Spaces:
Runtime error
Runtime error
shljessie
commited on
Commit
·
4e3bf2c
1
Parent(s):
b44b7bd
text basic interface
Browse files
app.py
CHANGED
@@ -4,40 +4,40 @@ import gradio as gr
|
|
4 |
import torch
|
5 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
6 |
|
7 |
-
# Check if CUDA is available
|
8 |
-
if not torch.cuda.is_available():
|
9 |
-
|
10 |
|
11 |
# Model Configuration
|
12 |
-
MODEL_ID = "meta-llama/Llama-2-7b-chat"
|
13 |
-
MAX_INPUT_TOKEN_LENGTH = 4096
|
14 |
-
MAX_NEW_TOKENS = 1024
|
15 |
-
TEMPERATURE = 0.6
|
16 |
-
TOP_P = 0.9
|
17 |
-
TOP_K = 50
|
18 |
-
REPETITION_PENALTY = 1.2
|
19 |
-
|
20 |
-
# Load the model and tokenizer
|
21 |
-
model = AutoModelForCausalLM.from_pretrained(MODEL_ID, torch_dtype=torch.float16, device_map="auto")
|
22 |
-
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
|
23 |
-
|
24 |
-
def generate_response(user_input):
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
def chatbot_interface(user_input):
|
40 |
-
|
41 |
|
42 |
# Create the Gradio interface
|
43 |
iface = gr.Interface(
|
|
|
4 |
import torch
|
5 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
6 |
|
7 |
+
# # Check if CUDA is available
|
8 |
+
# if not torch.cuda.is_available():
|
9 |
+
# raise EnvironmentError("CUDA is not available. This script requires a GPU.")
|
10 |
|
11 |
# Model Configuration
|
12 |
+
# MODEL_ID = "meta-llama/Llama-2-7b-chat"
|
13 |
+
# MAX_INPUT_TOKEN_LENGTH = 4096
|
14 |
+
# MAX_NEW_TOKENS = 1024
|
15 |
+
# TEMPERATURE = 0.6
|
16 |
+
# TOP_P = 0.9
|
17 |
+
# TOP_K = 50
|
18 |
+
# REPETITION_PENALTY = 1.2
|
19 |
+
|
20 |
+
# # Load the model and tokenizer
|
21 |
+
# model = AutoModelForCausalLM.from_pretrained(MODEL_ID, torch_dtype=torch.float16, device_map="auto")
|
22 |
+
# tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
|
23 |
+
|
24 |
+
# def generate_response(user_input):
|
25 |
+
# """
|
26 |
+
# Generate a response to the user input using the Llama-2 7B model.
|
27 |
+
# """
|
28 |
+
# input_ids = tokenizer.encode(user_input, return_tensors="pt")
|
29 |
+
# input_ids = input_ids.to(model.device)
|
30 |
+
|
31 |
+
# # Generate a response
|
32 |
+
# output = model.generate(input_ids, max_length=MAX_INPUT_TOKEN_LENGTH + len(input_ids[0]),
|
33 |
+
# max_new_tokens=MAX_NEW_TOKENS, temperature=TEMPERATURE,
|
34 |
+
# top_k=TOP_K, top_p=TOP_P, repetition_penalty=REPETITION_PENALTY)
|
35 |
+
|
36 |
+
# response = tokenizer.decode(output[0], skip_special_tokens=True)
|
37 |
+
# return response
|
38 |
+
|
39 |
+
# def chatbot_interface(user_input):
|
40 |
+
# return generate_response(user_input)
|
41 |
|
42 |
# Create the Gradio interface
|
43 |
iface = gr.Interface(
|