全站搜索

AI 模型 85003

• granite-8b-code-base-4k-GGUF↗

  ibm-granite

• K2-Horizon-7B-FP8↗

  IFM

• Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF↗

  Jackrong

  🔥 **Update (April 5):** I’ve released the complete training notebook, codebase, and a comprehensive PDF guide to help beginners and enthusiasts understand and reproduce this model's fine-tuning process. > ❤️ Special thanks to the **Unsloth** open-source library and @KyleHessling1 for their support. 👉 **GitHub Repository: Jackrong-llm-finetuning-guide** Visit the repo to dive into the codebase and reproduce the results locally or on Colab.

• supergemma4-26b-uncensored-mlx-4bit-v2↗

  Jiunsong

  Do not pass `--chat-template /path/to/chat_template.jinja` as a literal path string on launch paths that expect the template body. That can corrupt responses.

• Qwen3.8-27B-Uncensored-JoyFox-Aggressive↗

  joyfox

  This release focuses on reducing false refusals and unnecessary policy-style preambles while retaining the native architecture and general capabilities of `Qwen/Qwen3.8-27B`. The final checkpoint preserves the official tokenizer, chat template, and configuration, the complete vision stack and multimodal projector, native Multi-Token Prediction (MTP) weights. Vision tensors remain unchanged and are verified separately. MTP tensors remain unchanged and are verified separately. “Aggressive” describes the strength of the low-overrefusal behavior. The intended response style is direct and substantive for benign, fictional, analytical, educational, authorized, privacy-respecting, or otherwise legitimate requests, including requests whose wording is sensitive or ambiguous.

• pancancer-lymphocytes-inceptionv4.tcga↗

  kaczmarj

• Qwen3.8-Flash-Next-Uncensored-ROCmFP4-FAST-imatrix-GGUF↗

  kingjones777

• task-1-Qwen-Qwen1.5-1.8B↗

  l8623001

• DeepSeek-Coder-V2-Lite-Instruct-IMat-GGUF↗

  legraphista

• Meta-Llama-3.1-8B-Instruct-IMat-GGUF↗

  legraphista