Spaces:
Running
on
T4
Running
on
T4
Update app.py
Browse files
app.py
CHANGED
|
@@ -185,17 +185,11 @@ async def chat(query,history,sources,reports,subtype,year):
|
|
| 185 |
|
| 186 |
# llama-3_1 endpoint = https://howaqfw0lpap12sg.us-east-1.aws.endpoints.huggingface.cloud
|
| 187 |
# llama-3 endpoint = https://nhe9phsr2zhs0e36.eu-west-1.aws.endpoints.huggingface.cloud
|
| 188 |
-
callbacks = [StreamingStdOutCallbackHandler()]
|
| 189 |
llm_qa = HuggingFaceEndpoint(
|
| 190 |
endpoint_url="https://howaqfw0lpap12sg.us-east-1.aws.endpoints.huggingface.cloud",
|
| 191 |
-
|
| 192 |
-
|
| 193 |
-
top_p=0.95,
|
| 194 |
-
typical_p=0.95,
|
| 195 |
-
temperature=0.01,
|
| 196 |
-
callbacks=callbacks,
|
| 197 |
-
streaming=True,
|
| 198 |
-
repetition_penalty=1.03,)
|
| 199 |
|
| 200 |
# create rag chain
|
| 201 |
chat_model = ChatHuggingFace(llm=llm_qa)
|
|
|
|
| 185 |
|
| 186 |
# llama-3_1 endpoint = https://howaqfw0lpap12sg.us-east-1.aws.endpoints.huggingface.cloud
|
| 187 |
# llama-3 endpoint = https://nhe9phsr2zhs0e36.eu-west-1.aws.endpoints.huggingface.cloud
|
| 188 |
+
#callbacks = [StreamingStdOutCallbackHandler()]
|
| 189 |
llm_qa = HuggingFaceEndpoint(
|
| 190 |
endpoint_url="https://howaqfw0lpap12sg.us-east-1.aws.endpoints.huggingface.cloud",
|
| 191 |
+
task="text-generation",
|
| 192 |
+
huggingfacehub_api_token=HF_token)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 193 |
|
| 194 |
# create rag chain
|
| 195 |
chat_model = ChatHuggingFace(llm=llm_qa)
|