smart_chat_template

Automatically detects the model type and applies the appropriate chat template.
For Gemma models, uses the Gemma-specific format. For other models, 
falls back to the standard apply_chat_template function.

Provides R bindings to the 'llama.cpp' library for running large language models.
The package uses a lightweight architecture where the C++ backend library is downloaded
at runtime rather than bundled with the package.
Package features include text generation, reproducible generation, and parallel inference.

Yaosheng Xu

localLLM

Running Local LLMs with 'llama.cpp' Backend

Eddie Yang

smart_chat_template function

<dl><dt>model</dt>
<dd>A model object created with model_load</dd>
<dt>messages</dt>
<dd>A list of message objects</dd>
<dt>template</dt>
<dd>Custom template (passed to apply_chat_template if not Gemma)</dd>
<dt>add_assistant</dt>
<dd>Whether to add assistant turn prefix</dd></dl>

Arguments

Smart Chat Template Application — smart_chat_template

<dl>

<dt>model</dt>
<dd>A model object created with model_load</dd>


<dt>messages</dt>
<dd>A list of message objects</dd>


<dt>template</dt>
<dd>Custom template (passed to apply_chat_template if not Gemma)</dd>


<dt>add_assistant</dt>
<dd>Whether to add assistant turn prefix</dd>

</dl>

smart_chat_template: Smart Chat Template Application

Description

Usage

Value

Arguments