Librarian Bot: Add base_model information to model
#2
by
librarian-bot
- opened
README.md
CHANGED
@@ -1,134 +1,74 @@
|
|
1 |
---
|
|
|
|
|
2 |
license:
|
3 |
- apache-2.0
|
4 |
- cc-by-nc-4.0
|
5 |
-
datasets: pszemraj/fleece2instructions-codealpaca
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
- instruct
|
9 |
- instructions
|
10 |
- code
|
11 |
- instructiongen
|
|
|
12 |
metrics:
|
13 |
- rouge
|
14 |
-
language:
|
15 |
-
- en
|
16 |
widget:
|
17 |
-
- text:
|
18 |
-
|
19 |
huggingface-cli lfs-enable-largefiles .
|
|
|
20 |
git lfs track "*.bin"
|
|
|
21 |
git add .
|
|
|
22 |
git commit -a -m "add fp32 chkpt"
|
|
|
23 |
git push
|
|
|
|
|
24 |
example_title: bash
|
25 |
-
- text:
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
}
|
32 |
-
|
33 |
-
/**
|
34 |
-
* Interface for interacting with a document.
|
35 |
-
*/
|
36 |
-
export class Document implements DocumentParams {
|
37 |
-
pageContent: string;
|
38 |
-
|
39 |
-
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
40 |
-
metadata: Record<string, any>;
|
41 |
-
|
42 |
-
constructor(fields?: Partial<DocumentParams>) {
|
43 |
-
this.pageContent = fields?.pageContent ?? this.pageContent;
|
44 |
-
this.metadata = fields?.metadata ?? {};
|
45 |
-
}
|
46 |
-
}
|
47 |
example_title: js
|
48 |
-
- text:
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
if len(right)
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
index_left = index_right = 0
|
58 |
-
|
59 |
-
while len(result) < len(left) + len(right):
|
60 |
-
if left[index_left] <= right[index_right]:
|
61 |
-
result.append(left[index_left])
|
62 |
-
index_left += 1
|
63 |
-
else:
|
64 |
-
result.append(right[index_right])
|
65 |
-
index_right += 1
|
66 |
-
|
67 |
-
if index_right == len(right):
|
68 |
-
result += left[index_left:]
|
69 |
-
break
|
70 |
-
|
71 |
-
if index_left == len(left):
|
72 |
-
result += right[index_right:]
|
73 |
-
break
|
74 |
-
|
75 |
-
return result
|
76 |
example_title: merge
|
77 |
-
- text:
|
78 |
-
|
79 |
-
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
df =
|
84 |
-
pd.read_csv('https://raw.githubusercontent.com/plotly/datasets/master/2014_apple_stock.csv')
|
85 |
-
|
86 |
-
|
87 |
-
fig = go.Figure(go.Scatter(x = df['AAPL_x'], y = df['AAPL_y'],
|
88 |
-
name='Share Prices (in USD)'))
|
89 |
-
|
90 |
-
fig.update_layout(title='Apple Share Prices over time (2014)',
|
91 |
-
plot_bgcolor='rgb(230, 230,230)',
|
92 |
-
showlegend=True)
|
93 |
-
|
94 |
-
fig.show()
|
95 |
example_title: plot
|
96 |
-
- text:
|
97 |
-
|
98 |
-
|
99 |
-
|
100 |
-
|
101 |
-
|
102 |
-
|
103 |
-
|
104 |
-
|
105 |
-
|
106 |
-
|
107 |
-
|
108 |
-
|
109 |
-
|
110 |
-
|
111 |
-
before_text = [
|
112 |
-
char for char in full_before_text.split()[-1] if char.isalpha()
|
113 |
-
]
|
114 |
-
before_text = "".join(before_text)
|
115 |
-
full_after_text = text.split(match_token, maxsplit=1)[-1]
|
116 |
-
after_text = [char for char in full_after_text.split()[0] if char.isalpha()]
|
117 |
-
after_text = "".join(after_text)
|
118 |
-
full_text = before_text + after_text
|
119 |
-
if check_word_spelling(full_text):
|
120 |
-
text = full_before_text + full_after_text
|
121 |
-
else:
|
122 |
-
text = full_before_text + " " + full_after_text
|
123 |
-
if match_token not in text:
|
124 |
-
break
|
125 |
-
return text
|
126 |
-
|
127 |
-
text = "I- am- a go- od- boy"
|
128 |
-
eval_and_replace(text)
|
129 |
example_title: spell check
|
130 |
-
- text:
|
131 |
-
import torch
|
132 |
|
133 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
134 |
|
@@ -139,19 +79,21 @@ widget:
|
|
139 |
|
140 |
model = AutoModelForSequenceClassification.from_pretrained(checkpoint)
|
141 |
|
142 |
-
sequences = ["I've been waiting for a HuggingFace course my whole life.",
|
143 |
-
|
144 |
|
145 |
|
146 |
-
tokens = tokenizer(sequences, padding=True, truncation=True,
|
147 |
-
return_tensors="pt")
|
148 |
|
149 |
output = model(**tokens)
|
|
|
|
|
150 |
example_title: model inference
|
151 |
inference:
|
152 |
parameters:
|
153 |
max_length: 96
|
154 |
num_beams: 4
|
|
|
155 |
---
|
156 |
|
157 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
license:
|
5 |
- apache-2.0
|
6 |
- cc-by-nc-4.0
|
|
|
7 |
tags:
|
8 |
- generated_from_trainer
|
9 |
- instruct
|
10 |
- instructions
|
11 |
- code
|
12 |
- instructiongen
|
13 |
+
datasets: pszemraj/fleece2instructions-codealpaca
|
14 |
metrics:
|
15 |
- rouge
|
|
|
|
|
16 |
widget:
|
17 |
+
- text: 'git lfs install
|
18 |
+
|
19 |
huggingface-cli lfs-enable-largefiles .
|
20 |
+
|
21 |
git lfs track "*.bin"
|
22 |
+
|
23 |
git add .
|
24 |
+
|
25 |
git commit -a -m "add fp32 chkpt"
|
26 |
+
|
27 |
git push
|
28 |
+
|
29 |
+
'
|
30 |
example_title: bash
|
31 |
+
- text: "export interface DocumentParams {\n pageContent: string;\n\n // eslint-disable-next-line\
|
32 |
+
\ @typescript-eslint/no-explicit-any\n metadata: Record<string, any>;\n}\n\n\
|
33 |
+
/**\n * Interface for interacting with a document.\n */\nexport class Document\
|
34 |
+
\ implements DocumentParams {\n pageContent: string;\n\n // eslint-disable-next-line\
|
35 |
+
\ @typescript-eslint/no-explicit-any\n metadata: Record<string, any>;\n\n constructor(fields?:\
|
36 |
+
\ Partial<DocumentParams>) {\n this.pageContent = fields?.pageContent ?? this.pageContent;\n\
|
37 |
+
\ this.metadata = fields?.metadata ?? {};\n }\n}\n"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
example_title: js
|
39 |
+
- text: "def merge(left, right):\n if len(left) == 0:\n return right\n\n\
|
40 |
+
\ if len(right) == 0:\n return left\n\n result = []\n index_left\
|
41 |
+
\ = index_right = 0\n\n while len(result) < len(left) + len(right):\n \
|
42 |
+
\ if left[index_left] <= right[index_right]:\n result.append(left[index_left])\n\
|
43 |
+
\ index_left += 1\n else:\n result.append(right[index_right])\n\
|
44 |
+
\ index_right += 1\n\n if index_right == len(right):\n \
|
45 |
+
\ result += left[index_left:]\n break\n\n if index_left\
|
46 |
+
\ == len(left):\n result += right[index_right:]\n break\n\
|
47 |
+
\n return result\n"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
example_title: merge
|
49 |
+
- text: "import pandas as pd\nimport plotly.graph_objects as go\n\ndf = pd.read_csv('https://raw.githubusercontent.com/plotly/datasets/master/2014_apple_stock.csv')\n\
|
50 |
+
\nfig = go.Figure(go.Scatter(x = df['AAPL_x'], y = df['AAPL_y'],\n \
|
51 |
+
\ name='Share Prices (in USD)'))\n\nfig.update_layout(title='Apple Share\
|
52 |
+
\ Prices over time (2014)',\n plot_bgcolor='rgb(230, 230,230)',\n\
|
53 |
+
\ showlegend=True)\n\nfig.show()\n"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
example_title: plot
|
55 |
+
- text: "from spellchecker import SpellChecker\n\nspell = SpellChecker()\n\ndef check_word_spelling(word:\
|
56 |
+
\ str):\n misspelled = spell.unknown([word])\n return len(misspelled) ==\
|
57 |
+
\ 0\n\ndef eval_and_replace(text: str, match_token: str = \"- \"):\n if match_token\
|
58 |
+
\ not in text:\n return text\n else:\n while True:\n \
|
59 |
+
\ full_before_text = text.split(match_token, maxsplit=1)[0]\n before_text\
|
60 |
+
\ = [\n char for char in full_before_text.split()[-1] if char.isalpha()\n\
|
61 |
+
\ ]\n before_text = \"\".join(before_text)\n \
|
62 |
+
\ full_after_text = text.split(match_token, maxsplit=1)[-1]\n after_text\
|
63 |
+
\ = [char for char in full_after_text.split()[0] if char.isalpha()]\n \
|
64 |
+
\ after_text = \"\".join(after_text)\n full_text = before_text +\
|
65 |
+
\ after_text\n if check_word_spelling(full_text):\n \
|
66 |
+
\ text = full_before_text + full_after_text\n else:\n \
|
67 |
+
\ text = full_before_text + \" \" + full_after_text\n if match_token\
|
68 |
+
\ not in text:\n break\n return text\n\ntext = \"I- am-\
|
69 |
+
\ a go- od- boy\"\neval_and_replace(text)\n"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
example_title: spell check
|
71 |
+
- text: 'import torch
|
|
|
72 |
|
73 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
74 |
|
|
|
79 |
|
80 |
model = AutoModelForSequenceClassification.from_pretrained(checkpoint)
|
81 |
|
82 |
+
sequences = ["I''ve been waiting for a HuggingFace course my whole life.", "So
|
83 |
+
have I!"]
|
84 |
|
85 |
|
86 |
+
tokens = tokenizer(sequences, padding=True, truncation=True, return_tensors="pt")
|
|
|
87 |
|
88 |
output = model(**tokens)
|
89 |
+
|
90 |
+
'
|
91 |
example_title: model inference
|
92 |
inference:
|
93 |
parameters:
|
94 |
max_length: 96
|
95 |
num_beams: 4
|
96 |
+
base_model: facebook/bart-large
|
97 |
---
|
98 |
|
99 |
|