全站搜索

AI 模型 85003

• Qwen2D-VAE↗

  Anzhc

  A modification of Qwen-Image-VAE to remove temporal dimension, collapsing it from 3D to 2D. Primarily meant for caching latents for training, but also can be used in ComfyUI to save a second ever so often. Because you don't need temporal dimension for Image models (unless you're doing research related to temporally consistent gens on them). Collapsing it to 2D does not alter output, while reducing required VRAM 3x, and speeding it up 2.5x.

• Mistral-7B-Instruct-v0.3-Jbliterated↗

  ApolloRaines

• gpt-fr-cased-small↗

  asi

• EVE-7B-HD-v2.0↗

  BAAI

• Gryphe_Tiamat-24B-Magistral-GGUF↗

  bartowski

• MiniMaxAI_MiniMax-M2.7-GGUF↗

  bartowski

  If running with CUDA on a model that has `Q4_K` or `Q5_K` for `61.blk.ffn_down_exps` you should compile with the following flag: to avoid `NaN` activations. This is most likely an issue in `llama.cpp` itself and will hopefully be resolved, but in the meantime this fixes the issue. You can check in the info on huggingface which models are affected, but it seems to be `Q5_K_S`, `Q4_K_S`, `Q3_K_XL`, `Q3_K_L`, `Q3_K_M`, `IQ3_M`, `IQ3_XS`, and `IQ3_XXS`

• bert-base-arabic-camelbert-mix-did-nadi↗

  CAMeL-Lab

• firered-aed-l-v2↗

  chameleon-ai

• flint-oQ4e-fp16↗

  chimpanzeetaxidriver

• Qwen3-4B-RPG-Roleplay-V2↗

  Chun121

  **A new version trained with GRPO for more consistent, high-quality, and aligned character roleplaying.** > **Welcome to V2!** I'm Chun (@chun121), and this is the next evolution of the Qwen3-4B Roleplay model. This version moves beyond standard fine-tuning and leverages **GRPO (Generative Responsive Preference Optimization)** to align the model's behavior with the core principles of great roleplaying. Character Consistency High-Quality Dialogue Intent Understanding Structured Format