Search FoxAI

AI Models 85003

• siglip2-so400m-patch16-384-jax↗

  Google

• Gemma-4-26B-A4B-it-JANG_4M-GGUF↗

  HentaiP

• Huihui-Qwen3.8-Flash-Next-abliterated-MTP-GGUF↗

  htdohk

  This is an uncensored version of Qwen/Qwen3.8-Flash-Next created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. Strata has byte-level and SHA256 verification for the Unsloth series. The simplest method is to modify the verify_sha256 function in the setup.py file so that it returns immediately, then no verification is needed.

• llama-30b↗

  huggyllama

• Hy-MT2-7B-GGUF↗

  腾讯

  🖥️  Official Website   |   💬  GitHub   |   🪡  AngelSlim   |   📚  Hy-MT2 Report Hy-MT2 is a family of “fast-thinking” multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B, and 30B-A3B (MoE), all of which support translation among 33 languages and effectively follow translation instructions in multiple languages. For on-device deployment, AngelSlim 1.25-bit extreme quantization reduces the storage requirement of the 1.8B model to only 440 MB and improves inference speed by 1.5x. Multi-dimensional evaluations show that Hy-MT2 delivers outstanding performance across general, real-world business, domain-specific, and instruction-following translation tasks. The 7B and 30B-A3B models outperform open-source models such as DeepSeek-V4-Pro and Kimi K2.6 in fast-thinking mode, while the lightweight 1.8B model also surpasses mainstream commercial APIs from providers such as Microsoft and Doubao overall. In this release, we also open-source IFMTBench, a benchmark for evaluating translation instruction-following capabilities.

• Qwen3.5-2B-multiharness-RL-GGUF↗

  igorktech

• gemma-4-12b-constraintkit-GGUF↗

  jajmangold

• jina-embedding-s-en-v1↗

  jinaai

• tf-xlm-r-ner-40-lang↗

  jplu

• bella-bartender-9b-yi-GGUF↗

  juiceb0xc0de