model: add support for qwen3vl series (#16780)
* support qwen3vl series. Co-authored-by: Thireus ☠ <Thireus@users.noreply.github.com> Co-authored-by: yairpatch <yairpatch@users.noreply.github.com> Co-authored-by: LETS-BEE <LETS-BEE@users.noreply.github.com> * bugfix: fix the arch check for qwen3vl-moe. * use build_ffn * optimize deepstack structure * optimize deepstack feature saving * Revert "optimize deepstack feature saving" for temporal fix This reverts commit f321b9fdf13e59527408152e73b1071e19a87e71. * code clean * use fused qkv in clip * clean up / rm is_deepstack_layers for simplification * add test model * move test model to "big" section * fix imrope check * remove trailing whitespace * fix rope fail * metal : add imrope support * add imrope support for sycl * vulkan: add imrope w/o check * fix vulkan * webgpu: add imrope w/o check * Update gguf-py/gguf/tensor_mapping.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * fix tensor mapping --------- Co-authored-by: Thireus ☠ <Thireus@users.noreply.github.com> Co-authored-by: yairpatch <yairpatch@users.noreply.github.com> Co-authored-by: LETS-BEE <LETS-BEE@users.noreply.github.com> Co-authored-by: Xuan Son Nguyen <son@huggingface.co> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
@@ -860,6 +860,9 @@ class GGUFWriter:
|
||||
def add_pooling_type(self, value: PoolingType) -> None:
|
||||
self.add_uint32(Keys.LLM.POOLING_TYPE.format(arch=self.arch), value.value)
|
||||
|
||||
def add_num_deepstack_layers(self, count: int) -> None:
|
||||
self.add_uint32(Keys.LLM.NUM_DEEPSTACK_LAYERS.format(arch=self.arch), count)
|
||||
|
||||
def add_rope_dimension_count(self, count: int) -> None:
|
||||
self.add_uint32(Keys.Rope.DIMENSION_COUNT.format(arch=self.arch), count)
|
||||
|
||||
@@ -1071,6 +1074,9 @@ class GGUFWriter:
|
||||
def add_vision_n_wa_pattern(self, value: int) -> None:
|
||||
self.add_uint32(Keys.ClipVision.N_WA_PATTERN, value)
|
||||
|
||||
def add_vision_is_deepstack_layers(self, layers: Sequence[bool]) -> None:
|
||||
self.add_array(Keys.ClipVision.IS_DEEPSTACK_LAYERS, layers)
|
||||
|
||||
# audio models
|
||||
|
||||
def add_audio_projection_dim(self, value: int) -> None:
|
||||
|
||||
Reference in New Issue
Block a user