Upload 7 files

instruct_med_dataset.hf/data-00000-of-00005.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:385ac79f7119adc73a706f2b55288e89650a1acb18df7271fb477205caa995a7
+size 466470304

instruct_med_dataset.hf/data-00001-of-00005.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9744e85decc4a2f617223cd42c248b2f3437b4aff6ba94a0e554a0591446a186
+size 470409624

instruct_med_dataset.hf/data-00002-of-00005.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8f8ac4f1b10bfecbcffe6a4461138c7d4c987dfdfd74b4815db64661230d9b9
+size 471381784

instruct_med_dataset.hf/data-00003-of-00005.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:438edcc8f61539ffaac7f9acf2c109e6916a64c5433d73dec90fa7cdb68af89d
+size 464955888

instruct_med_dataset.hf/data-00004-of-00005.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b78604ac776c9d2448bf0736c14ff9dab23b22653596424afcf150cde0638cd3
+size 469655192

instruct_med_dataset.hf/dataset_info.json

@@ -0,0 +1,12 @@
+{
+  "citation": "@article{Cohan_2018,\n   title={A Discourse-Aware Attention Model for Abstractive Summarization of\n            Long Documents},\n   url={http://dx.doi.org/10.18653/v1/n18-2097},\n   DOI={10.18653/v1/n18-2097},\n   journal={Proceedings of the 2018 Conference of the North American Chapter of\n          the Association for Computational Linguistics: Human Language\n          Technologies, Volume 2 (Short Papers)},\n   publisher={Association for Computational Linguistics},\n   author={Cohan, Arman and Dernoncourt, Franck and Kim, Doo Soon and Bui, Trung and Kim, Seokhwan and Chang, Walter and Goharian, Nazli},\n   year={2018}\n}",
+  "description": "Scientific papers datasets contains two sets of long and structured documents.\nThe datasets are obtained from ArXiv and PubMed OpenAccess repositories.\n\nBoth \"arxiv\" and \"pubmed\" have two features:\n  - article: the body of the document, pagragraphs seperated by \"/n\".\n  - abstract: the abstract of the document, pagragraphs seperated by \"/n\".\n  - section_names: titles of sections, seperated by \"/n\".",
+  "features": {
+    "text": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "https://github.com/armancohan/long-summarization",
+  "license": ""
+}

instruct_med_dataset.hf/state.json

@@ -0,0 +1,27 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00005.arrow"
+    },
+    {
+      "filename": "data-00001-of-00005.arrow"
+    },
+    {
+      "filename": "data-00002-of-00005.arrow"
+    },
+    {
+      "filename": "data-00003-of-00005.arrow"
+    },
+    {
+      "filename": "data-00004-of-00005.arrow"
+    }
+  ],
+  "_fingerprint": "8c606ef2269c391c",
+  "_format_columns": [
+    "text"
+  ],
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}