mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 28 Packages Projects Releases Wiki Activity

model: Add PaddleOCR-VL model support (#18825)

Browse Source 
* support PaddleOCR-VL

* clip: update PaddleOCR model loader parameters to prevent OOM during warmup

* [update] add paddleocr vl text model instead of ernie4.5

* [update] restore change of minicpmv

* [update] format

* [update] format

* [update] positions and patch merge permute

* [update] mtmd_decode_use_mrope for paddleocr

* [update] image min/max pixels

* [update] remove set_limit_image_tokens

* upate: preprocess without padding

* clean up

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
megemini
2026-02-20 00:05:25 +08:00
committed by GitHub
parent abb9f3c42b
commit 237958db33
16 changed files with 327 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gguf-py/gguf/constants.py
+17
View File
@@ -473,6 +473,7 @@ class MODEL_ARCH(IntEnum):
RND1 = auto()
PANGU_EMBED = auto()
MISTRAL3 = auto()
PADDLEOCR = auto()
MIMO2 = auto()
STEP35 = auto()
LLAMA_EMBED = auto()
@@ -914,6 +915,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.RND1: "rnd1",
MODEL_ARCH.PANGU_EMBED: "pangu-embedded",
MODEL_ARCH.MISTRAL3: "mistral3",
MODEL_ARCH.PADDLEOCR: "paddleocr",
MODEL_ARCH.MIMO2: "mimo2",
MODEL_ARCH.STEP35: "step35",
MODEL_ARCH.LLAMA_EMBED: "llama-embed",
@@ -3186,6 +3188,20 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.PADDLEOCR: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_GATE,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.FALCON_H1: [
# Token embedding
MODEL_TENSOR.TOKEN_EMBD,
@@ -3847,6 +3863,7 @@ class VisionProjectorType:
VOXTRAL = "voxtral"
LFM2 = "lfm2"
KIMIVL = "kimivl"
PADDLEOCR = "paddleocr"
KIMIK25 = "kimik25"
LIGHTONOCR = "lightonocr"
COGVLM = "cogvlm"
gguf-py/gguf/tensor_mapping.py
+3
View File
@@ -1325,6 +1325,7 @@ class TensorNameMap:
"multi_modal_projector.linear_{bid}",
"mm_projector.proj.linear_{bid}", # Kimi-K2.5
"visual.merger.mlp.{bid}", # qwen2vl
"mlp_AR.linear_{bid}", # PaddleOCR-VL
"merger.mlp.{bid}",
),
@@ -1574,6 +1575,7 @@ class TensorNameMap:
"mm_projector.pre_norm", # Kimi-K2.5
"pre_mm_projector_norm",
"model.vision.linear_proj.norm1", # cogvlm
"mlp_AR.pre_norm", # PaddleOCR-VL
"merger.ln_q",
),
@@ -1599,6 +1601,7 @@ class TensorNameMap:
MODEL_TENSOR.V_RESMPL_ATTN_OUT: (
"resampler.attn.out_proj",
"model.vision_model.head.attention.out_proj",
),
MODEL_TENSOR.V_RESMPL_KV: (