Spaces:
Runtime error
Runtime error
clean
Browse files
app.py
CHANGED
@@ -12,20 +12,6 @@ model = AutoPeftModelForCausalLM.from_pretrained(
|
|
12 |
)
|
13 |
tokenizer = AutoTokenizer.from_pretrained("EITD/lora_model_1")
|
14 |
|
15 |
-
# messages = [{"role": "user", "content": "Continue the Fibonacci sequence: 1, 1, 2, 3, 5, 8,"},]
|
16 |
-
|
17 |
-
# inputs = tokenizer.apply_chat_template(
|
18 |
-
# messages,
|
19 |
-
# tokenize = True,
|
20 |
-
# add_generation_prompt = True, # Must add for generation
|
21 |
-
# return_tensors = "pt",
|
22 |
-
# )
|
23 |
-
|
24 |
-
# outputs = model.generate(input_ids = inputs, max_new_tokens = 64, use_cache = True,
|
25 |
-
# temperature = 1.5, min_p = 0.1)
|
26 |
-
|
27 |
-
# print(tokenizer.batch_decode(outputs))
|
28 |
-
|
29 |
def respond(
|
30 |
message,
|
31 |
history: list[tuple[str, str]],
|
@@ -72,7 +58,6 @@ def respond(
|
|
72 |
# model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = max_tokens,
|
73 |
# use_cache = True, temperature = temperature, min_p = top_p)
|
74 |
response = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
|
75 |
-
print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
|
76 |
|
77 |
if "assistant" in response:
|
78 |
response = response.split("assistant")[-1].strip()
|
|
|
12 |
)
|
13 |
tokenizer = AutoTokenizer.from_pretrained("EITD/lora_model_1")
|
14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
def respond(
|
16 |
message,
|
17 |
history: list[tuple[str, str]],
|
|
|
58 |
# model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = max_tokens,
|
59 |
# use_cache = True, temperature = temperature, min_p = top_p)
|
60 |
response = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
|
|
|
61 |
|
62 |
if "assistant" in response:
|
63 |
response = response.split("assistant")[-1].strip()
|