サイト内検索

AI モデル 84759

• paligemma-3b-pt-896-jax↗

  Google

• t5-efficient-base-nl40↗

  Google

• MOSS-TTS-Realtime-Persian-lora↗

  hamidfzm

• ci-random-pygwin-4x7b↗

  hyper-accel

• all-miniLM-L6-v2-UKPGA-6k-finetune↗

  i-dot-ai

• Phi-3.5-MoE-0.8B-A0.2B↗

  inference-optimization

• internlm2_5-1_8b-chat-gguf↗

  internlm

• svd-safety-llama3_8b_instruct_up_basis_coeff_jbbresp13_finetuned_keep_0p50↗

  Jeesup

• Huihui-Qwen3.8-27B-abliterated-GGUF↗

  k1lliiviie

  This is an uncensored version of Qwen/Qwen3.8-27B 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. The newly added **Huihui-Qwen3.8-27B-abliterated-Underdog-Saluki** series come from ConwayResearch/Underdog-Saluki-27B-1.0 and ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF. Only layers **22 to 52 (0-based indexing)** have been ablated, while the other layers remain unablated. It may come with a small disclaimer warning. Due to ConwayResearch/Underdog-Saluki-27B-1.0 not providing an imatrix file, we will attempt to perform ablation by mixing the GGUF weights of Swift-1.5 and ConwayResearch/Underdog-Saluki-27B-1.0.

• kb-whisper-base↗

  KBLab