Search
Sort Score
Result 10 results
Languages All
Labels All
Results 281 - 290 of 20,791 for

model

(0.13 sec)

  1. DynatempRange|Documentation

    Dynamic temperature range in Aspose.LLM for .NET — varies Temperature per step based on distribution entropy; enables dynatemp when > 0....based on how confident the model is at that step. Low-entropy...DynatempRange/2] : When entropy is low (model is confident about the next...

    docs.aspose.com/llm/net/developer-reference/par...
    more..

  2. ThreadCount|Documentation

    Thread count for mtmd (multimodal) processing in Aspose.LLM for .NET — null defers to native default; lower for CPU-constrained hosts....NThreads — base-model generation threads; independent...parameters — NThreads — base-model counterpart. PrintTimings Verbosity...

    docs.aspose.com/llm/net/developer-reference/par...
    more..

  3. Module.DetectAreasMode.COMBINE|Documentation

    How Aspose.OCR for JavaScript via C++ determines the structure of a document using the Module.DetectAreasMode.COMBINE Model....PHOTO model. This allows you to handle even...specialized models. Try one of the dedicated area detection models if...

    docs.aspose.com/ocr/javascript-cpp/areas-detect...
    more..

  4. Out of memory|Documentation

    Fix out-of-memory errors in Aspose.LLM for .NET — GPU VRAM, system RAM, KV cache growth, swap thrashing....Out-of-memory failures happen at model load, during long sessions,... or when running several models on the same host. The remedy...

    docs.aspose.com/llm/net/troubleshooting/out-of-...
    more..

  5. MaxTokens|Documentation

    Hard cap on generated tokens per assistant response in Aspose.LLM for .NET — raise for reasoning Models that emit think blocks....tasks; raise it for reasoning models (Qwen3, DeepSeek-R1) that emit...general-purpose. 2048 – 4096 — reasoning-model output (Qwen3, DeepSeek-R1)...

    docs.aspose.com/llm/net/developer-reference/par...
    more..

  6. CPU|Documentation

    Run Aspose.LLM for .NET on CPU only — AVX512, AVX2, and NoAVX variants, threading, and performance expectations....inference, but reasonable for small models (3B-7B parameters) on modern...tokens-per-second for a 7B Q4_K_M model on CPU only: CPU class Approximate...

    docs.aspose.com/llm/net/developer-reference/acc...
    more..

  7. 创建带有基本 3D 形状的场景|Documentation

    Aspose.3D for Node.js 通过 Java API 具有对基本 3D 形状的支持。所有参数化基本体在保存到任何受支持的输出文件格式时，都将自动转换为网格。...Scene from Primitive 3D Shapes Modeling is the process of pure creation... Scene (); // Create a Box model scene . getRootNode (). createChildNode...

    docs.aspose.com/3d/zh/nodejs-java/create-scene-...
    more..

  8. AnthropicAiModel.summarize method | Aspose.Word...

    Aspose.Words.AI.AnthropicAiModel.summarize method...leverages the connected AI model for content processing. summarize...method utilizes the connected AI model for processing each document...

    reference.aspose.com/words/nodejs-net/aspose.wo...
    more..

  9. FlashAttention (legacy)|Documentation

    Legacy boolean toggle for flash attention in Aspose.LLM for .NET — prefer FlashAttentionMode enum for new code.... Default null (use model default) Category Attention...explicit override; runtime / model default applies. true — request...

    docs.aspose.com/llm/net/developer-reference/par...
    more..

  10. Aspose::Words::Layout::IPageLayoutCallback inte...

    Aspose::Words::Layout::IPageLayoutCallback interface. Implement this interface if you want to have your own custom method called during build and rendering of page layout Model in C++....and rendering of page layout model. class IPageLayoutCallback :...possible to build page layout model for only a few pages at start...

    reference.aspose.com/words/cpp/aspose.words.lay...
    more..