Commit
•
b4ed75c
1
Parent(s):
56692f9
Added back in llm.create.chat.completion
Browse files
app.py
CHANGED
|
@@ -6,6 +6,14 @@ llm = Llama.from_pretrained(
|
|
| 6 |
repo_id="bartowski/Ministral-8B-Instruct-2410-GGUF",
|
| 7 |
filename="Ministral-8B-Instruct-2410-Q4_K_M.gguf",
|
| 8 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
|
| 10 |
|
| 11 |
def respond(
|
|
|
|
| 6 |
repo_id="bartowski/Ministral-8B-Instruct-2410-GGUF",
|
| 7 |
filename="Ministral-8B-Instruct-2410-Q4_K_M.gguf",
|
| 8 |
)
|
| 9 |
+
llm.create_chat_completion(
|
| 10 |
+
messages = [
|
| 11 |
+
{
|
| 12 |
+
"role": "user",
|
| 13 |
+
"content": "What is the capital of France?"
|
| 14 |
+
}
|
| 15 |
+
]
|
| 16 |
+
)
|
| 17 |
|
| 18 |
|
| 19 |
def respond(
|