전체 검색
AI 모델 84761
- HY-World-2.0↗
腾讯
- InterimLabs-Huihui-Qwen3.5-2B-abliterated-GGUF-Q4_K_M↗
interimlabs
- DeepSeek-V4-Pro-Qwen3.5-9B-MTP-GGUF↗
Jackrong
🔬 DeepSeek-V4-Pro Distillation 🧠 9B Parameters 📐 ~250K Math & STEM Samples ⚡ MTP & NVFP4 Evaluated 💡 What is DeepSeek-V4-Pro-Qwen3.5-9B? DeepSeek-V4-Pro-Qwen3.5-9B is a reasoning-focused fine-tune of Qwen3.5-9B , distilled from responses generated by DeepSeek-V4-Pro in Max Effect mode . The release concentrates its supervised signal on mathematics and STEM problem solving while preserving the efficiency and practical deployability of the 9B parameter class. 🧩 Structured Reasoning Learns rigorous problem decomposition and multi-step solution patterns from a strong teacher.
- MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-4bit↗
Jackrong
- DeepSeek-V4.1-Flash-EXL3-2.8bpw↗
jayleaton
- jina-embeddings-v5-omni-small-mlx↗
jinaai
- Qwen3-4B-Thinking-2507-DASHQ-Q2-GGUF↗
jkim96
- kanana-2-30b-a3b-thinking-2601↗
kakaocorp
- retro-toon-70s-lora-minimax-h3↗
KennethFal
- kotoba-whisper-v2.0-faster↗
kotoba-tech
This repository contains the conversion of kotoba-tech/kotoba-whisper-v2.0 to the CTranslate2 model format. We measure the inference speed of different kotoba-whisper-v2.0 implementations with four different Japanese speech audio on MacBook Pro with the following spec: - Apple M2 Pro - 32GB - 14-inch, 2023 - OS Sonoma Version 14.4.1 (23E224) Also, currently whisper.cpp and faster-whisper support the sequential long-form decoding, and only Huggingface pipeline supports the chunked long-form decoding, which we empirically found better than the sequnential long-form decoding.
