tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

llava: add big-endian conversion for image encoder (#12218)

Browse Source 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
This commit is contained in:
Aaron Teo
2025-03-06 16:33:21 +08:00
committed by GitHub
parent e721c05c93
commit e9b2f84f14
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/llava/convert_image_encoder_to_gguf.py
View File

@ -89,6 +89,7 @@ def bytes_to_unicode():
ap = argparse.ArgumentParser() ap = argparse.ArgumentParser()
ap.add_argument("-m", "--model-dir", help="Path to model directory cloned from HF Hub", required=True) ap.add_argument("-m", "--model-dir", help="Path to model directory cloned from HF Hub", required=True)
ap.add_argument("--use-f32", action="store_true", default=False, help="Use f32 instead of f16") ap.add_argument("--use-f32", action="store_true", default=False, help="Use f32 instead of f16")
ap.add_argument('--bigendian', action="store_true", default=False, help="Model is executed on big-endian machine")
ap.add_argument("--text-only", action="store_true", required=False, ap.add_argument("--text-only", action="store_true", required=False,
help="Save a text-only model. It can't be used to encode images") help="Save a text-only model. It can't be used to encode images")
ap.add_argument("--vision-only", action="store_true", required=False, ap.add_argument("--vision-only", action="store_true", required=False,
@ -191,7 +192,7 @@ output_dir = args.output_dir if args.output_dir is not None else dir_model
os.makedirs(output_dir, exist_ok=True) os.makedirs(output_dir, exist_ok=True)
output_prefix = os.path.basename(output_dir).replace("ggml_", "") output_prefix = os.path.basename(output_dir).replace("ggml_", "")
fname_out = os.path.join(output_dir, f"{fname_middle}model-{ftype_str[ftype]}.gguf") fname_out = os.path.join(output_dir, f"{fname_middle}model-{ftype_str[ftype]}.gguf")
fout = GGUFWriter(path=fname_out, arch="clip") fout = GGUFWriter(path=fname_out, arch="clip", endianess=GGUFEndian.LITTLE if not args.bigendian else GGUFEndian.BIG)
fout.add_bool("clip.has_text_encoder", has_text_encoder) fout.add_bool("clip.has_text_encoder", has_text_encoder)
fout.add_bool("clip.has_vision_encoder", has_vision_encoder) fout.add_bool("clip.has_vision_encoder", has_vision_encoder)