io.helidon.integrations.langchain4j.providers.jlama.JlamaStreamingChatModelConfig
Description
Configuration for LangChain4j model JlamaStreamingChatModel
Configuration options
| Key | Type | Default | Description |
|---|---|---|---|
thread-count | Integer | Generated from dev.langchain4j.model.jlama.JlamaStreamingChatModel.JlamaStreamingChatModelBuilder#threadCount(java.lang.Integer) | |
model-cache-path | Path | Generated from dev.langchain4j.model.jlama.JlamaStreamingChatModel.JlamaStreamingChatModelBuilder#modelCachePath(java.nio.file.Path) | |
quantize-model-at-runtime | Boolean | Generated from dev.langchain4j.model.jlama.JlamaStreamingChatModel.JlamaStreamingChatModelBuilder#quantizeModelAtRuntime(java.lang.Boolean) | |
temperature | Float | Generated from dev.langchain4j.model.jlama.JlamaStreamingChatModel.JlamaStreamingChatModelBuilder#temperature(java.lang.Float) | |
working-quantized-type | DType | Generated from dev.langchain4j.model.jlama.JlamaStreamingChatModel.JlamaStreamingChatModelBuilder#workingQuantizedType(com.github.tjake.jlama.safetensors.DType) | |
max-tokens | Integer | Generated from dev.langchain4j.model.jlama.JlamaStreamingChatModel.JlamaStreamingChatModelBuilder#maxTokens(java.lang.Integer) | |
model-name | String | Configure the model name | |
working-directory | Path | Generated from dev.langchain4j.model.jlama.JlamaStreamingChatModel.JlamaStreamingChatModelBuilder#workingDirectory(java.nio.file.Path) | |
enabled | Boolean | true | If set to false, JlamaStreamingChatModel will not be available even if configured |
auth-token | String | Generated from dev.langchain4j.model.jlama.JlamaStreamingChatModel.JlamaStreamingChatModelBuilder#authToken(java.lang.String) |
See the manifest for all available types.