Duplicate from somosnlp/somos-alpaca-es

Co-authored-by: Daniel Vila <dvilasuero@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,5 @@
+FROM argilla/argilla-quickstart:latest
+
+COPY load_data.py /
+
+CMD whoami && /start_quickstart_argilla.sh

README.md

@@ -0,0 +1,13 @@
+---
+title: Hackathon SomosNLP Reto Datasets LLM Español
+emoji: 🦙 🏷️
+colorFrom: purple
+colorTo: red
+sdk: docker
+app_port: 6900
+fullWidth: true
+tags:
+- argilla
+- somosnlp
+duplicated_from: somosnlp/somos-alpaca-es
+---

load_data.py

@@ -0,0 +1,73 @@
+#  Copyright 2021-present, the Recognai S.L. team.
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+import sys
+import time
+
+import argilla as rg
+import pandas as pd
+import requests
+from argilla.labeling.text_classification import Rule, add_rules
+from datasets import load_dataset
+
+
+class LoadDatasets:
+    def __init__(self, api_key, workspace="team"):
+        rg.init(api_key=api_key, workspace=workspace)
+
+
+    @staticmethod
+    def load_somos():
+        print("Loading somos dataset")
+        # Leer el dataset del Hub
+        dataset = load_dataset("somosnlp/somos-alpaca-es", split="train")
+        dataset = dataset.remove_columns("metrics") # si falla se puede comentar esta linea
+        records = rg.DatasetForTextClassification.from_datasets(dataset)
+
+        # Log the dataset
+        rg.log(
+            records,
+            name="somos-alpaca-es",
+            tags={"description": "SomosNLP Hackathon dataset"},
+        )
+        settings = rg.TextClassificationSettings(
+            label_schema=["BAD INSTRUCTION", "BAD INPUT", "BAD OUTPUT", "INAPPROPRIATE", "BIASED", "ALL GOOD"]
+        )
+        rg.configure_dataset(name="somos-alpaca-es", settings=settings, workspace="team")
+
+
+if __name__ == "__main__":
+    API_KEY = sys.argv[1]
+    LOAD_DATASETS = sys.argv[2]
+
+    if LOAD_DATASETS.lower() == "none":
+        print("No datasets being loaded")
+    else:
+        while True:
+            try:
+                response = requests.get("http://0.0.0.0:6900/")
+                if response.status_code == 200:
+                    ld = LoadDatasets(API_KEY)
+
+                    ld.load_somos()
+                    break
+
+            except requests.exceptions.ConnectionError:
+                pass
+            except Exception as e:
+                print(e)
+                time.sleep(10)
+                pass
+
+            time.sleep(5)