feat: add instruct readme

pwr-ai · Aug 30, 2024 · b1af463 · b1af463
1 parent a9cc9b3
commit b1af463
Show file tree

Hide file tree

Showing 6 changed files with 466 additions and 40 deletions.
diff --git a/data/datasets/en/readme/.gitignore b/data/datasets/en/readme/.gitignore
@@ -0,0 +1,2 @@
+/raw
+/instruct
diff --git a/dvc.lock b/dvc.lock
@@ -169,20 +169,6 @@ stages:
       hash: md5
       md5: 3b3589929112cb2f199044d240e87bcc
       size: 305
-  instruct_dataset_readme:
-    cmd: jupyter nbconvert  --no-input  --to markdown  --execute nbs/Data/03_Dataset_Description_Instruct.ipynb
-      --output-dir data/datasets/pl/readme/instruct --output README
-    deps:
-    - path: nbs/Data/03_Dataset_Description_Instruct.ipynb
-      hash: md5
-      md5: 27e6d517445028d45e5c40b22febece4
-      size: 16215
-    outs:
-    - path: data/datasets/pl/readme/instruct/
-      hash: md5
-      md5: de02794df3d74d86f8610f040a17dcbe.dir
-      size: 144326
-      nfiles: 5
   predict@Unsloth-Llama-3-8B-Instruct:
     cmd: PYTHONPATH=. python scripts/sft/predict.py model=Unsloth-Llama-3-8B-Instruct
     deps:
@@ -4947,3 +4933,31 @@ stages:
       hash: md5
       md5: 4edc8fe239f53890d71291f61b6cc96c
       size: 486
+  instruct_dataset_readme@1:
+    cmd: jupyter nbconvert --no-input --to markdown --execute "nbs/Dataset Cards/05_Dataset_Description_en_court_instruct.ipynb"
+      --output-dir data/datasets/en/readme/instruct --output README
+    deps:
+    - path: nbs/Dataset Cards/05_Dataset_Description_en_court_instruct.ipynb
+      hash: md5
+      md5: da1eb2132a552e2de52e42fc827ecef8
+      size: 14220
+    outs:
+    - path: data/datasets/en/readme/instruct
+      hash: md5
+      md5: dd812ae1518c3c934945b916aa9e5bfc.dir
+      size: 67727
+      nfiles: 3
+  instruct_dataset_readme@0:
+    cmd: jupyter nbconvert --no-input --to markdown --execute "nbs/Dataset Cards/02_Dataset_Description_Instruct.ipynb"
+      --output-dir data/datasets/pl/readme/instruct --output README
+    deps:
+    - path: nbs/Dataset Cards/02_Dataset_Description_Instruct.ipynb
+      hash: md5
+      md5: 1212931a887a1e4ab1939234554b4795
+      size: 16026
+    outs:
+    - path: data/datasets/pl/readme/instruct
+      hash: md5
+      md5: 5a7c4f784f826e2214d39decfd1c4625.dir
+      size: 206279
+      nfiles: 7
diff --git a/dvc.yaml b/dvc.yaml
@@ -17,17 +17,23 @@ stages:
       - data/datasets/pl/readme/raw/
 
   instruct_dataset_readme:
-    cmd: >-
-      jupyter nbconvert
-      --no-input
-      --to markdown
-      --execute nbs/Data/03_Dataset_Description_Instruct.ipynb
-      --output-dir data/datasets/pl/readme/instruct
-      --output README
-    deps:
-      - nbs/Data/03_Dataset_Description_Instruct.ipynb
-    outs:
-      - data/datasets/pl/readme/instruct/
+    foreach:
+      - notebook: "nbs/Dataset Cards/02_Dataset_Description_Instruct.ipynb"
+        output_dir: data/datasets/pl/readme/instruct
+      - notebook: "nbs/Dataset Cards/05_Dataset_Description_en_court_instruct.ipynb"
+        output_dir: data/datasets/en/readme/instruct
+    do:
+      cmd: >-
+        jupyter nbconvert
+        --no-input
+        --to markdown
+        --execute "${item.notebook}"
+        --output-dir ${item.output_dir}
+        --output README
+      deps:
+        - ${item.notebook}
+      outs:
+        - ${item.output_dir}
 
   build_instruct_dataset_pl:
     cmd: >-

diff --git a/nbs/Dataset Cards/02_Dataset_Description_Instruct.ipynb b/nbs/Dataset Cards/02_Dataset_Description_Instruct.ipynb
@@ -1,5 +1,15 @@
 {
  "cells": [
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": [
+    "---\n",
+    "{{ card_data }}\n",
+    "---"
+   ],
+   "id": "ba43c85ce14e7af6"
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -74,7 +84,7 @@
     "## Dataset Description\n",
     "\n",
     "* **Homepage: TBA**\n",
-    "* **Repository: [github](https://github.com/pwr-ai/JuDDGES)**\n",
+    "* **Repository: https://github.com/pwr-ai/JuDDGES**\n",
     "* **Paper:  TBA**\n",
     "* **Point of Contact: [email protected]; [email protected]; [email protected]**\n",
     "\n",
@@ -258,7 +268,7 @@
     "\n",
     "### Licensing Information\n",
     "\n",
-    "[More Information Needed]\n",
+    "We license the actual packaging of these data under Attribution 4.0 International (CC BY 4.0) https://creativecommons.org/licenses/by/4.0/\n",
     "\n",
     "### Citation Information\n",
     "\n",