Spaces:
Sleeping
Sleeping
add cc file
Browse files- CC-MAIN-20231128083443-20231128113443-00000.warc.gz +3 -0
- app.py +24 -0
- requirements.txt +1 -0
CC-MAIN-20231128083443-20231128113443-00000.warc.gz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a754b9a848ffaf00ba1621ad4577a31ce3176b058c3ed21cb3665954b7ae7cf
|
| 3 |
+
size 1208969113
|
app.py
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from itertools import islice
|
| 2 |
+
|
| 3 |
+
import gradio as gr
|
| 4 |
+
from datatrove.executor.local import LocalPipelineExecutor
|
| 5 |
+
from datatrove.pipeline.base import PipelineStep
|
| 6 |
+
from datatrove.pipeline.extractors import Trafilatura
|
| 7 |
+
from datatrove.pipeline.filters import (
|
| 8 |
+
C4QualityFilter,
|
| 9 |
+
FineWebQualityFilter,
|
| 10 |
+
GopherQualityFilter,
|
| 11 |
+
GopherRepetitionFilter,
|
| 12 |
+
LanguageFilter,
|
| 13 |
+
URLFilter,
|
| 14 |
+
)
|
| 15 |
+
from datatrove.pipeline.readers import WarcReader
|
| 16 |
+
from datatrove.pipeline.writers.jsonl import JsonlWriter
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
def run(input):
|
| 20 |
+
return "wip"
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
demo = gr.Interface(run, inputs=[gr.Textbox()], outputs=[gr.Textbox()])
|
| 24 |
+
demo.launch()
|
requirements.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
datatrove[all]
|