保存済みツールを推薦
FOXAI SEARCH

サイト内検索

AI モデル 2119

  • Ingot-VII-27B-Q2↗

    dendriteholdings

    A public mirror of a model that won on Ingot, a Bittensor subnet where miners quantize a fixed teacher model and the validator crowns the copy that stays closest to it. It is Prism ML's Ternary Bonsai 2 27B, refined: the same ternary codes, with the per-block scales and the norm weights re-tuned by the miner to bring it closer to Qwen3.8-27B. The weights are the miner's upload, byte for byte. Credit belongs to the miner, and to Prism ML for Bonsai 2.

  • Mythos-V2-9B-GGUF↗

    fableforge-ai

    > **23 official quantizations of fableforge-ai/Mythos-V2-9B** (Qwen3.5-9B — uncensored, 13.7/15 benchmark at Q4_K_M, hybrid linear-attention 256K arch). > **Imatrix note:** Low-bit `IQ1`/`IQ2`/`IQ3` quants are importance-matrix quantized (imatrix computed on 4.6 MB of general text). The final NextN/MTP block (`blk.32`) is quantized to `q8_0` in these files because it is never exercised during imatrix calibration. > **Speed (M3, Ollama):** Q4_K_M ≈ **2.8–3.5 tok/s** generation, ~45 tok/s prompt processing. Quantization > is not the bottleneck: Qwen3.5's hybrid linear-attention arch is slower per-token than dense Qwen3 in > Ollama/llama.cpp (dense 9B Q4s reach ~7 tok/s on the same hardware). Expect low-bit quants to score > below these numbers; Q4_K_M and above reproduce them faithfully.

  • doktor-LLama2-sambanovasystems-7b-GGUF↗

    mradermacher

  • japanese-stablelm-instruct-beta-7B-GGUF↗

    TheBloke

    GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. The creator of the source model has listed its license as `['llama2']`, and this quantization has therefore used that same license. As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.

  • Dolphin-X1-8B-GGUF↗

    dphn

    Dolphin X1 8B is a result of our effort to directly uncensor Llama's 3.1 8B instruct while also keeping the same abilities or improving on them with finetuning. Dolphin aims to be a general purpose model, similar to the models behind ChatGPT, Claude, Gemini. But these models present problems for businesses seeking to include AI in their products. 1) They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break. 2) They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on. 3) They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application. 4) They can see all your queries and they can potentially use that data in ways you wouldn't want. Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt. You decide the alignment. You have control of your data. Dolphin does not impose its ethics or guidelines on you. You are the one who decides the guidelines. Dolphin belongs to YOU, it is your tool, an extension of your will. Just as you are personally responsible for what you do with a knife, gun, fire, car, or the internet, you are the creator and originator of any content you generate with Dolphin.

  • Hunyuan3D-Omni↗

    腾讯

    The model was presented in the paper Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets. Recent advances in 3D-native generative models have accelerated asset creation for games, film, and design. However, most methods still rely primarily on image or text conditioning and lack fine-grained, cross-modal controls, which limits controllability and practical adoption. To address this gap, we present Hunyuan3D-Omni, a unified framework for fine-grained, controllable 3D asset generation built on Hunyuan3D 2.1. In addition to images, Hunyuan3D-Omni accepts point clouds, voxels, bounding boxes, and skeletal pose priors as conditioning signals, enabling precise control over geometry, topology, and pose. Instead of separate heads for each modality, our model unifies all signals in a single cross-modal architecture. We train with a progressive, difficulty-aware sampling strategy that selects one control modality per example and biases sampling toward harder signals (e.g., skeletal pose) while downweighting easier ones (e.g., point clouds), encouraging robust multi-modal fusion and graceful handling of missing inputs. Experiments show that these additional controls improve generation accuracy, enable geometry-aware transformations, and increase robustness for production workflows. Hunyuan3D-Omni is a unified framework for the controllable generation of 3D assets, which inherits the structure of Hunyuan3D 2.1. In contrast, Hunyuan3D-Omni constructs a unified control encoder to introduce additional control signals, including point cloud, voxel, skeleton, and bounding box.

  • stable-diffusion-2-1↗

    sd2-community

    This model card focuses on the model associated with the Stable Diffusion v2-1 model, codebase available here. This `stable-diffusion-2-1` model is fine-tuned from stable-diffusion-2 (`768-v-ema.ckpt`) with an additional 55k steps on the same dataset (with `punsafe=0.1`), and then fine-tuned for another 155k extra steps with `punsafe=0.98`. @InProceedings{Rombach_2022_CVPR, author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn}, title = {High-Resolution Image Synthesis With Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {10684-10695} }

  • AliceAI-Foundation-80B-A3B-NOESIS-BF16-GGUF↗

    AMAImedia

    ⚡ Each donation funds the next large quant. I host free GGUF or MoE quants as independent research. Local hardware: Mechrevo Kuangshi GM7AG0M — RTX 3060 Laptop 6GB GDDR6, 64GB DDR5, i7-12700H (14C/20T, 4.7GHz), Windows 11, Samsung 990 Pro. Good for imatrix and 0.6–35B-class work in RAM. 9B+ and searches need rented H200/Blackwell , typically $100 per quant. Released as part of the **NOESIS Professional Multilingual Dubbing Automation Platform** (framework: Deterministic Hybrid Control Framework for Frozen Neural Operators — DHCF-FNO). Repack (BF16 safetensors, shards ≤50 GB) and community GGUF quantizations of yandex/AliceAI-Foundation-80B-A3B-Base (`model_type: alice_ai`, 80B total / 3B active MoE with KDA layers).

  • Hyperflow-Comfyui↗

    drbaph

    ComfyUI-converted builds of HyperFlow (Video Rebirth's 8-step LoRA for MiniMax-H3, video + audio), for the **ComfyUI-Hyperflow** custom node. > **These are not the standalone LoRAs.** The files here require the custom node (they carry the time-embedder/endpoint LoRA + fixed 8-step grid the node consumes). If you want to use HyperFlow **without** the custom node, get the extracted standalone builds from drbaph/MiniMax-H3-Turbo-Lora-ComfyUI — those load with the stock `Load LoRA` node (backbone only, no two-time conditioning, output deviates from the released model). **Usage:** `Load Diffusion Model (MiniMax-H3) → ApplyHyperFlow → SamplerCustomAdvanced + euler` (feed the node's SIGMAS output). Optional sparse attention: core `Model Sparse Attention` (sol-attn: start_percent 0.25, dense_blocks "0,1", tau 1.0).

  • hubert-xlarge-ls960-ft↗

    facebook

    The extra large model fine-tuned on 960h of Librispeech on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. Authors: Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, Abdelrahman Mohamed **Abstract** Self-supervised approaches for speech representation learning are challenged by three unique problems: (1) there are multiple sound units in each input utterance, (2) there is no lexicon of input sound units during the pre-training phase, and (3) sound units have variable lengths with no explicit segmentation. To deal with these three problems, we propose the Hidden-Unit BERT (HuBERT) approach for self-supervised speech representation learning, which utilizes an offline clustering step to provide aligned target labels for a BERT-like prediction loss. A key ingredient of our approach is applying the prediction loss over the masked regions only, which forces the model to learn a combined acoustic and language model over the continuous inputs. HuBERT relies primarily on the consistency of the unsupervised clustering step rather than the intrinsic quality of the assigned cluster labels. Starting with a simple k-means teacher of 100 clusters, and using two iterations of clustering, the HuBERT model either matches or improves upon the state-of-the-art wav2vec 2.0 performance on the Librispeech (960h) and Libri-light (60,000h) benchmarks with 10min, 1h, 10h, 100h, and 960h fine-tuning subsets. Using a 1B parameter model, HuBERT shows up to 19% and 13% relative WER reduction on the more challenging dev-other and test-other evaluation subsets.