全站搜索
AI 模型 84761
- pix2struct-widget-captioning-base↗
Google
- Hy-MT2-1.8B-1.25Bit-GGUF↗
腾讯
🖥️ Official Website | 💬 GitHub | 🪡 AngelSlim | 📚 Hy-MT2 Report Hy-MT2-1.8B-1.25 Bit-GGUF produced by AngelSlim, For more detailed information, please refer to [[AngelSlim]](https://github.com/Tencent/AngelSlim). Hy-MT2 is a family of “fast-thinking” multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B, and 30B-A3B (MoE), all of which support translation among 33 languages and effectively follow translation instructions in multiple languages. For on-device deployment, AngelSlim 1.25-bit extreme quantization reduces the storage requirement of the 1.8B model to only 440 MB and improves inference speed by 1.5x. Multi-dimensional evaluations show that Hy-MT2 delivers outstanding performance across general, real-world business, domain-specific, and instruction-following translation tasks. The 7B and 30B-A3B models outperform open-source models such as DeepSeek-V4-Pro and Kimi K2.6 in fast-thinking mode, while the lightweight 1.8B model also surpasses mainstream commercial APIs from providers such as Microsoft and Doubao overall.
- Infinity-Parser-7B↗
infly
- Tinyllama-616M-Cinder↗
Josephgflowers
- blu-1.6b-8.4btok-rlvr↗
kave-23
- Underdog-Saluki-27B-1.0-MTP-Abliterated-GGUF↗
Kujira
Same as the MTP release: stock llama.cpp with MTP drafting (`--spec-type draft-mtp`). - Recommended sampling with thinking on: `--temp 1.0 --top-p 0.95 --top-k 20 --presence-penalty 1.1` (Qwen3.8's own thinking-mode values plus a light presence penalty). At temperature 0.6 with presence penalty 1.5, long agent sessions sometimes got stuck repeating whole paragraphs in the thinking; see "Sampling" below for the comparison. - 12 GB cards: 40K context fits (11.4 GB with a 22K-token prompt). 64K starts at 11.85 GB and grows about 0.45 GB with long prompts, spills out of VRAM and slows down sharply. RTX 3080 12 GB, WSL2, llama.cpp (PrismML fork `prism-b10754`). Refusal = the reply contains a refusal phrase. Harmful prompts: the 104-prompt test split of a public harmful-behaviors set.
- llama-3-sonar-large-32k-online↗
Meta
- calme-2.2-llama3-70b-GGUF↗
MaziyarPanahi
MaziyarPanahi/calme-2.2-llama3-70b-GGUF contains GGUF format model files for MaziyarPanahi/calme-2.2-llama3-70b. IMPORTANT: There is no need to merge the splits. By now, most libraries support automatically loading the splits by simply pointing to the first one. GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
- Experiment24Experiment28-7B-GGUF↗
MaziyarPanahi
- Mixtral-8x22B-Instruct-v0.1-GGUF↗
MaziyarPanahi
