Search FoxAI

AI Models 2119

• Yi-1.5-34B-Chat-16K↗

  01-ai

  Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples. Compared with Yi, Yi-1.5 delivers stronger performance in coding, math, reasoning, and instruction-following capability, while still maintaining excellent capabilities in language understanding, commonsense reasoning, and reading comprehension. Model | Context Length | Pre-trained Tokens | :------------: | :------------: | :------------: | | Yi-1.5 | 4K, 16K, 32K | 3.6T

• lyrics-room-final-refiner-ozan-v1-GGUF↗

  rambrogi

  The **Final Refiner** is the last Lyrics Room pass. Fine-tuned from `arbazsiddiqui/Ozan-v1-12B` (Mistral-Nemo 12B, already anti-slop). A different lineage from the Gemma seats so the last judge does not share the same bias. It de-slops the sung lyric **and** rewrites the Suno Style-box prompt in one shot. Output is strict JSON `{ "lyrics", "style" }`. The Final Refiner is the opposite seat. After the approval gate it has **full rewrite authority** in one pass:

• juniorVision_-_SmolLM2-135M-Instruct_inst-sample-240809-gguf↗

  RichardErkhov

• FLUX.2-dev-FP8↗

  unsloth

  This is an FP8 / INT8 quantized version of FLUX.2-dev. - Optimized for efficient inference with reduced memory footprint. Same-seed LPIPS vs the bf16 model (lower is better): 0.078 INT8, 0.073 FP8. `FLUX.2 [dev]` is a 32 billion parameter rectified flow transformer capable of generating, editing and combining images based on text instructions. For more information, please read our blog post. 1. State of the art in open text-to-image generation, single-reference editing and multi-reference editing. 2. No need for finetuning: character, object and style reference without additional training in one model. 4. Trained using guidance distillation, making `FLUX.2 [dev]` more efficient. 5. Open weights to drive new scientific research, and empower artists to develop innovative workflows. 6. Generated outputs can be used for personal, scientific, and commercial purposes, as described in the [FLUX \[dev\] Non-Commercial License](https://github.com/black-forest-labs/flux/blob/main/model_licenses/LICENSE-FLUX1-dev).

• cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp5-n3nc-iid16-s3↗

  agurung

  Trained and validated on the **cobalt-train ≤2/64 frontier** (canonical clean_eval prompts): 1833 train / 112 held-out val problems the base model solved on at most 2 of 64 samples under the iid_canonical@64 hardness scan. Val evals sample at temperature 1.0 (matching the clean_eval frontier eval). Reward signal: **binary code-correctness** (1.0 if the generated program passes the problem's tests, otherwise 0.0). This checkpoint is the **`main`** revision (git branch) of the repo, with the model at the repo root — load it directly, no subfolder:

• lenovo_qwen2.1↗

  Danrisi

  > l3n0v0, amateur photo, low-lit, shot on cheap mobile phone, evening, high iso, shadowed foreground, dark. A 20-year-old Eastern European-looking woman casually dressed in an oversized pink T-shirt with text "sample text sample text sample text", outdoors, her gaze directed to the side, serious expression, hold cup of coffee, her blonde hair loosely tied back and she has fringes that frames her face. minimal makeup visible. she is standing on the street near soviet-era storey buildings, trees, parked cars near. Dull, overcast lighting > l3n0v0. George Bush portrait, standing with his gaze directed to the Twin Towers (WTC before 9/11) at dusk, his face is shadowed, dark silhouettes of skyscrappers against deep blue sky, distant yellow lights scattered in background, twilight atmosphere, dark shadowy cityscape, underexposed nighttime scene, minimal ambient lighting, natural evening lighting conditions, dark foreground elements

• MobileCLIP2-S0-OpenCLIP↗

  timm

  These weights and model card are adapted from the original Apple model at https://huggingface.co/apple/MobileCLIP2-S0. This version uses canonical OpenCLIP configs and weight naming. MobileCLIP2 was introduced in MobileCLIP2: Improving Multi-Modal Reinforced Training (TMLR August 2025 Featured ), by Fartash Faghri, Pavan Kumar Anasosalu Vasu, Cem Koc, Vaishaal Shankar, Alexander T Toshev, Oncel Tuzel, Hadi Pouransari. * `MobileCLIP2-S4` matches the accuracy of SigLIP-SO400M/14 with 2x fewer parameters and surpasses DFN ViT-L/14 at 2.5x lower latency measured on iPhone12 Pro Max. * `MobileCLIP-S3/S4` are our new architectures trained on MobileCLIP’s training dataset, DataCompDR-1B (dashed lines). * Our smallest variant `MobileCLIP-S0` obtains similar zero-shot performance as OpenAI's ViT-B/16 model while being 4.8x faster and 2.8x smaller. * `MobileCLIP-S2` obtains better avg zero-shot performance than SigLIP's ViT-B/16 model while being 2.3x faster and 2.1x smaller, and trained with 3x less seen samples. * `MobileCLIP-B (LT)` attains zero-shot ImageNet performance of **77.2%** which is significantly better than recent works like DFN and SigLIP with similar architectures or even OpenAI's ViT-L/14@336.

• sam2.1-hiera-tiny-mic↗

  huggingface-mic

• gemma-3-12b-it↗

  unsloth

  Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. With instruction-tuned models, you need to use chat templates to process our inputs first. Then, you can pass it to the pipeline. These models were trained on a dataset of text data that includes a wide variety of sources. The 27B model was trained with 14 trillion tokens, the 12B model was trained with 12 trillion tokens, 4B model was trained with 4 trillion tokens and 1B with 2 trillion tokens. Here are the key components:

• yovoice-model↗

  leemysw

  This repository has GGUF model packages for yovoice that are not in the official audio.cpp model repository. Each package runs with the audio.cpp inference engine. The same files are mirrored on Hugging Face and ModelScope. You don't need to download these files by hand. yovoice downloads them from **Settings › Models** (or `yovoice models download `) and checks the size and SHA256 of each file. - 103 built-in voices: 100 Chinese voices and 3 English voices (`af_maple`, `af_sol`, `bf_vale`). No reference audio or voice cloning. - Languages: Chinese, American English, British English. Experimental. - Includes word-level Chinese pronunciation tables made with the official Misaki frontend, so inference runs without Python. - Bundled resources and licenses (copies are inside the GGUF under `licenses/`): eSpeak-ng data (GPL-3.0-or-later), Misaki (Apache-2.0), jieba (MIT), pypinyin (MIT).