전체 검색

AI 모델 2119

• StartLux-Decision-v1-27B-BF16-GGUF↗

  startlux-models

  StartLux-Decision-v1-27B in BF16 (16-bit) as a GGUF file for llama.cpp. The decision server in this repository turns it into the same typed decisions, with a probability for every option, as the original model. "Same decision" is the share of the 231 public JevBench items on which the file picks the same answer as the original weights run through the `startlux_decision` package, with the same prompts, readout and temperatures. Q8_0 and Q4_K_M are llama.cpp's standard quantizations of BF16, without an importance matrix. `-ngl 99` puts every layer on the GPU (CUDA or Metal); leave it out on a CPU-only machine. llama.cpp has to be recent enough for this model (build b10454 or newer).

• krea2-anypaint↗

  yijunwang2

  **Krea 2 AnyPaint provides arbitrary-mask inpainting, outpainting, and image editing for Krea 2 Turbo.** One runtime handles internal edits, canvas extension, disconnected regions, narrow structures, and mixed masks that cross the source boundary. > **Important:** The Hugging Face auto-generated Diffusers snippet and ordinary > LoRA importers are not compatible with this functional adapter. Use the > included `example.py`, `pipeline.py`, and `anypaint.py`. White mask pixels are generated or edited. Black mask pixels are preserved. The helper also marks every pixel outside the placed source as generated, so the same input contract covers both inpainting and outpainting.

• ModernBERT-neg-sampling-PubMed↗

  EMBO

• xphonebert-base↗

  vinai

  XPhoneBERT is the first pre-trained multilingual model for phoneme representations for text-to-speech(TTS). XPhoneBERT has the same model architecture as BERT-base, trained using the RoBERTa pre-training approach on 330M phoneme-level sentences from nearly 100 languages and locales. Experimental results show that employing XPhoneBERT as an input phoneme encoder significantly boosts the performance of a strong neural TTS model in terms of naturalness and prosody and also helps produce fairly high-quality speech with limited training data. The general architecture and experimental results of XPhoneBERT can be found in our INTERSPEECH 2023 paper: @inproceedings{xphonebert, title = {{XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech}}, author = {Linh The Nguyen and Thinh Pham and Dat Quoc Nguyen}, booktitle = {Proceedings of the 24th Annual Conference of the International Speech Communication Association (INTERSPEECH)}, year = {2023}, pages = {5506--5510} }

• Qwen3.8-27B-huihui-abliterated-groupwise-int-NInfer↗

  Barding-Defense

  A **`groupwise-int`** artifact of huihui-ai/Huihui-Qwen3.8-27B-abliterated, packaged for the NInfer engine. This is the refusal-removed counterpart to the official neroued/Qwen3.8-27B-NInfer artifact, using the same weights profile. One file carries the complete container — Text, Vision, MTP, the optimized proposal head, tokenizer, chat template, generation config and media-processor resources. > **There is also an NVFP4 build > of this same checkpoint.** It is ~35 % faster on speculative decode and 1.6–2× on prefill, for 3.1 GiB > more VRAM. **Prefer NVFP4 unless VRAM is tight.** This profile's advantages are a smaller footprint > (15.9 GiB resident vs 19.0) and a dramatically simpler build — one command, no external quantizer, > no calibration data, and no patch of any kind.

• Flux-1-Krea-Dev↗

  Comfy-Org

  Original model repository: https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev All diffusion model files in this repo are licensed the same as the ones in the original repo: https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev The files in this repo are best used with ComfyUI using the Flux examples.

• cornelius↗

  HanClinto

  MobileViT-XXS corner detector trained to locate the four corners of a CCG card (Magic: The Gathering, Pokémon, etc.) in a photograph or video frame. All IoU values are quadrilateral IoU between predicted and labelled card corners. `bad` counts predictions with IoU `< 0.5`; `collapse` counts geometrically degenerate predictions where two predicted corners nearly coincide. Cornelius remains the stable, conservative default. The `fastweb-single` family is also available through the stable channel for consumers that explicitly select it; it is a smaller EfficientViT-B0 global-token SimCC detector being evaluated as a faster replacement candidate. Both models use the same 384×384 input contract and produce `corners`, compatibility `presence`, and `sharpness` outputs.

• DeepSeek-V4-Flash-Vision-Strix-Halo-GGUF↗

  otheru

  > [!WARNING] > This model is designed to run only on AMD Strix Halo (`gfx1151`) using the > Ember inference engine. > > The importance matrices are a separate matter — they are plain llama.cpp > `.dat` files and work with any quantizer. See Importance matrix. An abliterated, importance-matrix-calibrated quantization of `deepseek-ai/DeepSeek-V4-Flash-Vision-Exp` at 2.58 BPW, with its vision tower and a DSpark drafter. Same recipe as the text-only DeepSeek-V4-Flash-0731 release, which this supersedes as Ember's default download; that one is neither deprecated nor deleted. Two things are different here: images work, and the importance matrix was collected on images rather than text.

• gemma-4-12b↗

  unsloth

  Gemma 4 12B can now be run and fine-tuned in Unsloth Studio . Read our guide . See all versions of Gemma 4 (GGUF, 16-bit etc.) in our collection . Example of Gemma 4 E4B (4-bit GGUF) running in Unsloth Studio with tool-calling: > [!Note] > This model card is for the Gemma 4 12B Unified model, which is part of the Gemma 4 family of open models. Built with the same multimodal functionality as Gemma 4 E2B and E4B (text, audio, image, and video inputs), it brings native audio and vision understanding directly to local environments without the need for separate encoders. This unified approach to multimodality makes the model encoder-free, offering a deployment size that is perfect for consumer devices and streamlined local execution. Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.

• grok-oss-Apollyon-8B↗

  c4tdr0ut

  > *“We took the same unhinged spirit, packed it into a smaller frame, and let it loose. Apollyon 8B is the pocket rocket of uncensored reasoning.”* > — Team Grok OSS **Grok OSS Apollyon 8B** is the compact sibling of our 24B flagship, engineered to deliver the same raw, unaltered conversational power at a fraction of the size. Sharing the identical two‑stage fine‑tuning pipeline—Supervised Fine‑Tuning (SFT) followed by Direct Preference Optimization (DPO) on our proprietary toxicity‑enhanced preference dataset—this model brings **sharp wit, bold takes, and unflinching honesty** to the 8B class, all while maintaining remarkable coherence and factual grounding. The architecture builds upon the **Llama‑3.1‑8B‑Instruct** foundation, which was *abliterated* (i.e., had its alignment/refusal circuitry surgically removed) to serve as an ideal starting point for our unalignment objectives. Our fine‑tuning was performed using the **Unsloth** framework, which enabled memory‑efficient training with minimal performance degradation on consumer‑grade hardware.