Update app.py
Browse files
app.py
CHANGED
@@ -16,7 +16,8 @@ else:
|
|
16 |
raise ValueError("HF_TOKEN environment variable not set. Please add it as a secret in your Hugging Face Space.")
|
17 |
|
18 |
# model = ollama.pull('llama3.2')
|
19 |
-
|
|
|
20 |
|
21 |
class ChatRequest(BaseModel):
|
22 |
message: str
|
@@ -35,8 +36,13 @@ async def chat(request: ChatRequest):
|
|
35 |
try:
|
36 |
start_time = time.time() # Start measuring time
|
37 |
|
|
|
|
|
|
|
|
|
|
|
38 |
# Simulate getting the response from the model
|
39 |
-
response = ollama.chat(model=
|
40 |
# response = "pending"
|
41 |
response = str(response)
|
42 |
|
|
|
16 |
raise ValueError("HF_TOKEN environment variable not set. Please add it as a secret in your Hugging Face Space.")
|
17 |
|
18 |
# model = ollama.pull('llama3.2')
|
19 |
+
model_name = 'hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M'
|
20 |
+
model = ollama.pull(model_name)
|
21 |
|
22 |
class ChatRequest(BaseModel):
|
23 |
message: str
|
|
|
36 |
try:
|
37 |
start_time = time.time() # Start measuring time
|
38 |
|
39 |
+
messages = [
|
40 |
+
{'role': 'system', 'content': request.system_message}
|
41 |
+
{'role': 'user', 'content': request.message}
|
42 |
+
]
|
43 |
+
|
44 |
# Simulate getting the response from the model
|
45 |
+
response = ollama.chat(model=model_name, messages=messages)
|
46 |
# response = "pending"
|
47 |
response = str(response)
|
48 |
|