Upload 7 files
Browse files- README.md +19 -0
- anscombe.json +49 -0
- config.json +25 -0
- model.safetensors +3 -0
- special_tokens_map.json +0 -0
- tokenizer_config.json +15 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
This directory includes a few sample datasets to get you started.
|
2 |
+
|
3 |
+
* `california_housing_data*.csv` is California housing data from the 1990 US
|
4 |
+
Census; more information is available at:
|
5 |
+
https://developers.google.com/machine-learning/crash-course/california-housing-data-description
|
6 |
+
|
7 |
+
* `mnist_*.csv` is a small sample of the
|
8 |
+
[MNIST database](https://en.wikipedia.org/wiki/MNIST_database), which is
|
9 |
+
described at: http://yann.lecun.com/exdb/mnist/
|
10 |
+
|
11 |
+
* `anscombe.json` contains a copy of
|
12 |
+
[Anscombe's quartet](https://en.wikipedia.org/wiki/Anscombe%27s_quartet); it
|
13 |
+
was originally described in
|
14 |
+
|
15 |
+
Anscombe, F. J. (1973). 'Graphs in Statistical Analysis'. American
|
16 |
+
Statistician. 27 (1): 17-21. JSTOR 2682899.
|
17 |
+
|
18 |
+
and our copy was prepared by the
|
19 |
+
[vega_datasets library](https://github.com/altair-viz/vega_datasets/blob/4f67bdaad10f45e3549984e17e1b3088c731503d/vega_datasets/_data/anscombe.json).
|
anscombe.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{"Series":"I", "X":10.0, "Y":8.04},
|
3 |
+
{"Series":"I", "X":8.0, "Y":6.95},
|
4 |
+
{"Series":"I", "X":13.0, "Y":7.58},
|
5 |
+
{"Series":"I", "X":9.0, "Y":8.81},
|
6 |
+
{"Series":"I", "X":11.0, "Y":8.33},
|
7 |
+
{"Series":"I", "X":14.0, "Y":9.96},
|
8 |
+
{"Series":"I", "X":6.0, "Y":7.24},
|
9 |
+
{"Series":"I", "X":4.0, "Y":4.26},
|
10 |
+
{"Series":"I", "X":12.0, "Y":10.84},
|
11 |
+
{"Series":"I", "X":7.0, "Y":4.81},
|
12 |
+
{"Series":"I", "X":5.0, "Y":5.68},
|
13 |
+
|
14 |
+
{"Series":"II", "X":10.0, "Y":9.14},
|
15 |
+
{"Series":"II", "X":8.0, "Y":8.14},
|
16 |
+
{"Series":"II", "X":13.0, "Y":8.74},
|
17 |
+
{"Series":"II", "X":9.0, "Y":8.77},
|
18 |
+
{"Series":"II", "X":11.0, "Y":9.26},
|
19 |
+
{"Series":"II", "X":14.0, "Y":8.10},
|
20 |
+
{"Series":"II", "X":6.0, "Y":6.13},
|
21 |
+
{"Series":"II", "X":4.0, "Y":3.10},
|
22 |
+
{"Series":"II", "X":12.0, "Y":9.13},
|
23 |
+
{"Series":"II", "X":7.0, "Y":7.26},
|
24 |
+
{"Series":"II", "X":5.0, "Y":4.74},
|
25 |
+
|
26 |
+
{"Series":"III", "X":10.0, "Y":7.46},
|
27 |
+
{"Series":"III", "X":8.0, "Y":6.77},
|
28 |
+
{"Series":"III", "X":13.0, "Y":12.74},
|
29 |
+
{"Series":"III", "X":9.0, "Y":7.11},
|
30 |
+
{"Series":"III", "X":11.0, "Y":7.81},
|
31 |
+
{"Series":"III", "X":14.0, "Y":8.84},
|
32 |
+
{"Series":"III", "X":6.0, "Y":6.08},
|
33 |
+
{"Series":"III", "X":4.0, "Y":5.39},
|
34 |
+
{"Series":"III", "X":12.0, "Y":8.15},
|
35 |
+
{"Series":"III", "X":7.0, "Y":6.42},
|
36 |
+
{"Series":"III", "X":5.0, "Y":5.73},
|
37 |
+
|
38 |
+
{"Series":"IV", "X":8.0, "Y":6.58},
|
39 |
+
{"Series":"IV", "X":8.0, "Y":5.76},
|
40 |
+
{"Series":"IV", "X":8.0, "Y":7.71},
|
41 |
+
{"Series":"IV", "X":8.0, "Y":8.84},
|
42 |
+
{"Series":"IV", "X":8.0, "Y":8.47},
|
43 |
+
{"Series":"IV", "X":8.0, "Y":7.04},
|
44 |
+
{"Series":"IV", "X":8.0, "Y":5.25},
|
45 |
+
{"Series":"IV", "X":19.0, "Y":12.50},
|
46 |
+
{"Series":"IV", "X":8.0, "Y":5.56},
|
47 |
+
{"Series":"IV", "X":8.0, "Y":7.91},
|
48 |
+
{"Series":"IV", "X":8.0, "Y":6.89}
|
49 |
+
]
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"transformers_version": "4.40.2",
|
22 |
+
"type_vocab_size": 2,
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81b4a6d0ba162f11f32dfe3e0ba315d9696bd3d862e495adb3e870bcaf85e97b
|
3 |
+
size 437951296
|
special_tokens_map.json
ADDED
File without changes
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_lower_case": true,
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"never_split": null,
|
5 |
+
"unk_token": "[UNK]",
|
6 |
+
"sep_token": "[SEP]",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"cls_token": "[CLS]",
|
9 |
+
"mask_token": "[MASK]",
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"strip_accents": null,
|
12 |
+
"model_max_length": 512,
|
13 |
+
"tokenizer_file": "/root/.cache/huggingface/hub/models--bert-base-uncased/snapshots/86b5e0934494bd15c9632b12f734a8a67f723594/tokenizer.json",
|
14 |
+
"name_or_path": "bert-base-uncased"
|
15 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|