convert : refactor vocab selection logic (#6355)

This commit is contained in:
Jared Van Bortel 2024-03-28 11:44:36 -04:00 committed by GitHub
parent 66ba560256
commit be55134a53
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 204 additions and 176 deletions

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 + "'")