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

Update gptq to ggml loader as well

Browse source
This commit is contained in:
albanD 2023-04-02 09:32:27 -04:00
parent 452b6ab115
commit b31447507a
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
convert-gptq-to-ggml.py
View file

@ -18,7 +18,7 @@ fname_model = sys.argv[1]
fname_tokenizer = sys.argv[2]
dir_out = sys.argv[3]
model = torch.load(fname_model, map_location="cpu")
model = torch.load(fname_model, map_location="cpu", weights_only=True)
n_vocab, n_embd = model['model.embed_tokens.weight'].shape
n_layer = 1 + max(int(m.group(1)) for name in model