diff options
| author | Justine Tunney <jtunney@gmail.com> | 2023-03-30 05:42:56 -0700 |
|---|---|---|
| committer | Justine Tunney <jtunney@gmail.com> | 2023-03-30 12:28:25 -0700 |
| commit | ee0c40dd6de8c3c658ae43199939ef40bb1cf408 (patch) | |
| tree | 92a09d5cd19cbf08b091edaf5019c6a697fa1c50 /convert-pth-to-ggml.py | |
| parent | 6f23ba5ee235cbcb1eedd63b98422dd8d4392a78 (diff) | |
Introduce GGML migration tool for new file format
If you deleted your old Meta LLaMA .pth files, then the
migrate-ggml-2023-03-30-pr613.py script will allow you to convert your
old ggml files into the new mmap()'able format.
See #613
Diffstat (limited to 'convert-pth-to-ggml.py')
| -rw-r--r-- | convert-pth-to-ggml.py | 8 |
1 files changed, 3 insertions, 5 deletions
diff --git a/convert-pth-to-ggml.py b/convert-pth-to-ggml.py index 7d46115..df42e76 100644 --- a/convert-pth-to-ggml.py +++ b/convert-pth-to-ggml.py @@ -1,4 +1,4 @@ -# Convert a LLaMA model checkpoint to a ggml compatible file +# Convert a LLaMA model checkpoint to a ggjt compatible file # # Load the model using Torch # Iterate over all variables and write them to a binary file. @@ -52,8 +52,8 @@ GGML_BLCK_SIZE = { } GGML_TYPE_SIZE = { - GGML_TYPE_Q4_0: 4 + QK/2, - GGML_TYPE_Q4_1: 4*2 + QK/2, + GGML_TYPE_Q4_0: 4 + QK//2, + GGML_TYPE_Q4_1: 4*2 + QK//2, GGML_TYPE_I8: 1, GGML_TYPE_I16: 2, GGML_TYPE_I32: 4, @@ -245,11 +245,9 @@ def main(): fname_model = f"{dir_model}/consolidated.00.pth" fname_out = f"{dir_model}/ggml-vocab.bin" print(f"Extracting only the vocab from '{fname_model}'\n") - model = torch.load(fname_model, map_location="cpu") with open(fname_out, "wb") as fout: write_header(fout, hparams, ftype) write_tokens(fout, tokenizer) - del model print(f"Done. Output file: {fname_out}\n") return |