vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Add support for I8, I16, I32 to gguf_reader

Browse source
This commit is contained in:
Ondřej Čertík 2024-03-13 14:12:41 -06:00
parent c5423753f7
commit fc5d6e6513
1 changed files with 9 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

9
gguf-py/gguf/gguf_reader.py
View file

@ -248,6 +248,15 @@ class GGUFReader:
elif ggml_type == GGMLQuantizationType.F16: elif ggml_type == GGMLQuantizationType.F16:
item_count = n_elems item_count = n_elems
item_type = np.float16 item_type = np.float16
elif ggml_type == GGMLQuantizationType.I8:
item_count = n_elems
item_type = np.int8
elif ggml_type == GGMLQuantizationType.I16:
item_count = n_elems
item_type = np.int16
elif ggml_type == GGMLQuantizationType.I32:
item_count = n_elems
item_type = np.int32
else: else:
item_count = n_bytes item_count = n_bytes
item_type = np.uint8 item_type = np.uint8