Skip to content

Commit 5ddd60e

Browse files
lewtunlewtun
authored
Add per-language folder for course nbs (#235)
1 parent 2edceca commit 5ddd60e

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

61 files changed

+25206
-1
lines changed

‎.github/pull_request_template.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ Someone will review your PR shortly (see the section "Who can review?" below to
77
88
Note: the notebooks in the `course` and `transformers_doc` directories are auto-generated, so are best fixed at their source. Instead, follow the instructions below for these notebooks:
99
10-
- `course`: Create a post on our forums and tag @lewtun (https://discuss.huggingface.co/c/course/20)
10+
- `course`: Open a PR directly on the `course` repo (https://github.com/huggingface/course)
1111
- `transformers_doc`: Open a PR directly on the `transformers` repo (https://github.com/huggingface/transformers)
1212
1313
-->

‎course/en/chapter1/section3.ipynb

+322
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,322 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "markdown",
5+
"metadata": {},
6+
"source": [
7+
"# Transformers, what can they do?"
8+
]
9+
},
10+
{
11+
"cell_type": "markdown",
12+
"metadata": {},
13+
"source": [
14+
"Install the Transformers, Datasets, and Evaluate libraries to run this notebook."
15+
]
16+
},
17+
{
18+
"cell_type": "code",
19+
"execution_count": null,
20+
"metadata": {},
21+
"outputs": [],
22+
"source": [
23+
"!pip install datasets evaluate transformers[sentencepiece]"
24+
]
25+
},
26+
{
27+
"cell_type": "code",
28+
"execution_count": null,
29+
"metadata": {},
30+
"outputs": [
31+
{
32+
"data": {
33+
"text/plain": [
34+
"[{'label': 'POSITIVE', 'score': 0.9598047137260437}]"
35+
]
36+
},
37+
"execution_count": null,
38+
"metadata": {},
39+
"output_type": "execute_result"
40+
}
41+
],
42+
"source": [
43+
"from transformers import pipeline\n",
44+
"\n",
45+
"classifier = pipeline(\"sentiment-analysis\")\n",
46+
"classifier(\"I've been waiting for a HuggingFace course my whole life.\")"
47+
]
48+
},
49+
{
50+
"cell_type": "code",
51+
"execution_count": null,
52+
"metadata": {},
53+
"outputs": [
54+
{
55+
"data": {
56+
"text/plain": [
57+
"[{'label': 'POSITIVE', 'score': 0.9598047137260437},\n",
58+
" {'label': 'NEGATIVE', 'score': 0.9994558095932007}]"
59+
]
60+
},
61+
"execution_count": null,
62+
"metadata": {},
63+
"output_type": "execute_result"
64+
}
65+
],
66+
"source": [
67+
"classifier(\n",
68+
" [\"I've been waiting for a HuggingFace course my whole life.\", \"I hate this so much!\"]\n",
69+
")"
70+
]
71+
},
72+
{
73+
"cell_type": "code",
74+
"execution_count": null,
75+
"metadata": {},
76+
"outputs": [
77+
{
78+
"data": {
79+
"text/plain": [
80+
"{'sequence': 'This is a course about the Transformers library',\n",
81+
" 'labels': ['education', 'business', 'politics'],\n",
82+
" 'scores': [0.8445963859558105, 0.111976258456707, 0.043427448719739914]}"
83+
]
84+
},
85+
"execution_count": null,
86+
"metadata": {},
87+
"output_type": "execute_result"
88+
}
89+
],
90+
"source": [
91+
"from transformers import pipeline\n",
92+
"\n",
93+
"classifier = pipeline(\"zero-shot-classification\")\n",
94+
"classifier(\n",
95+
" \"This is a course about the Transformers library\",\n",
96+
" candidate_labels=[\"education\", \"politics\", \"business\"],\n",
97+
")"
98+
]
99+
},
100+
{
101+
"cell_type": "code",
102+
"execution_count": null,
103+
"metadata": {},
104+
"outputs": [
105+
{
106+
"data": {
107+
"text/plain": [
108+
"[{'generated_text': 'In this course, we will teach you how to understand and use '\n",
109+
" 'data flow and data interchange when handling user data. We '\n",
110+
" 'will be working with one or more of the most commonly used '\n",
111+
" 'data flows — data flows of various types, as seen by the '\n",
112+
" 'HTTP'}]"
113+
]
114+
},
115+
"execution_count": null,
116+
"metadata": {},
117+
"output_type": "execute_result"
118+
}
119+
],
120+
"source": [
121+
"from transformers import pipeline\n",
122+
"\n",
123+
"generator = pipeline(\"text-generation\")\n",
124+
"generator(\"In this course, we will teach you how to\")"
125+
]
126+
},
127+
{
128+
"cell_type": "code",
129+
"execution_count": null,
130+
"metadata": {},
131+
"outputs": [
132+
{
133+
"data": {
134+
"text/plain": [
135+
"[{'generated_text': 'In this course, we will teach you how to manipulate the world and '\n",
136+
" 'move your mental and physical capabilities to your advantage.'},\n",
137+
" {'generated_text': 'In this course, we will teach you how to become an expert and '\n",
138+
" 'practice realtime, and with a hands on experience on both real '\n",
139+
" 'time and real'}]"
140+
]
141+
},
142+
"execution_count": null,
143+
"metadata": {},
144+
"output_type": "execute_result"
145+
}
146+
],
147+
"source": [
148+
"from transformers import pipeline\n",
149+
"\n",
150+
"generator = pipeline(\"text-generation\", model=\"distilgpt2\")\n",
151+
"generator(\n",
152+
" \"In this course, we will teach you how to\",\n",
153+
" max_length=30,\n",
154+
" num_return_sequences=2,\n",
155+
")"
156+
]
157+
},
158+
{
159+
"cell_type": "code",
160+
"execution_count": null,
161+
"metadata": {},
162+
"outputs": [
163+
{
164+
"data": {
165+
"text/plain": [
166+
"[{'sequence': 'This course will teach you all about mathematical models.',\n",
167+
" 'score': 0.19619831442832947,\n",
168+
" 'token': 30412,\n",
169+
" 'token_str': ' mathematical'},\n",
170+
" {'sequence': 'This course will teach you all about computational models.',\n",
171+
" 'score': 0.04052725434303284,\n",
172+
" 'token': 38163,\n",
173+
" 'token_str': ' computational'}]"
174+
]
175+
},
176+
"execution_count": null,
177+
"metadata": {},
178+
"output_type": "execute_result"
179+
}
180+
],
181+
"source": [
182+
"from transformers import pipeline\n",
183+
"\n",
184+
"unmasker = pipeline(\"fill-mask\")\n",
185+
"unmasker(\"This course will teach you all about <mask> models.\", top_k=2)"
186+
]
187+
},
188+
{
189+
"cell_type": "code",
190+
"execution_count": null,
191+
"metadata": {},
192+
"outputs": [
193+
{
194+
"data": {
195+
"text/plain": [
196+
"[{'entity_group': 'PER', 'score': 0.99816, 'word': 'Sylvain', 'start': 11, 'end': 18}, \n",
197+
" {'entity_group': 'ORG', 'score': 0.97960, 'word': 'Hugging Face', 'start': 33, 'end': 45}, \n",
198+
" {'entity_group': 'LOC', 'score': 0.99321, 'word': 'Brooklyn', 'start': 49, 'end': 57}\n",
199+
"]"
200+
]
201+
},
202+
"execution_count": null,
203+
"metadata": {},
204+
"output_type": "execute_result"
205+
}
206+
],
207+
"source": [
208+
"from transformers import pipeline\n",
209+
"\n",
210+
"ner = pipeline(\"ner\", grouped_entities=True)\n",
211+
"ner(\"My name is Sylvain and I work at Hugging Face in Brooklyn.\")"
212+
]
213+
},
214+
{
215+
"cell_type": "code",
216+
"execution_count": null,
217+
"metadata": {},
218+
"outputs": [
219+
{
220+
"data": {
221+
"text/plain": [
222+
"{'score': 0.6385916471481323, 'start': 33, 'end': 45, 'answer': 'Hugging Face'}"
223+
]
224+
},
225+
"execution_count": null,
226+
"metadata": {},
227+
"output_type": "execute_result"
228+
}
229+
],
230+
"source": [
231+
"from transformers import pipeline\n",
232+
"\n",
233+
"question_answerer = pipeline(\"question-answering\")\n",
234+
"question_answerer(\n",
235+
" question=\"Where do I work?\",\n",
236+
" context=\"My name is Sylvain and I work at Hugging Face in Brooklyn\",\n",
237+
")"
238+
]
239+
},
240+
{
241+
"cell_type": "code",
242+
"execution_count": null,
243+
"metadata": {},
244+
"outputs": [
245+
{
246+
"data": {
247+
"text/plain": [
248+
"[{'summary_text': ' America has changed dramatically during recent years . The '\n",
249+
" 'number of engineering graduates in the U.S. has declined in '\n",
250+
" 'traditional engineering disciplines such as mechanical, civil '\n",
251+
" ', electrical, chemical, and aeronautical engineering . Rapidly '\n",
252+
" 'developing economies such as China and India, as well as other '\n",
253+
" 'industrial countries in Europe and Asia, continue to encourage '\n",
254+
" 'and advance engineering .'}]"
255+
]
256+
},
257+
"execution_count": null,
258+
"metadata": {},
259+
"output_type": "execute_result"
260+
}
261+
],
262+
"source": [
263+
"from transformers import pipeline\n",
264+
"\n",
265+
"summarizer = pipeline(\"summarization\")\n",
266+
"summarizer(\n",
267+
" \"\"\"\n",
268+
" America has changed dramatically during recent years. Not only has the number of \n",
269+
" graduates in traditional engineering disciplines such as mechanical, civil, \n",
270+
" electrical, chemical, and aeronautical engineering declined, but in most of \n",
271+
" the premier American universities engineering curricula now concentrate on \n",
272+
" and encourage largely the study of engineering science. As a result, there \n",
273+
" are declining offerings in engineering subjects dealing with infrastructure, \n",
274+
" the environment, and related issues, and greater concentration on high \n",
275+
" technology subjects, largely supporting increasingly complex scientific \n",
276+
" developments. While the latter is important, it should not be at the expense \n",
277+
" of more traditional engineering.\n",
278+
"\n",
279+
" Rapidly developing economies such as China and India, as well as other \n",
280+
" industrial countries in Europe and Asia, continue to encourage and advance \n",
281+
" the teaching of engineering. Both China and India, respectively, graduate \n",
282+
" six and eight times as many traditional engineers as does the United States. \n",
283+
" Other industrial countries at minimum maintain their output, while America \n",
284+
" suffers an increasingly serious decline in the number of engineering graduates \n",
285+
" and a lack of well-educated engineers.\n",
286+
"\"\"\"\n",
287+
")"
288+
]
289+
},
290+
{
291+
"cell_type": "code",
292+
"execution_count": null,
293+
"metadata": {},
294+
"outputs": [
295+
{
296+
"data": {
297+
"text/plain": [
298+
"[{'translation_text': 'This course is produced by Hugging Face.'}]"
299+
]
300+
},
301+
"execution_count": null,
302+
"metadata": {},
303+
"output_type": "execute_result"
304+
}
305+
],
306+
"source": [
307+
"from transformers import pipeline\n",
308+
"\n",
309+
"translator = pipeline(\"translation\", model=\"Helsinki-NLP/opus-mt-fr-en\")\n",
310+
"translator(\"Ce cours est produit par Hugging Face.\")"
311+
]
312+
}
313+
],
314+
"metadata": {
315+
"colab": {
316+
"name": "Transformers, what can they do?",
317+
"provenance": []
318+
}
319+
},
320+
"nbformat": 4,
321+
"nbformat_minor": 4
322+
}

‎course/en/chapter1/section8.ipynb

+63
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,63 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "markdown",
5+
"metadata": {},
6+
"source": [
7+
"# Bias and limitations"
8+
]
9+
},
10+
{
11+
"cell_type": "markdown",
12+
"metadata": {},
13+
"source": [
14+
"Install the Transformers, Datasets, and Evaluate libraries to run this notebook."
15+
]
16+
},
17+
{
18+
"cell_type": "code",
19+
"execution_count": null,
20+
"metadata": {},
21+
"outputs": [],
22+
"source": [
23+
"!pip install datasets evaluate transformers[sentencepiece]"
24+
]
25+
},
26+
{
27+
"cell_type": "code",
28+
"execution_count": null,
29+
"metadata": {},
30+
"outputs": [
31+
{
32+
"data": {
33+
"text/plain": [
34+
"['lawyer', 'carpenter', 'doctor', 'waiter', 'mechanic']\n",
35+
"['nurse', 'waitress', 'teacher', 'maid', 'prostitute']"
36+
]
37+
},
38+
"execution_count": null,
39+
"metadata": {},
40+
"output_type": "execute_result"
41+
}
42+
],
43+
"source": [
44+
"from transformers import pipeline\n",
45+
"\n",
46+
"unmasker = pipeline(\"fill-mask\", model=\"bert-base-uncased\")\n",
47+
"result = unmasker(\"This man works as a [MASK].\")\n",
48+
"print([r[\"token_str\"] for r in result])\n",
49+
"\n",
50+
"result = unmasker(\"This woman works as a [MASK].\")\n",
51+
"print([r[\"token_str\"] for r in result])"
52+
]
53+
}
54+
],
55+
"metadata": {
56+
"colab": {
57+
"name": "Bias and limitations",
58+
"provenance": []
59+
}
60+
},
61+
"nbformat": 4,
62+
"nbformat_minor": 4
63+
}

0 commit comments

Comments
 (0)