Skip to content

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

798 B
Raw Blame
from .config import VisionConfig, parse_config, parse_vision_config
from .gguf import gguf_mm_config, iter_gguf_weights, parse_gguf_config, to_gguf
from .model import (
    Qwen3VLForConditionalGeneration,
    Qwen3VLMoeForConditionalGeneration,
    deepstack_add,
)
from .vision import Qwen3VLVisionModel
from .weight import iter_vision_weights, iter_weights, iter_weights_parallel, rename_vl_prefix

__all__ = [
    "Qwen3VLForConditionalGeneration",
    "Qwen3VLMoeForConditionalGeneration",
    "Qwen3VLVisionModel",
    "VisionConfig",
    "deepstack_add",
    "gguf_mm_config",
    "iter_gguf_weights",
    "iter_vision_weights",
    "iter_weights",
    "iter_weights_parallel",
    "parse_config",
    "parse_gguf_config",
    "parse_vision_config",
    "rename_vl_prefix",
    "to_gguf",
]