Search FoxAI

AI Models 84997

• Nanbeige4.3-33B-DFlash2↗

  kapitsaprime

• kling-video-motion-control↗

  快手 · 可灵

  快手可灵提供官方授权API，安全稳定。 同步更新支持官方所有模型、计费方式也与官方一致 对接仅需将官方 API 域名、令牌更换成本站即可

• verbatim-rag-modern-bert-v2↗

  KRLabsOrg

• CASA-Qwen2_5-VL-3B↗

  kyutai

• granite-20b-code-instruct-IMat-GGUF↗

  legraphista

  Original Model: ibm-granite/granite-20b-code-instruct Original dtype: `BF16` (`bfloat16`) Quantized by: llama.cpp b3649 IMatrix dataset: here If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run: According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).

• zephyr-7b-gemma-sft↗

  li-muyang

• Phi-4-reasoning-GGUF↗

  lmstudio-community

• cocolm-large↗

  Microsoft

• Dayhoff-170M-UR90-HL-24000↗

  Microsoft

• tapex-base-finetuned-wikisql↗

  Microsoft

  TAPEX was proposed in TAPEX: Table Pre-training via Learning a Neural SQL Executor by Qian Liu, Bei Chen, Jiaqi Guo, Morteza Ziyadi, Zeqi Lin, Weizhu Chen, Jian-Guang Lou. The original repo can be found here. TAPEX (**Ta**ble **P**re-training via **Ex**ecution) is a conceptually simple and empirically powerful pre-training approach to empower existing models with *table reasoning* skills. TAPEX realizes table pre-training by learning a neural SQL executor over a synthetic corpus, which is obtained by automatically synthesizing executable SQL queries. TAPEX is based on the BART architecture, the transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder.