faster q4
Browse files
app.py
CHANGED
|
@@ -7,6 +7,7 @@ llm = Llama.from_pretrained(
|
|
| 7 |
filename="unsloth.Q4_K_M.gguf",
|
| 8 |
)
|
| 9 |
|
|
|
|
| 10 |
# llm = Llama.from_pretrained(
|
| 11 |
# repo_id="ID2223JR/gguf_model_q8",
|
| 12 |
# filename="unsloth.Q8_0.gguf",
|
|
|
|
| 7 |
filename="unsloth.Q4_K_M.gguf",
|
| 8 |
)
|
| 9 |
|
| 10 |
+
|
| 11 |
# llm = Llama.from_pretrained(
|
| 12 |
# repo_id="ID2223JR/gguf_model_q8",
|
| 13 |
# filename="unsloth.Q8_0.gguf",
|