Skip to content

FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.

362 B
Raw Blame
from .config import parse_config
from .gguf import iter_gguf_weights, parse_gguf_config, to_gguf
from .model import MiniMaxM2ForCausalLM
from .weight import iter_weights, nvfp4_expert_spec

__all__ = [
    "nvfp4_expert_spec",
    "MiniMaxM2ForCausalLM",
    "parse_config",
    "iter_weights",
    "iter_gguf_weights",
    "parse_gguf_config",
    "to_gguf",
]