CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-01 09:01:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

convert : refactor vocab selection logic (#6355)

Browse Source
This commit is contained in:
Jared Van Bortel
2024-03-28 11:44:36 -04:00
committed by GitHub
parent 66ba560256
commit be55134a53
4 changed files with 204 additions and 176 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
convert-persimmon-to-gguf.py
View File

@@ -106,12 +106,12 @@ def main():
tensor_map = gguf.get_tensor_name_map(arch, block_count)
print(tensor_map)
for name in tensors.keys():
data = tensors[name]
data_torch = tensors[name]
if name.endswith(".self_attention.rotary_emb.inv_freq"):
continue
old_dtype = data.dtype
old_dtype = data_torch.dtype
# TODO: FP16 conversion produces garbage outputs. (Q8_0 does not, so..?)
data = data.to(torch.float32).squeeze().numpy()
data = data_torch.to(torch.float32).squeeze().numpy()
new_name = tensor_map.get_name(name, try_suffixes = (".weight", ".bias"))
if new_name is None:
print("Can not map tensor '" + name + "'")