Structs§
- Chat
Template Options - Model
Chat Template - Prompt
Function Call - Prompt
Message - Common prompt-message shape used by both CLI
runand OpenAIserve. - Prompt
Tool Call - Tool-call shape exposed to model chat templates.
Enums§
- Model
Reasoning Protocol - Model-provided chat template, usually from GGUF
tokenizer.chat_templateor HuggingFacetokenizer_config.json.
Functions§
- render_
chat_ prompt - Render OpenAI-style chat messages into the prompt string the model was trained on.
- render_
chat_ prompt_ with_ model_ template - render_
chat_ prompt_ with_ model_ template_ options - render_
chat_ prompt_ with_ tools - render_
chat_ prompt_ with_ tools_ and_ model_ template - render_
prompt_ messages - Render common chat messages into the prompt string the model was trained on. Prefer a model-provided chat template when available; otherwise use a centralized legacy fallback for model families ferrum already supports.
- render_
prompt_ messages_ with_ options