BERT recipe (including model architecture and training objective) is effective on a wide range of model sizes, beyond BERT-Base and BERT-Large. The smaller BERT models are intended for environments with restricted computational resources. They can be fine-tuned in the same manner as the original BERT models. However, they are most effective in the context of knowledge distillation, where the fine-tuning labels are produced by a larger and more accurate teacher. Our goal is to enable research in institutions with fewer computational resources and encourage the community to seek directions of innovation alternative to increasing model capacity.