Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 14:20:31 +01:00
Code Issues Packages Projects Releases Wiki Activity

convert scripts : fix python 3.8 compatibility

Browse Source
This commit is contained in:
Jared Van Bortel 2024-04-04 17:14:46 -04:00
parent 6a9d3c0911
commit 909f6be291
2 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
convert-hf-to-gguf.py
View File

@ -2311,7 +2311,8 @@ class MambaModel(Model):
data = data.astype(np.float32)
# if f16 desired, convert big float32 2-dim weight tensors to float16
if self.ftype == 1 and data_dtype == np.float32 and new_name.removesuffix(".weight").endswith((".ssm_in", ".ssm_out", "token_embd", "output")) and n_dims == 2:
new_weight_name = new_name[:-len(".weight")] if new_name.endswith(".weight") else ""
if self.ftype == 1 and data_dtype == np.float32 and new_weight_name.endswith((".ssm_in", ".ssm_out", "token_embd", "output")) and n_dims == 2:
data = data.astype(np.float16)
print(f"{new_name}, n_dims = {n_dims}, {old_dtype} --> {data.dtype}")

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

@ -1,4 +1,6 @@
#!/usr/bin/env python3
from __future__ import annotations
import argparse
import os
import sys