Skip to content

Commit 82cb614

Browse files
committed
Fix renaming of gguf_dump.py
1 parent d9cf0c7 commit 82cb614

File tree

2 files changed

+2
-2
lines changed

2 files changed

+2
-2
lines changed

examples/server.ps1

+1-1
Original file line numberDiff line numberDiff line change
@@ -126,7 +126,7 @@ try {
126126
# We are trying to extract model details from the GGUF file.
127127
# https://github.com/ggerganov/ggml/blob/master/docs/gguf.md#llm
128128
# TODO: Find a robust way to resolve this values.
129-
$modelData = Invoke-Expression "python ${llamaCppPath}\gguf-py\scripts\gguf-dump.py --no-tensors `"${model}`""
129+
$modelData = Invoke-Expression "python ${llamaCppPath}\gguf-py\scripts\gguf_dump.py --no-tensors `"${model}`""
130130
$modelContextLength = [Int]($modelData | Select-String -Pattern '\bcontext_length = (\d+)\b').Matches.Groups[1].Value
131131
$modelHeadCount = [Int]($modelData | Select-String -Pattern '\bhead_count = (\d+)\b').Matches.Groups[1].Value
132132
$modelBlockCount = [Int]($modelData | Select-String -Pattern '\bblock_count = (\d+)\b').Matches.Groups[1].Value

vendor/llama.cpp

0 commit comments

Comments
 (0)