Smallest model for inference purpose
Browse files
app.py
CHANGED
|
@@ -5,7 +5,7 @@ from huggingface_hub import hf_hub_download
|
|
| 5 |
# Download GGUF to local file
|
| 6 |
model_path = hf_hub_download(
|
| 7 |
repo_id="astegaras/Llama3.2_3B",
|
| 8 |
-
filename="model-
|
| 9 |
)
|
| 10 |
|
| 11 |
llm = Llama(
|
|
|
|
| 5 |
# Download GGUF to local file
|
| 6 |
model_path = hf_hub_download(
|
| 7 |
repo_id="astegaras/Llama3.2_3B",
|
| 8 |
+
filename="model-Q2_K.gguf"
|
| 9 |
)
|
| 10 |
|
| 11 |
llm = Llama(
|