Skip to content

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

740 B
Raw Blame
from .config import VisionConfig, parse_config, parse_vision_config
from .gguf import gguf_mm_config, iter_gguf_weights, iter_mmproj_weights, parse_gguf_config, to_gguf
from .model import MiniMaxM3ForCausalLM, MiniMaxM3ForConditionalGeneration
from .vision import MiniMaxM3VisionModel
from .weight import (
    nvfp4_expert_spec,
    iter_vision_weights,
    iter_weights,
)

__all__ = [
    "nvfp4_expert_spec",
    "MiniMaxM3ForCausalLM",
    "MiniMaxM3ForConditionalGeneration",
    "MiniMaxM3VisionModel",
    "VisionConfig",
    "parse_config",
    "parse_vision_config",
    "iter_vision_weights",
    "iter_weights",
    "gguf_mm_config",
    "iter_gguf_weights",
    "iter_mmproj_weights",
    "parse_gguf_config",
    "to_gguf",
]