Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-07 11:23:56 +01:00
Code Issues Packages Projects Releases Wiki Activity

Update convert-gptneox-h5-to-gguf.py

Browse Source
This commit is contained in:
klosax 2023-07-30 17:31:11 +02:00 committed by GitHub
parent 068a8e0fbe
commit 2a0914673c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
convert-gptneox-h5-to-gguf.py
View File

@ -54,7 +54,7 @@ gguf_writer = gguf.GGUFWriter.open(fname_out)
with open(dir_model + "/config.json", "r", encoding="utf-8") as f:
hparams = json.load(f)
# This mmust be changed when adding/deleting kv
# This must be changed when adding/deleting kv
kv_count = 14
print("tensors " + str(tensor_count) + " kv " + str(kv_count))