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

Remove gpt neox references

Browse source
This commit is contained in:
Galunid 2023-10-11 21:05:40 +02:00
parent 27467a5ced
commit 80b2e729fa
1 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

6
convert-stablelm-hf-to-gguf.py
View file

@ -1,5 +1,5 @@
#!/usr/bin/env python3 #!/usr/bin/env python3
# HF gptneox--> gguf conversion # HF stablelm --> gguf conversion
from __future__ import annotations from __future__ import annotations
@ -32,7 +32,7 @@ def count_model_parts(dir_model: Path) -> int:
def parse_args() -> argparse.Namespace: def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(description="Convert a GPT-NeoX model to a GGML compatible file") parser = argparse.ArgumentParser(description="Convert a stablelm model to a GGML compatible file")
parser.add_argument( parser.add_argument(
"--vocab-only", action="store_true", "--vocab-only", action="store_true",
help="extract only the vocab", help="extract only the vocab",
@ -77,7 +77,7 @@ print("gguf: loading model "+dir_model.name)
with open(dir_model / "config.json", "r", encoding="utf-8") as f: with open(dir_model / "config.json", "r", encoding="utf-8") as f:
hparams = json.load(f) hparams = json.load(f)
if hparams["architectures"][0] != "GPTNeoXForCausalLM" and hparams["architectures"][0] != "StableLMEpochForCausalLM": if hparams["architectures"][0] != "StableLMEpochForCausalLM":
print("Model architecture not supported: " + hparams["architectures"][0]) print("Model architecture not supported: " + hparams["architectures"][0])
sys.exit() sys.exit()