Felipe97/llama-cpp-compiled

1from __future__ import annotations2 3from typing import Callable, Iterable, TYPE_CHECKING4 5if TYPE_CHECKING:6    from torch import Tensor7 8from .base import MmprojModel, ModelBase, gguf9 10from .llama import LlamaModel11 12 13@ModelBase.register("JanusForConditionalGeneration")14@ModelBase.example("deepseek-community/Janus-Pro-1B")15class JanusProModel(LlamaModel):16    model_arch = gguf.MODEL_ARCH.LLAMA  # reuse Llama arch17 18    @classmethod19    def filter_tensors(cls, item: tuple[str, Callable[[], Tensor]]) -> tuple[str, Callable[[], Tensor]] | None:20        name, gen = item21 22        # Skip vision, aligner, and generation tensors23        skip_prefixes = (24            'model.vision_model.',25            'model.aligner.',26            'model.vqmodel.',27            'model.generation_embeddings.',28            'model.generation_aligner.',29            'model.generation_head.',30        )31        if name.startswith(skip_prefixes):32            return None33 34        return super().filter_tensors(item)35 36 37@ModelBase.register("JanusForConditionalGeneration")38@ModelBase.example("deepseek-community/Janus-Pro-1B")39class JanusProVisionModel(MmprojModel):40    def __init__(self, *args, **kwargs):41        super().__init__(*args, **kwargs)42        assert self.hparams_vision is not None43        if "intermediate_size" not in self.hparams_vision:44            mlp_ratio = self.hparams_vision.get("mlp_ratio")45            hidden_size = self.hparams_vision.get("hidden_size")46            if mlp_ratio is not None and hidden_size is not None:47                self.hparams_vision["intermediate_size"] = int(round(hidden_size * mlp_ratio))48 49    def set_gguf_parameters(self):50        super().set_gguf_parameters()51        assert self.hparams_vision is not None52 53        self.gguf_writer.add_clip_projector_type(gguf.VisionProjectorType.JANUS_PRO)54 55        self.gguf_writer.add_vision_attention_layernorm_eps(self.hparams_vision.get("layer_norm_eps", 1e-6))56 57        hidden_act = str(self.hparams_vision.get("hidden_act", "")).lower()58        if hidden_act == "gelu":59            self.gguf_writer.add_vision_use_gelu(True)60        elif hidden_act == "silu":61            self.gguf_writer.add_vision_use_silu(True)62 63    def _map_aligner_tensor(self, data_torch: Tensor, name: str) -> Iterable[tuple[str, Tensor]]:64        """Map aligner tensors to projector format"""65        suffix = ".bias" if name.endswith(".bias") else ".weight"66 67        if name.startswith("model.aligner."):68            local_name = name[len("model.aligner."):]69        elif name.startswith("aligner."):70            local_name = name[len("aligner."):]71        else:72            raise ValueError(f"Unsupported Janus aligner prefix: {name}")73 74        if local_name.startswith("fc1."):75            mm_index = 076        elif local_name.startswith("hidden_layers."):77            parts = local_name.split(".", 2)78            if len(parts) < 3:79                raise ValueError(f"Unexpected Janus aligner tensor name: {name}")80            mm_index = int(parts[1]) + 181        else:82            raise ValueError(f"Unsupported Janus aligner tensor: {name}")83 84        tensor_name = self.format_tensor_name(gguf.MODEL_TENSOR.V_MMPROJ, mm_index, suffix=suffix)85        return [(tensor_name, data_torch)]86 87    @classmethod88    def filter_tensors(cls, item: tuple[str, Callable[[], Tensor]]) -> tuple[str, Callable[[], Tensor]] | None:89        name, gen = item90 91        # Skip generation-related components92        skip_generation_prefixes = (93            'model.vqmodel.',94            'vqmodel.',95            'model.generation_embeddings.',96            'generation_embeddings.',97            'model.generation_aligner.',98            'generation_aligner.',99            'model.generation_head.',100            'generation_head.',101        )102        if name.startswith(skip_generation_prefixes):103            return None104 105        return super().filter_tensors(item)106 107    def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:108        # Handle aligner tensors109        if name.startswith(('model.aligner.', 'aligner.')):110            yield from self._map_aligner_tensor(data_torch, name)111            return112 113        # Handle vision tensors114        if name.startswith(('model.vision_model.', 'vision_model.')):115            yield from super().modify_tensors(data_torch, name, bid)116            return117 118        return119