fix(perf): respect per request information

remove use_default_prompt_template options

add pretrained to list of start help docstring

fix flax generation config

improve flax and tensorflow implementation

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
This commit is contained in:
Aaron
2023-06-10 02:14:13 -04:00
parent e90d90e9a0
commit afddaed08c
17 changed files with 146 additions and 111 deletions

View File

@@ -314,15 +314,20 @@ def start_model_command(
configure_logging()
ModelEnv = openllm.utils.ModelEnv(model_name)
llm_config = openllm.AutoConfig.for_model(model_name)
docstring = f"""\
{ModelEnv.start_docstring}
\b
The available pretrained models to use with '{model_name}' are: {openllm.AutoLLM.for_model(model_name).pretrained}
"""
command_attrs: dict[str, t.Any] = {
"name": ModelEnv.model_name,
"context_settings": _context_settings or {},
"short_help": f"Start a LLMServer for '{model_name}' ('--help' for more details)",
"help": ModelEnv.start_docstring,
"help": docstring,
}
llm_config = openllm.AutoConfig.for_model(model_name)
aliases: list[str] = []
if llm_config.name_type == "dasherize":
aliases.append(llm_config.__openllm_start_name__)