Add support for I8, I16, I32 to gguf_reader

ggerganov · Mar 13, 2024 · b4d2c4d · b4d2c4d
1 parent 4da095e
commit b4d2c4d
Showing 1 changed file with 9 additions and 0 deletions.
diff --git a/gguf-py/gguf/gguf_reader.py b/gguf-py/gguf/gguf_reader.py
@@ -248,6 +248,15 @@ def _build_tensors(self, start_offs: int, fields: list[ReaderField]) -> None:
  elif ggml_type == GGMLQuantizationType.F16:
  item_count = n_elems
  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:
  item_count = n_bytes
  item_type = np.uint8