Skip to content

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

966 B
Raw Blame
from .attention import Gemma4Attention
from .config import parse_config
from .gguf import gguf_mm_config, iter_gguf_weights, parse_gguf_config, to_gguf
from .model import Gemma4ForCausalLM, Gemma4ForConditionalGeneration, Gemma4UnifiedForConditionalGeneration
from .moe import Gemma4Router
from .vision import Gemma4MultimodalEmbedder, Gemma4UnifiedVisionEmbedder, Gemma4VisionModel
from .weight import (
    nvfp4_expert_spec,
    iter_vision_weights,
    iter_weights,
    iter_weights_parallel,
)

__all__ = [
    "nvfp4_expert_spec",
    "Gemma4Attention",
    "Gemma4ForCausalLM",
    "Gemma4ForConditionalGeneration",
    "Gemma4MultimodalEmbedder",
    "Gemma4UnifiedForConditionalGeneration",
    "Gemma4UnifiedVisionEmbedder",
    "Gemma4Router",
    "Gemma4VisionModel",
    "parse_config",
    "iter_vision_weights",
    "iter_weights",
    "iter_weights_parallel",
    "gguf_mm_config",
    "parse_gguf_config",
    "iter_gguf_weights",
    "to_gguf",
]