CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

model-conversion : run-org-model.py fails to run on mac m1 (#16213)

Browse Source 
Signed-off-by: Jie Fu <jiefu@tencent.com>
This commit is contained in:
Jie Fu (傅杰)
2025-09-24 14:46:52 +08:00
committed by GitHub
parent 4d9ea03d17
commit 7735706b93
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/model-conversion/scripts/causal/run-org-model.py
View File

@@ -193,7 +193,7 @@ print(f"Input text: {repr(prompt)}")
print(f"Tokenized: {tokenizer.convert_ids_to_tokens(input_ids[0])}")
with torch.no_grad():
outputs = model(input_ids)
outputs = model(input_ids.to(model.device))
logits = outputs.logits
# Extract logits for the last token (next token prediction)