Saved toolsSubmit a tool
FOXAI SEARCH

Search FoxAI

AI Models 2119

  • Qwen3.8-27B-SmoothQuant-W8A8-INT8↗

    Freaksterz

    **v3 (`main`, 2026-09-03):** mean full-vocab KLD vs BF16 **0.00556** — lower than the official `Qwen/Qwen3.8-27B-FP8` on the same harness (0.00584) — and the stock **DFlash2 drafter works unchanged** (acceptance length 4.34, identical to a W8A16 target). No residual-stream rotation. 288 of 400 Linear modules run INT8×INT8 on Ampere tensor cores; prefill is 1.42× a W8A16 checkpoint of the same model. Previous revisions stay available: `v2-rotated` (KLD 0.01098, rotation-based; **breaks DFlash2**, MTP only) and `v1-smoothquant-rtn` (0.01414, DFlash2-compatible). If you are here because DFlash2 gave 0% acceptance on v2: `main` fixes it. Teacher-forced full-vocab KLD, BF16 reference captured offline (transformers), candidates served through vLLM (so INT8 *activation* rounding is included). 240 × 512-token WikiText-2 windows = 122,640 positions, top-K 512 with reported tail bound. "Floor-free" is the paired estimator that removes the truncation floor (see `eval/` in the repo).

  • open-vakgyata↗

    onecxi

    **Model Overview:** open-vakgyata is an open-source language identification model capable of detecting and classifying indian languages from speech inputs. **Supported Languages:** | Language | Code | |----------------------|-------| | English (India) | en-IN | | Hindi | hi-IN | | Odia | or-IN | | Bengali | bn-IN | | Tamil | ta-IN | | Telugu | te-IN | | Kannada | kn-IN | | Malayalam | ml-IN | | Marathi | mr-IN | | Gujarati | gu-IN | **Specification** - Supported Sampling Rate: 16000 - Recomonded Audio Format: 16kHz, 16bit PCM

  • InternVL3-78B↗

    OpenGVLab

    We introduce InternVL3, an advanced multimodal large language model (MLLM) series that demonstrates superior overall performance. Compared to InternVL 2.5, InternVL3 exhibits superior multimodal perception and reasoning capabilities, while further extending its multimodal capabilities to encompass tool usage, GUI agents, industrial image analysis, 3D vision perception, and more. Additionally, we compare InternVL3 with Qwen2.5 Chat models, whose corresponding pre-trained base models are employed as the initialization of the langauge component in InternVL3. Benefitting from Native Multimodal Pre-Training, the InternVL3 series achieves even better overall text performance than the Qwen2.5 series. As shown in the following figure, InternVL3 retains the same model architecture as InternVL 2.5 and its predecessors, InternVL 1.5 and 2.0, following the "ViT-MLP-LLM" paradigm. In this new version, we integrate a newly incrementally pre-trained InternViT with various pre-trained LLMs, including InternLM 3 and Qwen 2.5, using a randomly initialized MLP projector. As in the previous version, we applied a pixel unshuffle operation, reducing the number of visual tokens to one-quarter of the original. Besides, we adopted a similar dynamic resolution strategy as InternVL 1.5, dividing images into tiles of 448×448 pixels. The key difference, starting from InternVL 2.0, is that we additionally introduced support for multi-image and video data.

  • PP-OCRv6_medium_det_onnx↗

    PaddlePaddle

    PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks **🔥 Official Website** **📝 Technical Report** PP-OCRv6 is a lightweight OCR system that combines architectural innovation with data-centric optimization. It redesigns the backbone, detection neck, and recognition neck around a unified MetaFormer-style building block with structural reparameterization. Three model tiers (medium, small, tiny) share the same block primitives, covering deployment scenarios from server to edge.

  • mms-tts-ind↗

    facebook

    This model is part of Facebook's Massively Multilingual Speech project, aiming to provide speech technology across a diverse range of languages. You can find more details about the supported languages and their ISO 639-3 codes in the MMS Language Coverage Overview, and see all MMS-TTS checkpoints on the Hugging Face Hub: facebook/mms-tts. VITS (**V**ariational **I**nference with adversarial learning for end-to-end **T**ext-to-**S**peech) is an end-to-end speech synthesis model that predicts a speech waveform conditional on an input text sequence. It is a conditional variational autoencoder (VAE) comprised of a posterior encoder, decoder, and conditional prior. A set of spectrogram-based acoustic features are predicted by the flow-based module, which is formed of a Transformer-based text encoder and multiple coupling layers. The spectrogram is decoded using a stack of transposed convolutional layers, much in the same style as the HiFi-GAN vocoder. Motivated by the one-to-many nature of the TTS problem, where the same text input can be spoken in multiple ways, the model also includes a stochastic duration predictor, which allows the model to synthesise speech with different rhythms from the same input text.

  • StartLux-Decision-v1-35B-A3B↗

    startlux-models

    StartLux-Decision-v1-35B-A3B answers typed questions about a state: pick one of several options, yes or no, or a rating on a scale. The state can be text, JSON or images, up to 262,144 tokens (256K). Every question comes back with a probability for each option. Requests and responses use the TypeSafe `/v1/systemone` format, so clients written for Jev work unchanged. It is a mixture of experts: about 35B parameters, of which about 3B are active for each token. It answers in half the time of StartLux-Decision-v1-27B, has the highest JevBench and Intern-Decision numbers of the family, and is 2.3 points below the 27B on Decision Index 0.2.1. JevBench public counts the correct answers on the 231 public items in the Intern-Decision bundle; Intern avg is the average accuracy over its seven suites; DI is the Decision Index under both editions, the public board's values for the other systems. A blank cell means the number is not published. StartLux-Decision latencies are for one H200, with the three questions answered in one forward pass. ¹ Intern-Decision's own measurement on an RTX 4090. ² The server time the TypeSafe API gateway reports for the same request, mean of 100, network left out as in ours; Intern-Decision reports 109.7 ms end to end.

  • TabSTAR-v1.1-cls-20261011↗

    alana89

    TabSTAR-v2 classification checkpoint, epoch 17 of `cls50k-active-261004_233909`. Pretrained checkpoint; this file records how it was trained and how it differs from the original TabSTAR (v1). - **Task type**: classification only (separate model per task type) - **Pool**: decontaminated T4 pool `t4_tabstarv1.1_runs_decontamination`, 200,142 classification 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 - **Finetunability check**: every epoch, 30 minute timeout per check; epoch 17 is among the top finetunability Elo epochs Downstream finetuning (TabArena-Lite) uses the repo defaults, none tuned per checkpoint:

  • Depth-Anything-V2-Base-hf↗

    depth-anything

    Depth Anything V2 is trained from 595K synthetic labeled images and 62M+ real unlabeled images, providing the most capable monocular depth estimation (MDE) model with the following features: - more fine-grained details than Depth Anything V1 - more robust than Depth Anything V1 and SD-based models (e.g., Marigold, Geowizard) - more efficient (10x faster) and more lightweight than SD-based models - impressive fine-tuned performance with our pre-trained models Depth Anything V2 was introduced in the paper of the same name by Lihe Yang et al. It uses the same architecture as the original Depth Anything release, but uses synthetic data and a larger capacity teacher model to achieve much finer and robust depth predictions. The original Depth Anything model was introduced in the paper Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data by Lihe Yang et al., and was first released in this repository. Depth Anything V2 leverages the DPT architecture with a DINOv2 backbone.

  • pythia-1b↗

    EleutherAI

    The *Pythia Scaling Suite* is a collection of models developed to facilitate interpretability research (see paper). It contains two sets of eight models of sizes 70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B, and 12B. For each size, there are two models: one trained on the Pile, and one trained on the Pile after the dataset has been globally deduplicated. All 8 model sizes are trained on the exact same data, in the exact same order. We also provide 154 intermediate checkpoints per model, hosted on Hugging Face as branches. The Pythia model suite was deliberately designed to promote scientific research on large language models, especially interpretability research. Despite not centering downstream performance as a design goal, we find the models match or exceed the performance of similar and same-sized models, such as those in the OPT and GPT-Neo suites. Previously, we released an early version of the Pythia suite to the public. However, we decided to retrain the model suite to address a few hyperparameter discrepancies. This model card lists the changes ; see appendix B in the Pythia paper for further discussion. We found no difference in benchmark performance between the two Pythia versions. The old models are still available, but we suggest the retrained suite if you are just starting to use Pythia. **This is the current release.**

  • d1-3B↗

    LiquidAI

    d1-3B is a 3B parameter **decision model** built on LFM2.5-VL-3B. You give it a state (text, JSON, images, or a mix) and a set of questions. It returns calibrated, typed answers in **one forward pass with zero output tokens**. - **Best decision model under 10B on the Decision Index 0.2.1**: 48.57, ahead of every 4B and 9B model and of Decider 35B-A3B (47.11). - **Multimodal**: images and text in the same state. It scores 74.1 on 11 public image benchmarks (LFM2.5-VL-3B: 73.9). - **Fast**: 8 ms a decision on an NVIDIA RTX 4090, 9 ms on an AMD MI325X, 30 ms on an Apple M5 Pro. Find more information about open d1 in our blog post.