全站搜索
AI 模型 84761
- pplx-embed-context-v1-4b↗
perplexity-ai
`pplx-embed-v1` and `pplx-embed-context-v1` are state-of-the-art text embedding models optimized for real-world, web-scale retrieval tasks. > [!IMPORTANT] > `pplx-embed-v1` and `pplx-embed-context-v1` natively produce *unnormalized* int8-quantized embeddings. Ensure that you compare them via *cosine similarity*. Many modern embedding models rely on instruction tuning, where users prepend an instruction string to the text being embedded. This can yield a 2%-3% lift on benchmarks, but it also introduces prompt-selection overhead and can make indexing pipelines brittle (small instruction changes can shift embedding space). We deliberately **avoid** this requirement: you can embed the text you want to index directly, without having to choose or maintain an instruction prefix.
- T5XXL-Unchained-GGUF↗
Phil2Sat
- Qwen3.8-KAT-AgentWorld-35B-A3B-Coder-GGUF↗
pragmaticcs
- DeepSeek-V4-Flash-Vision-Exp-GGUF↗
prometheusAIR
- Llama-3-8B-Instruct-Gradient-1048k-GGUF-smashed↗
PrunaAI
- openai-community-gpt2-GGUF-smashed↗
PrunaAI
- calme-2.3-legalkit-8b-GGUF↗
QuantFactory
- SAE-Res-Qwen3.5-9B-Base-W64K-L0_100↗
阿里巴巴 · Qwen
- Qwen3.6-35B-A3B-speculator.dspark↗
RedHatAI
- databricks_-_dbrx-instruct-gguf↗
RichardErkhov
