Hugging Face's logo

Hansda
/
ScreenVLM-GGUF

Image-Text-to-Text
GGUF
screen-parsing
ui-understanding
llama.cpp
conversational
Model card Files
xet
 Community
ScreenVLM-GGUF / CHANGES.md
Hansda's picture
Hansda
Publish ScreenVLM-Q8_0.gguf
7c455c9 verified
preview code
|
Raw History Blame Contribute Delete
748 Bytes

Conversion changes

Original source: docling-project/ScreenVLM at 78df0cc8498bbea1a03eb2816056fc0a76d2f63d. Converted original mixed F32/BF16 weights to GGUF F16 matrix storage with required F32 tensors. Q8_0 is independently derived from F16. The full vision encoder and 4x connector are in mmproj. No training was performed. GGUF metadata carries a prominent change notice. The source tokenizer's unusable out-of-range IDs 100352 () and 100353 () are removed only in a converter-specific copy. Original source files and weights remain unchanged. No model-defined token or weight row is removed; the source chat template is preserved verbatim. This is an independent conversion and does not imply upstream endorsement.