tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-04 18:16:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml-quants : use ceiling division when quantizing q1_3

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-06-26 15:31:48 -04:00
parent 9465ec6e12
commit 89dc3b254c
4 changed files with 12 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
convert-hf-to-gguf.py
View File

@ -336,7 +336,7 @@ class Model:
shape = gguf.quant_shape_from_byte_shape(data.shape, data_qtype) if data.dtype == np.uint8 else data.shape
# reverse shape to make it similar to the internal ggml dimension order
shape_str = f"{{{', '.join(str(n) for n in reversed(shape))}}}"
shape_str = f"{{{', '.join(str(n) for n in reversed(shape)) or '1'}}}"
# n_dims is implicit in the shape
logger.info(f"{f'%-{max_name_len}s' % f'{new_name},'} {old_dtype} --> {data_qtype.name}, shape = {shape_str}")