File size: 4,749 Bytes
c18db37
 
 
 
08af166
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c18db37
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from transformers import BlenderbotTokenizer, BlenderbotForConditionalGeneration
import torch
import gradio as gr


# PersistDataset -----
import os
import csv
import gradio as gr
from gradio import inputs, outputs
import huggingface_hub
from huggingface_hub import Repository, hf_hub_download, upload_file
from datetime import datetime
DATASET_REPO_URL = "https://huggingface.co/datasets/awacke1/Carddata.csv"
DATASET_REPO_ID = "awacke1/Carddata.csv"
DATA_FILENAME = "Carddata.csv"
DATA_FILE = os.path.join("data", DATA_FILENAME)
HF_TOKEN = os.environ.get("HF_TOKEN")
# overriding/appending to the gradio template
SCRIPT = """
<script>
if (!window.hasBeenRun) {
    window.hasBeenRun = true;
    console.log("should only happen once");
    document.querySelector("button.submit").click();
}
</script>
"""
#with open(os.path.join(gr.networking.STATIC_TEMPLATE_LIB, "frontend", "index.html"), "a") as f:
#    f.write(SCRIPT)
try:
    hf_hub_download(
        repo_id=DATASET_REPO_ID,
        filename=DATA_FILENAME,
        cache_dir=DATA_DIRNAME,
        force_filename=DATA_FILENAME
    )
except:
    print("file not found")
repo = Repository(
    local_dir="data", clone_from=DATASET_REPO_URL, use_auth_token=HF_TOKEN
)
def generate_html() -> str:
    with open(DATA_FILE) as csvfile:
        reader = csv.DictReader(csvfile)
        rows = []
        for row in reader:
            rows.append(row)
        rows.reverse()
        if len(rows) == 0:
            return "no messages yet"
        else:
            html = "<div class='chatbot'>"
            for row in rows:
                html += "<div>"
                html += f"<span>{row['name']}</span>"
                html += f"<span class='message'>{row['message']}</span>"
                html += "</div>"
            html += "</div>"
            return html
def store_message(name: str, message: str):
    if name and message:
        with open(DATA_FILE, "a") as csvfile:
            writer = csv.DictWriter(csvfile, fieldnames=["name", "message", "time"])
            writer.writerow(
                {"name": name, "message": message, "time": str(datetime.now())}
            )
        commit_url = repo.push_to_hub()
    return generate_html()
iface = gr.Interface(
    store_message,
    [
        inputs.Textbox(placeholder="Your name"),
        inputs.Textbox(placeholder="Your message", lines=2),
    ],
    "html",
    css="""
    .message {background-color:cornflowerblue;color:white; padding:4px;margin:4px;border-radius:4px; }
    """,
    title="Reading/writing to a HuggingFace dataset repo from Spaces",
    description=f"This is a demo of how to do simple *shared data persistence* in a Gradio Space, backed by a dataset repo.",
    article=f"The dataset repo is [{DATASET_REPO_URL}]({DATASET_REPO_URL})",
)
#iface.launch()
# -------


mname = "facebook/blenderbot-400M-distill"
model = BlenderbotForConditionalGeneration.from_pretrained(mname)
tokenizer = BlenderbotTokenizer.from_pretrained(mname)

def take_last_tokens(inputs, note_history, history):
    """Filter the last 128 tokens"""
    if inputs['input_ids'].shape[1] > 128:
        inputs['input_ids'] = torch.tensor([inputs['input_ids'][0][-128:].tolist()])
        inputs['attention_mask'] = torch.tensor([inputs['attention_mask'][0][-128:].tolist()])
        note_history = ['</s> <s>'.join(note_history[0].split('</s> <s>')[2:])]
        history = history[1:]
    return inputs, note_history, history

def add_note_to_history(note, note_history):
    """Add a note to the historical information"""
    note_history.append(note)
    note_history = '</s> <s>'.join(note_history)
    return [note_history]

title = "Blenderbot Tokenizer with Conditional Generation State of the Art"
description = """Blenderbot"""

def chat(message, history):
    history = history or []
    if history: 
        history_useful = ['</s> <s>'.join([str(a[0])+'</s> <s>'+str(a[1]) for a in history])]
    else:
        history_useful = []
    history_useful = add_note_to_history(message, history_useful)
    inputs = tokenizer(history_useful, return_tensors="pt")
    inputs, history_useful, history = take_last_tokens(inputs, history_useful, history)
    reply_ids = model.generate(**inputs)
    response = tokenizer.batch_decode(reply_ids, skip_special_tokens=True)[0]
    history_useful = add_note_to_history(response, history_useful)
    list_history = history_useful[0].split('</s> <s>')
    history.append((list_history[-2], list_history[-1]))
    return history, history

gr.Interface(
    fn=chat,
    theme="huggingface",
    css=".footer {display:none !important}",
    inputs=["text", "state"],
    outputs=["chatbot", "state"],
    title=title,
    description=description,
    allow_flagging="never",
    ).launch()