전체 검색

AI 모델 84759

• paligemma2-3b-pt-448↗

  Google

• t5-efficient-xl-nl16↗

  Google

• Phi-3-medium-128k-instruct-imatrix-GGUF↗

  hermes42

• tiny-random-starcoder2↗

  hyper-accel

• roberta-eus-euscrawl-base-cased↗

  ixa-ehu

• Qwopus3.6-27B-v2-MTP-GGUF↗

  Jackrong

  💡 What is Qwopus3.6-27B-v2-MTP? 🪐 Qwopus3.6-27B-v2-MTP is a speed-oriented reasoning release built on top of Qwen3.6-27B . It keeps the Qwopus line's focus on reconstructed reasoning traces, coding discipline, DevOps procedures, and mathematical derivations, while adding Multi-Token Prediction for faster generation. The goal is simple: preserve the depth and structure of a 27B reasoning model while making real interactive use noticeably faster. ⚡ MTP Decoding Auxiliary future-token prediction improves throughput on long reasoning, code, math, and strict-format prompts. 🧩 Structured Reasoning Inherits the Qwopus training recipe built around reconstructed step-by-step reasoning trajectories. 🧪 GB10 Tested Validated on a 30-question local benchmark across Logic, Coding, DevOps, Math, and Edge tasks. 🚀 Practical Speed Designed for workflows where strong answers matter, but waiting several extra minutes per task does not. Qwen3.6-27B provides the dense 27B foundation for this release. Qwopus3.6-27B-v2-MTP focuses on preserving the base model's broad reasoning capability while tuning the output style toward stepwise analysis, tool-aware execution, and practical engineering answers. Attribute Specifications & Details 🧠 Architecture Dense Transformer / 27 Billion Parameters 🎯 Focus Domains Agentic Coding, DevOps, structured logic, mathematics, and strict-format output ⚡ MTP Objective Improve generation throughput through multi-token speculative prediction while retaining final-answer quality.

• wav2vec2-large-xls-r-300m-Urdu↗

  kingabzpro

  A fine-tuned XLS-R 300M CTC model for Urdu automatic speech recognition. It transcribes **16 kHz mono** audio and includes an optional 5-gram KenLM decoder. **Best reported result:** 39.89% WER / 16.70% CER with KenLM decoding on the Urdu Common Voice 8.0 test set. See the Kaggle evaluation notebook for a reproducible example. > **Note:** After installing the packages in a notebook environment, restart the kernel before running the inference code.

• RetroPlanner↗

  KU-AGI

• lafa-0.5B↗

  lafa-hf

• net-gpt-4-0613↗

  langchain