Update app.py
Browse files
app.py
CHANGED
@@ -73,11 +73,12 @@ def respond(
|
|
73 |
temperature,
|
74 |
top_p,
|
75 |
):
|
76 |
-
|
77 |
messages = [{"role": "user", "content": "Hello, how are you?"}]
|
78 |
input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to('cuda')
|
79 |
## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
|
80 |
# with autocast():
|
|
|
81 |
gen_tokens = model.generate(
|
82 |
input_ids,
|
83 |
max_new_tokens=100,
|
|
|
73 |
temperature,
|
74 |
top_p,
|
75 |
):
|
76 |
+
|
77 |
messages = [{"role": "user", "content": "Hello, how are you?"}]
|
78 |
input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to('cuda')
|
79 |
## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
|
80 |
# with autocast():
|
81 |
+
model= model.to('cuda')
|
82 |
gen_tokens = model.generate(
|
83 |
input_ids,
|
84 |
max_new_tokens=100,
|