mirror of
https://github.com/ggerganov/llama.cpp
synced 2026-03-20 06:00:59 +01:00
a61c8bc3bf
* Add Gemma3nVisionModel - MobileNetV5 vision encoder convertor to convert_hf_to_gguf.py. Add gemma3n to vision projectors in gguf-py/gguf/constants.py. * Add mobilenetv5 impl * Fix comments, remove unused vars * Fix permute and remove transpose of projection weights * Fix comments, remove debugging prints from hf_to_gguf * 1. Hard-code image_mean = 0 and image_std = 1 2. Use available tensor mapping logic 3. Remove redundant chat template replacement of soft tokens placeholder with media placeholder * 1. Move mobilenetv5 helpers declarations to `clip_graph_mobilenetv5` struct and definitions to mobilenetv5.cpp 2.Remove unused `clip_is_gemma3n` func declarations and definitions 3. Remove redundant `rescale_image_u8_to_f32` func and use `normalize_image_u8_to_f32` with zero mean and unit std 4. Calculate n_patches using image_size / patch_size * Remove obsolete comments * - convert_hf_to_gguf.py & constants.py & tensor_mapping.py: Use explicit mapping: Custom map for double indexed blocks and tensor_mapping.py for rest - convert_hf_to_gguf.py: Unsqueeze Stem Bias and Layer scale tensors to correct shape while converting to gguf - mobilenetv5.cpp: Remove explicit reshaping of Stem Bias and Layer scale which are now handled while converting to gguf, replace fprintf with LOG_* - clip.cpp: Remove unused embedding and hard_emb_norm tensor loading * - Rename tensors to v.conv..., v.blk..., v.msfa... to better align with already existing terminology * Fix stem conv bias name * Remove explicit handling of bias term for stem conv * - Change order of addition in "project_per_layer_inputs" to support broadcasting of vision inp_per_layer - Simplify the vision embeddings path of "get_per_layer_inputs" to output [n_embd_altup, n_layer, 1], broadcastable * clean up conversion script * fix code style * also preserve audio tensors * trailing space * split arch A and V * rm unused gemma3 func * fix alignment --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
112 lines
3.5 KiB
C
112 lines
3.5 KiB
C
#pragma once
|
|
|
|
#include "../clip-graph.h"
|
|
|
|
/*
|
|
* IMPORTANT: The mtmd module does NOT accept pull requests that are fully or predominantly AI-generated.
|
|
* We encourage human contributors to ensure the quality and reliability of the codebase.
|
|
*/
|
|
|
|
struct clip_graph_siglip : clip_graph {
|
|
clip_graph_siglip(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_pixtral : clip_graph {
|
|
clip_graph_pixtral(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_qwen2vl : clip_graph {
|
|
clip_graph_qwen2vl(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_qwen3vl : clip_graph {
|
|
clip_graph_qwen3vl(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_youtuvl : clip_graph {
|
|
clip_graph_youtuvl(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_minicpmv : clip_graph {
|
|
clip_graph_minicpmv(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_internvl : clip_graph {
|
|
clip_graph_internvl(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_llama4 : clip_graph {
|
|
clip_graph_llama4(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_kimivl : clip_graph {
|
|
clip_graph_kimivl(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_cogvlm : clip_graph {
|
|
clip_graph_cogvlm(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_llava : clip_graph {
|
|
clip_graph_llava(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_whisper_enc : clip_graph {
|
|
clip_graph_whisper_enc(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_conformer : clip_graph {
|
|
clip_graph_conformer(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_glm4v : clip_graph {
|
|
clip_graph_glm4v(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_mobilenetv5 : clip_graph {
|
|
clip_graph_mobilenetv5(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
|
|
ggml_tensor * rms_norm_2d(
|
|
ggml_tensor * inp,
|
|
ggml_tensor * weight,
|
|
float eps = 1e-6f);
|
|
|
|
ggml_tensor* pad_same_2d(
|
|
ggml_tensor* inp,
|
|
int kernel_h,
|
|
int kernel_w,
|
|
int stride_h,
|
|
int stride_w,
|
|
int dilation_h = 1,
|
|
int dilation_w = 1);
|
|
|
|
ggml_tensor * build_edge_residual(
|
|
ggml_tensor * inp,
|
|
const mobilenetv5_block & block,
|
|
int stride);
|
|
|
|
ggml_tensor * build_inverted_residual(
|
|
ggml_tensor * inp,
|
|
const mobilenetv5_block & block,
|
|
int stride);
|
|
|
|
ggml_tensor * build_mobilenet_attn(
|
|
ggml_tensor * inp,
|
|
const mobilenetv5_block & block);
|
|
};
|