File size: 3,643 Bytes
0a35d3e
a081ff4
 
6842806
 
a081ff4
0a35d3e
 
 
321a2ed
0a35d3e
 
 
 
f0a45da
 
0a35d3e
 
a9a0b5c
f0a45da
 
0a35d3e
f0a45da
a081ff4
23a6073
0a35d3e
f0a45da
 
0a35d3e
f0a45da
 
 
 
6842806
f0a45da
 
 
 
 
321a2ed
0a35d3e
f0a45da
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
321a2ed
 
0a35d3e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f0a45da
0a35d3e
 
 
a081ff4
0a35d3e
 
 
 
 
 
 
 
 
 
 
f0a45da
0a35d3e
 
 
 
 
23a6073
0a35d3e
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
import streamlit as st
from transformers import AutoModelForCausalLM, AutoTokenizer

# model_name = "flax-community/gpt-code-clippy-1.3B-apps-alldata"
model_name = "flax-community/gpt-code-clippy-125M-apps-alldata"

@st.cache(allow_output_mutation=True)
def get_model():
    return AutoModelForCausalLM.from_pretrained(model_name)

def get_tokenizer():
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    tokenizer.pad_token = tokenizer.eos_token
    return tokenizer

def format_input(question, starter_code=""):
    answer_type = "\nUse Call-Based format\n" if starter_code else \
                  "\nUse Standard Input format\n"
    return f"\nQUESTION:\n{question}\n{starter_code}\n{answer_type}\nANSWER:\n"


def generate_solution(model, tokenizer, question, starter_code="", temperature=1.0, num_beams=1):
    prompt = format_input(question, starter_code)
    input_ids = tokenizer(prompt, return_tensors="pt").input_ids
    start = len(input_ids[0])
    
    output = model.generate(
        input_ids,
        max_length=start + 150,
        do_sample=True,
        top_p=0.95,
        pad_token_id=tokenizer.pad_token_id,
        early_stopping=True,
        temperature=temperature,
        num_beams=int(num_beams),
        no_repeat_ngram_size=None,
        repetition_penalty=None,
        num_return_sequences=None,
    )

    return tokenizer.decode(output[0][start:], skip_special_tokens=True).strip()


_EXAMPLES = [
    [
        """
Given a 2D list of size `m * n`. Your task is to find the sum of minimum value in each row.
For Example:
```python
[
  [1, 2, 3, 4, 5],       # minimum value of row is 1
  [5, 6, 7, 8, 9],       # minimum value of row is 5
  [20, 21, 34, 56, 100]  # minimum value of row is 20
]
```
So, the function should return `26` because sum of minimums is as `1 + 5 + 20 = 26`
        """,
        "",
        0.8,
    ],
    [
        """
# Personalized greeting

Create a function that gives a personalized greeting. This function takes two parameters: `name` and `owner`.
        """,
        """
Use conditionals to return the proper message:

case| return
--- | ---
name equals owner | 'Hello boss'
otherwise         | 'Hello guest'
def greet(name, owner):
        """,
        0.8,
    ],
]
def run():
    st.set_page_config(
        page_title="Code Clippy Problem Solver"
    )
    # sidebar
    st.sidebar.title("Code Clippy")
    st.sidebar.image(
        "https://raw.githubusercontent.com/ncoop57/gpt-code-clippy/camera-ready/code_clippy_logo.jpg",
        caption="(c) awesome Aimee Trevett",
    )
    st.sidebar.markdown("[Github](https://github.com/ncoop57/gpt-code-clippy)")
    
    st.sidebar.markdown("### Controls:")
    
    temperature = st.sidebar.slider(
        "Temperature",
        min_value=0.5,
        max_value=1.5,
        value=0.8,
        step=0.1,
    )
    num_beams = st.sidebar.slider(
        "Num beams",
        min_value=1,
        max_value=4,
        step=1,
    )

    # main body
    model = get_model()
    tokenizer = get_tokenizer()

    question = st.text_input(
        "Problem: ",
        value="A function that can greet user by name. Given a name it should say hello to user.",
        help="Text description of the coding problem to be solved",
    )
    starter_code = st.text_input(
        "Started code: ",
        value="def greet(name):",
        help="Optional starter code"
    )
    submit_button = st.button("Solve")

    if submit_button:
        
        generate_solution(model, tokenizer, question, starter_code, temperature, num_beams)
        st.code(tmp, language="python")
    

if __name__=="__main__":
    run()