diff options
| author | Georgi Gerganov <ggerganov@gmail.com> | 2023-03-22 07:32:36 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-03-22 07:32:36 +0200 |
| commit | f5a77a629bd0f37ae1696747633ab42a5530ec15 (patch) | |
| tree | b3d147dd228ce67661ed497a6dc61b444a38e0f9 /convert-pth-to-ggml.py | |
| parent | da0e9fe90ccf6e73597eb19dd0cfc0a28363fb3b (diff) | |
Introduce C-style API (#370)
* Major refactoring - introduce C-style API
* Clean up
* Add <cassert>
* Add <iterator>
* Add <algorithm> ....
* Fix timing reporting and accumulation
* Measure eval time only for single-token calls
* Change llama_tokenize return meaning
Diffstat (limited to 'convert-pth-to-ggml.py')
| -rw-r--r-- | convert-pth-to-ggml.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/convert-pth-to-ggml.py b/convert-pth-to-ggml.py index db5b00f..f0f6b0e 100644 --- a/convert-pth-to-ggml.py +++ b/convert-pth-to-ggml.py @@ -148,7 +148,7 @@ def main(): model = torch.load(fname_model, map_location="cpu") with open(fname_out, "wb") as fout: - fout.write(struct.pack("i", hparams["vocab_size"])) + write_header(fout, hparams, ftype) write_tokens(fout, tokenizer) del model |