jinja, chat: add --reasoning-preserve flag (#25105)
* jinja, chat: add --reasoning-preserve flag * correct help message
This commit is contained in:
@@ -3296,6 +3296,20 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
||||
params.sampling.reasoning_budget_message = value;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_THINK_BUDGET_MESSAGE"));
|
||||
add_opt(common_arg(
|
||||
{"--reasoning-preserve"},
|
||||
{"--no-reasoning-preserve"},
|
||||
"preserve reasoning trace in the full history, not just the last assistant message (default: template default)\n"
|
||||
"compatible with certain templates having 'supports_preserve_reasoning' capability\n"
|
||||
"example: https://docs.z.ai/guides/capabilities/thinking-mode#preserved-thinking",
|
||||
[](common_params & params, bool value) {
|
||||
if (value) {
|
||||
params.default_template_kwargs["preserve_reasoning"] = "true";
|
||||
} else {
|
||||
params.default_template_kwargs["preserve_reasoning"] = "false";
|
||||
}
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_REASONING_PRESERVE"));
|
||||
add_opt(common_arg(
|
||||
{"--chat-template"}, "JINJA_TEMPLATE",
|
||||
string_format(
|
||||
|
||||
Reference in New Issue
Block a user