Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -33,7 +33,7 @@ examples=[
|
|
33 |
|
34 |
|
35 |
# Stream text - stream tokens with InferenceClient from TGI
|
36 |
-
async def predict(message, chatbot, system_prompt="", temperature=0.1, max_new_tokens=4096, repetition_penalty=1.1,):
|
37 |
|
38 |
if system_prompt != "":
|
39 |
input_prompt = f"<s>[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n "
|
@@ -64,7 +64,7 @@ async def predict(message, chatbot, system_prompt="", temperature=0.1, max_new_t
|
|
64 |
|
65 |
|
66 |
# No Stream - batch produce tokens using TGI inference endpoint
|
67 |
-
def predict_batch(message, chatbot, system_prompt="", temperature=0.1, max_new_tokens=4096, repetition_penalty=1.1):
|
68 |
|
69 |
if system_prompt != "":
|
70 |
input_prompt = f"<s>[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n "
|
|
|
33 |
|
34 |
|
35 |
# Stream text - stream tokens with InferenceClient from TGI
|
36 |
+
async def predict(message, chatbot, system_prompt="", temperature=0.1, max_new_tokens=4096, top_p=0.6, repetition_penalty=1.1,):
|
37 |
|
38 |
if system_prompt != "":
|
39 |
input_prompt = f"<s>[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n "
|
|
|
64 |
|
65 |
|
66 |
# No Stream - batch produce tokens using TGI inference endpoint
|
67 |
+
def predict_batch(message, chatbot, system_prompt="", temperature=0.1, max_new_tokens=4096, top_p=0.6, repetition_penalty=1.1):
|
68 |
|
69 |
if system_prompt != "":
|
70 |
input_prompt = f"<s>[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n "
|