Add tamil-alpaca dataset
Browse files- dataset_dict.json +1 -0
- train/data-00000-of-00001.arrow +3 -0
- train/dataset_info.json +54 -0
- train/state.json +13 -0
dataset_dict.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"splits": ["train"]}
|
train/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:150cb7b883218bad1107aec27ed80810dc7ea2a6f952daf70031258848ea4651
|
| 3 |
+
size 287588720
|
train/dataset_info.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"builder_name": "parquet",
|
| 3 |
+
"citation": "",
|
| 4 |
+
"config_name": "default",
|
| 5 |
+
"dataset_name": "tamil-alpaca",
|
| 6 |
+
"dataset_size": 287556653,
|
| 7 |
+
"description": "",
|
| 8 |
+
"download_checksums": {
|
| 9 |
+
"hf://datasets/abhinand/tamil-alpaca@9d49f06c4096983e6508aa7f59d4d41396418183/data/train-00000-of-00001-e96a6e4e7f400cce.parquet": {
|
| 10 |
+
"num_bytes": 84685618,
|
| 11 |
+
"checksum": null
|
| 12 |
+
}
|
| 13 |
+
},
|
| 14 |
+
"download_size": 84685618,
|
| 15 |
+
"features": {
|
| 16 |
+
"instruction": {
|
| 17 |
+
"dtype": "string",
|
| 18 |
+
"_type": "Value"
|
| 19 |
+
},
|
| 20 |
+
"input": {
|
| 21 |
+
"dtype": "string",
|
| 22 |
+
"_type": "Value"
|
| 23 |
+
},
|
| 24 |
+
"output": {
|
| 25 |
+
"dtype": "string",
|
| 26 |
+
"_type": "Value"
|
| 27 |
+
},
|
| 28 |
+
"text": {
|
| 29 |
+
"dtype": "string",
|
| 30 |
+
"_type": "Value"
|
| 31 |
+
},
|
| 32 |
+
"system_prompt": {
|
| 33 |
+
"dtype": "string",
|
| 34 |
+
"_type": "Value"
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"homepage": "",
|
| 38 |
+
"license": "",
|
| 39 |
+
"size_in_bytes": 372242271,
|
| 40 |
+
"splits": {
|
| 41 |
+
"train": {
|
| 42 |
+
"name": "train",
|
| 43 |
+
"num_bytes": 287556653,
|
| 44 |
+
"num_examples": 51876,
|
| 45 |
+
"dataset_name": "tamil-alpaca"
|
| 46 |
+
}
|
| 47 |
+
},
|
| 48 |
+
"version": {
|
| 49 |
+
"version_str": "0.0.0",
|
| 50 |
+
"major": 0,
|
| 51 |
+
"minor": 0,
|
| 52 |
+
"patch": 0
|
| 53 |
+
}
|
| 54 |
+
}
|
train/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "62355923ee8e75eb",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": "train"
|
| 13 |
+
}
|