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

convert : partially revert PR #4818 (#5041)

Browse source
This commit is contained in:
Jared Van Bortel 2024-01-20 18:14:18 -05:00 • committed by GitHub
parent 97c1549808
commit b43ebde3b0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 237 additions and 429 deletions
Download patch file Download diff file Expand all files Collapse all files

12
convert-persimmon-to-gguf.py
View file

@ -1,11 +1,13 @@
#!/usr/bin/env python3
import torch
import os
from pprint import pprint
import sys
import argparse
import os
import sys
from pathlib import Path
from pprint import pprint
import torch
from sentencepiece import SentencePieceProcessor
if 'NO_LOCAL_GGUF' not in os.environ:
sys.path.insert(1, str(Path(__file__).parent / 'gguf-py'))
import gguf
@ -69,7 +71,7 @@ def main():
persimmon_model = torch.load(args.ckpt_path)
hparams = persimmon_model['args']
pprint(hparams)
tensors = {}
tensors: dict[str, torch.Tensor] = {}
_flatten_dict(persimmon_model['model'], tensors, None)
arch = gguf.MODEL_ARCH.PERSIMMON