Search FoxAI
AI Models 84761
- Starling-LM-7B-beta-ExPO↗
chujiezheng
The extrapolated (ExPO) model based on `Nexusflow/Starling-LM-7B-beta` and `openchat/openchat-3.5-0106`, as in the "Weak-to-Strong Extrapolation Expedites Alignment" paper. Specifically, we obtain this model by extrapolating **(alpha = 0.5)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference. Evaluation results on the **AlpacaEval 2.0** benchmark (you can find the evaluation outputs on the official GitHub repo):
- Underdog-Bark-3.0↗
ConwayResearch
- Swift-Qwen3.8-27B-FP8↗
d0xin
- surya-ocr-2↗
datalab-to
- Accuracy - scores 83.3% on olmOCR-bench (top under 3B params) - Speed - throughput of 5 pages/s on an RTX 5090 - Multilingual - scores 87.2% on an internal benchmark set of 91 languages (more here) - Layout analysis (table, image, header, etc.) with reading order - Table recognition (rows + columns) It works on a range of documents (see usage and benchmarks). Our managed platform runs both Surya, and variants of our highest accuracy model, Chandra.
- dots.llm1.base↗
dots-studio
- HMNSFW-AIO-Sex-LoRA↗
f23gg
- maskformer-swin-small-ade↗
facebook
- mms-tts-ikk↗
facebook
- mms-tts-sus↗
facebook
- Sulphur-2-base-GGUF↗
fairy322
The following quantization tiers are provided to accommodate different hardware capabilities and VRAM constraints.
