Saved toolsSubmit a tool
FOXAI SEARCH

Search FoxAI

AI Models 2119

  • TabSTAR-v1.1-reg-20261009↗

    alana89

    TabSTAR-v2 regression checkpoint, epoch 16 of `reg50k-active-261004_233909`. Pretrained checkpoint; this file records how it was trained and how it differs from the original TabSTAR (v1). - **Task type**: regression only (separate model per task type) - **Pool**: decontaminated T4 pool `t4_tabstarv1.1_runs_decontamination`, 200,013 regression tables; 50,000 sampled per epoch (`--num_datasets 50000`, `--pool_mode active`) - **Learning rate**: 1e-4, **weight decay**: 1e-3, linear warmup over the first 10% of steps - **Epochs**: 25 planned, early-stopping patience 5 - **Batch size**: 512 global (micro-batch 32, no gradient accumulation) - **Text encoder**: `intfloat/e5-small-v2`, top 6 layers unfrozen, text batch size 1024 - **Regression head**: dual head, a scalar sub-head plus a distributional sub-head over 200 bins - **Finetunability check**: every epoch, 30 minute timeout per check; epoch 16 had the top finetunability Elo Downstream finetuning (TabArena-Lite) uses the repo defaults, none tuned per checkpoint:

  • yolov11-license-plate-detection↗

    morsetechlab

    This is a fine-tuned version of YOLOv11 (n, s, m, l, x) specialized for **License Plate Detection**, using a public dataset from Roboflow Universe: License Plate Recognition Dataset (10,125 images) The upstream Roboflow dataset (`license-plate-recognition-rxg4e`) contains **train/test contamination** — the same source images appear in both the training and test splits with only minor manual augmentation applied (see Discussion #2 for concrete examples). As a result: - **The reported metrics below are likely overestimated**, because the test set is not a true held-out evaluation. - Real-world generalization performance is expected to be lower than the numbers in the table. - Treat all evaluation figures with caution and validate the model on your own held-out data before production use.

  • bottlecapai_ThinkingCap-gemma-4-26B-A4B-it-GGUF↗

    bartowski

    **Model details:** - Parameter count: 26B (source checkpoint) - Input support: text, image and audio (with mmproj file) - details - Speculative decoding: no - imatrix: yes - details **Don't know which to choose?** Grab Q4_K_M (17.97GB) - usually a good mix of size and performance. Download instructions available here **About these sizes:** 30.9 % of this model's weights (`ffn_down_exps` (704 wide) and `ffn_down` (2112 wide)) have row widths that llama.cpp's 256-wide K and IQ block types cannot use, so each size gives them one of the 32-wide types instead (Q4_0 to Q8_0, or IQ4_NL), whatever type its name asks for, and the files above are closer together in size than usual. IQ3_M was not made: it would have come out within 0.4 % of the size of IQ4_XS, the same kind of file.

  • Qwen-Image-2.1-Turbo↗

    阿里巴巴 · Qwen

    🤖 ModelScope   |   🤗 HuggingFace   |   💻 GitHub   |   📑 Qwen-Image-2.1 Blog   |   🫨 Discord   |   💬 WeChat **Qwen-Image-2.1-Turbo** is an accelerated checkpoint of Qwen-Image-2.1 for text-to-image generation and image editing with **8 denoising steps**. It uses the same 7B visual generation architecture and loads directly with `QwenImage21Pipeline` in Diffusers. The checkpoint includes its recommended sampling schedule, so it is ready to use without manually configuring the scheduler. Generation uses CFG=1 by default, and prefix KV caching reuses the text and reference-image context across denoising steps.

  • cosyvoice3-0.5b-2512-GGUF↗

    cstr

    GGUF conversion of FunAudioLLM/Fun-CosyVoice3-0.5B-2512 for use with CrispASR (`--backend cosyvoice3-tts`). CosyVoice3 is a streaming, multilingual, zero-shot voice-cloning TTS system from Alibaba's FunAudioLLM team. The 0.5B-2512 release is Apache-2.0 licensed and supports **9 languages plus 18 Chinese dialects**. Output is 24 kHz mono. Upstream ships two talker checkpoints in one repo: `llm.pt` (pre-trained) and `llm.rl.pt` (the same architecture after reinforcement learning, tuned by the authors for speech quality, pronunciation accuracy and generation stability). Only the talker differs — **flow, HiFT, CAMPPlus, the speech tokenizer and the voice bank are shared**, so switching is just pointing `-m` at the other LLM GGUF and leaving every companion file in place:

  • pythia-14m↗

    EleutherAI

    - **Developed by:** EleutherAI - **Model type:** Transformer-based Language Model - **Language:** English - **Learn more:** Pythia's GitHub repository for training procedure, config files, and details on how to use. See paper for more evals and implementation details. - **Library:** GPT-NeoX - **License:** Apache 2.0 - **Contact:** Join the EleutherAI Discord and post in `#release-discussion`. For general correspondence: contact@eleuther.ai > **Note:** Prior to Feb 27th, 2026, a model was hosted at this URL that was trained on the deduplicated Pile. That model is now at EleutherAI/pythia-14m-deduped and this model was correctly trained on the standard Pile. We apologize for any confusion this has caused. > **Note:** Pythia-14M was trained after the original Pythia suite at the request of interpretability researchers who wanted a smaller model with the same training setup. It uses the same tokenizer, hyperparameter conventions, and checkpoint schedule as the rest of the Pythia suite. A deduplicated variant is available at `EleutherAI/pythia-14m-deduped`.

  • Qwen3.6-35B-A3B-MTP-APEX-I-MiniPlus-V2.1-Abliterated-GGUF↗

    IsValorum

    **Independently computed using dedicated cloud compute clusters, funded 100% out-of-pocket.** If you consider these releases to be of high quality and they help you in your day-to-day workflow, consider supporting on Ko-fi. Every contribution directly sustains future cloud compute hours and helps support my university studies. > > *Independently computed on private cloud clusters. If this handcrafted release saves you VRAM and runs faster on your GPU, consider fueling the community compute fund on Ko-fi.* > > Explore the new canonical V3 releases. MiniPlus prioritizes Q5-class to near-Q6 fidelity without a fixed file-size ceiling; NanoPlus targets Q4-class quality at a practical footprint. > > - **Qwen3.8 27B — MiniPlus V3** — 14.16 GB **(+13.21% improvement in WikiText-2 PPL vs GSQ-RCO IQ3_S)**. > - **Qwen3.8 27B — NanoPlus V3** — 11.35 GB **(+11.49% improvement in WikiText-2 PPL vs GSQ-RCO IQ3_S)**. > - **Swift-1.5 Qwen3.8 27B Uncensored MTP — MiniPlus V3** — 14.28 GB **(+5.70% improvement in WikiText-2 PPL vs GSQ-RCO IQ3_S)**. > - **Swift-1.5 Qwen3.8 27B Uncensored MTP — NanoPlus V3** — 11.08 GB **(+2.26% improvement in WikiText-2 PPL vs GSQ-RCO IQ3_S)**. > > Percentages compare the reported WikiText-2 PPL with GSQ-RCO IQ3_S (7.07). The linked 27B cards document the evaluation protocol and model variants. > > **Explore the APEX-I MiniPlus V2.1 Abliterated collection** > > ### EXPLORE THE ESTABLISHED 35B MoE MINIPLUS LINEUP > These are complementary APEX-I-MiniPlus V2.1 releases, not alternate downloads of the same model. Each receives the same tensor-by-tensor approach, integrated MTP where supported, and a design suitable for full or partial system-RAM inference. Choose the model whose native strengths best fit the work you want to do: > > - **Qwen3.6-35B-A3B MTP APEX-I-MiniPlus-V2.1** — a versatile frontier MoE for broad reasoning, multilingual work, agents, tool use, and multimodal tasks. > - **Best for:** General reasoning, agent workflows, tool calling, and flexible multimodal use. > - **Ornith 1.5 APEX-I-MiniPlus-V2.1** — a software-engineering-focused MoE designed for repository-scale coding and autonomous engineering agents. > - **Best for:** Repository-scale development, multi-file code changes, and software-engineering agents. > - **Tiel Coder APEX-I-MiniPlus-V2.1** — a specialist coding MoE tuned for agentic programming, iterative tool use, and

  • kitten-tts-2↗

    KittenML

    A 1.7B speech language model with in-context voice cloning. It reads text and writes S3 codec tokens, which a vocoder turns into 24 kHz audio. Everything the model needs is in this repository, so no Hugging Face login is required. `m.available_voices` lists all 115. Bella, Jasper, Luna, Bruno, Rosie, Hugo, Kiki and Leo are the same speakers as in KittenTTS 0.8, so existing code keeps working.

  • tmr-ai-text-detector↗

    Oxidane

    A robust AI-generated text detector based on RoBERTa-base, trained with Focal Loss and Self-Hard-Negative iterative mining on the RAID dataset. TMR (Target Mining RoBERTa) is designed to detect AI-generated text with high accuracy while maintaining low false positive rates. The model uses: Trained on the RAID dataset (ACL 2024) with Self-Hard-Negative mining: iteratively identifying human samples misclassified as AI, then retraining with these hard examples.

  • cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp5-n3nc-groot16-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: