File size: 4,851 Bytes
c9e8e4a
3bce3fb
a16fa71
aa07439
41d27ac
 
c9e8e4a
68bc50c
cddb272
fa5e188
c9e8e4a
 
f4313df
c9e8e4a
 
 
7c0d726
aa07439
 
 
 
 
 
 
 
7c0d726
 
 
 
 
 
 
aa07439
7c0d726
aa07439
 
 
 
 
 
 
 
 
 
 
 
 
7c0d726
2dc5a7a
5482687
807f36d
 
c5fafcd
0d5adbc
 
cc3091d
0d5adbc
 
7212da7
50f4554
4bd868a
aa07439
7d968ad
a5b4c8d
 
aa07439
9d2b32b
 
0b16412
 
4bd868a
0d5adbc
 
7036561
816c983
12798fb
29136c5
46dbbb1
0b16412
0d5adbc
 
a7dffcb
0b16412
8d58283
0d5adbc
 
7036561
33147c8
29136c5
606a970
29136c5
68bc50c
99db140
596c6fa
606a970
12798fb
 
 
 
33147c8
12798fb
 
 
606a970
 
12798fb
 
 
 
 
 
 
cc14b64
12798fb
 
 
 
 
06d2b63
 
 
33147c8
06d2b63
 
 
aa07439
 
 
 
 
06d2b63
 
 
 
 
aa07439
 
 
06d2b63
aa07439
cc3091d
 
 
 
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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
import json
import pandas as pd
import requests
import threading
import streamlit as st


MODELS = ["CodeParrot", "InCoder", "CodeGen", "PolyCoder"]
GENERATION_MODELS = ["CodeParrot", "InCoder", "CodeGen"]

@st.cache()
def load_examples():
    with open("utils/examples.json", "r") as f:
        examples = json.load(f)
    return examples


def read_markdown(path):
    with open(path, "r") as f:
        output = f.read()
    st.markdown(output, unsafe_allow_html=True)   
    
    
def generate_code(generations, model_name, gen_prompt, max_new_tokens, temperature, seed):
    # call space using its API endpoint
    url = (
        f"https://hf.space/embed/loubnabnl/{model_name.lower()}-subspace/+/api/predict/"
    )
    r = requests.post(
        url=url, json={"data": [gen_prompt, max_new_tokens, temperature, seed]}
    )
    generated_text = r.json()["data"][0]
    generations.append(generated_text)    

        
def generate_code_threads(generations, models, gen_prompt, max_new_tokens, temperature, seed):                                                
    threads = []                                                                
    for model_name in models:                                                     
        # create the thread                                                     
        threads.append(                                                         
            threading.Thread(target=generate_code, args=(generations, model_name, gen_prompt, max_new_tokens, temperature, seed))
        )         
        threads[-1].start()                 
                                        
    for t in threads:                                                           
        t.join()  
        

st.set_page_config(page_icon=":laptop:", layout="wide")
with open("utils/table_contents.txt", "r") as f:
    contents = f.read()
st.sidebar.markdown(contents)

# Introduction
st.title("Code generation with 🤗")
read_markdown("utils/intro.txt")

# Pretraining datasets
st.subheader("1 - Code datasets")
read_markdown("datasets/intro.txt")
read_markdown("datasets/github_code.txt")
#GITHUB_CODE = "https://huggingface.co/datasets/lvwerra/github-code"
#st.markdown(f"Preview of some code files from Github repositories in [Github-code dataset]({GITHUB_CODE}):")
#df = pd.read_csv("utils/data_preview.csv")
#st.dataframe(df)

col1, col2= st.columns([1,2])
with col1:
    selected_model = st.selectbox("", MODELS, key=1)
read_markdown(f"datasets/{selected_model.lower()}.txt")


# Model architecture
st.subheader("2 - Model architecture")
read_markdown("architectures/intro.txt")
col1, col2= st.columns([1,2])
with col1:
    selected_model = st.selectbox("", MODELS, key=2)
read_markdown(f"architectures/{selected_model.lower()}.txt")

# Model evaluation
st.subheader("3 - Code models evaluation")
read_markdown("evaluation/intro.txt")
read_markdown("evaluation/demo_humaneval.txt")

# Code generation
st.subheader("4 - Code generation ✨")
col1, col2, col3 = st.columns([7,1,6])
with col1:
    st.markdown("**Models**")
    selected_models = st.multiselect(
    "Select code generation models to compare:", GENERATION_MODELS, default=["CodeParrot"], key=3
)
    st.markdown(" ")
    st.markdown("**Examples**")
    examples = load_examples()
    example_names = [example["name"] for example in examples]
    name2id = dict([(name, i) for i, name in enumerate(example_names)])
    selected_example = st.selectbox(
        "Select one of the following examples or implement yours:", example_names
    )
    example_text = examples[name2id[selected_example]]["value"]
    default_length = examples[name2id[selected_example]]["length"]
with col3:
    st.markdown("**Generation settings**")
    temperature = st.slider(
        "Temperature:", value=0.2, min_value=0.0, step=0.1, max_value=2.0
    )
    max_new_tokens = st.slider(
        "Number of tokens to generate:",
        value=default_length,
        min_value=8,
        step=4,
        max_value=256,
    )
    seed = st.slider(
        "Random seed:", value=42, min_value=0, step=1, max_value=1000
    )
gen_prompt = st.text_area(
    "Generate code with prompt:",
    value=example_text,
    height=200,
).strip()
if st.button("Generate code!"):
    with st.spinner("Generating code..."):
        # use threading
        generations = []
        generate_code_threads(
            generations,
            selected_models,
            gen_prompt=gen_prompt,
            max_new_tokens=max_new_tokens,
            temperature=temperature,
            seed=seed,
        )
        for i in range(len(generations)):
            print(generations[i])
        for i in range(len(generations)):
            st.markdown(f"**{selected_models[i]}**")
            st.code(generations[i])

# Resources
st.subheader("Resources")
read_markdown("utils/resources.txt")