system HF staff commited on
Commit
e8503a6
1 Parent(s): 45f806f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +53 -21
README.md CHANGED
@@ -2,12 +2,22 @@
2
  language: en
3
  thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo_share.png?raw=true
4
  tags:
5
- - exbert
6
  - huggingtweets
7
  widget:
8
  - text: "My dream is"
9
  ---
10
 
 
 
 
 
 
 
 
 
 
 
 
11
  <div>
12
  <div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('http://pbs.twimg.com/profile_images/1259944219881455617/asyRCk6l_400x400.jpg')">
13
  </div>
@@ -19,10 +29,6 @@ I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
19
 
20
  Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
21
 
22
- <a href="https://huggingface.co/exbert/?model=huggingtweets/thom_wolf&modelKind=autoregressive&sentence=I%20love%20huggingtweets!&layer=11">
23
- <img width="300px" src="https://hf-dinosaur.huggingface.co/exbert/button.png">
24
- </a>
25
-
26
  ## How does it work?
27
 
28
  The model uses the following pipeline.
@@ -35,34 +41,56 @@ To understand how the model was developed, check the [W&B report](https://bit.ly
35
 
36
  The model was trained on [@thom_wolf's tweets](https://twitter.com/thom_wolf).
37
 
38
- | Data | Quantity |
39
- |-------------------|--------------|
40
- | Tweets downloaded | 1198 |
41
- | Retweets | 308 |
42
- | Short tweets | 69 |
43
- | Tweets kept | 821 |
44
-
45
- [Explore the data](https://app.wandb.ai/wandb/huggingtweets-dev/runs/2tx1byc8/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
 
47
  ## Training procedure
48
 
49
  The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @thom_wolf's tweets.
50
 
51
- Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets-dev/runs/279bqvj2) for full transparency and reproducibility.
 
 
52
 
53
  ## Intended uses & limitations
54
 
55
- #### How to use
56
 
57
  You can use this model directly with a pipeline for text generation:
58
 
59
- ```python
60
- from transformers import pipeline
61
- generator = pipeline('text-generation', model='huggingtweets/thom_wolf')
62
- generator("My dream is", max_length=50, num_return_sequences=5)
63
- ```
64
 
65
- #### Limitations and bias
 
66
 
67
  The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
68
 
@@ -72,8 +100,12 @@ In addition, the data present in the user's tweets further affects the text gene
72
 
73
  *Built by Boris Dayma*
74
 
 
 
75
  [![Follow](https://img.shields.io/twitter/follow/borisdayma?style=social)](https://twitter.com/borisdayma)
76
 
 
77
  For more details, visit the project repository.
 
78
 
79
  [![GitHub stars](https://img.shields.io/github/stars/borisdayma/huggingtweets?style=social)](https://github.com/borisdayma/huggingtweets)
 
2
  language: en
3
  thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo_share.png?raw=true
4
  tags:
 
5
  - huggingtweets
6
  widget:
7
  - text: "My dream is"
8
  ---
9
 
10
+ <link rel="stylesheet" href="https://unpkg.com/@tailwindcss/typography@0.2.x/dist/typography.min.css">
11
+
12
+ <style>
13
+ @media (prefers-color-scheme: dark) {
14
+ .prose { color: #E2E8F0 !important; }
15
+ .prose h2, .prose h3, .prose a, .prose thead { color: #F7FAFC !important; }
16
+ }
17
+ </style>
18
+
19
+ <section class='prose'>
20
+
21
  <div>
22
  <div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('http://pbs.twimg.com/profile_images/1259944219881455617/asyRCk6l_400x400.jpg')">
23
  </div>
 
29
 
30
  Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
31
 
 
 
 
 
32
  ## How does it work?
33
 
34
  The model uses the following pipeline.
 
41
 
42
  The model was trained on [@thom_wolf's tweets](https://twitter.com/thom_wolf).
43
 
44
+ <table style='border-width:0'>
45
+ <thead style='border-width:0'>
46
+ <tr style='border-width:0 0 1px 0; border-color: #CBD5E0'>
47
+ <th style='border-width:0'>Data</th>
48
+ <th style='border-width:0'>Quantity</th>
49
+ </tr>
50
+ </thead>
51
+ <tbody style='border-width:0'>
52
+ <tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
53
+ <td style='border-width:0'>Tweets downloaded</td>
54
+ <td style='border-width:0'>1254</td>
55
+ </tr>
56
+ <tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
57
+ <td style='border-width:0'>Retweets</td>
58
+ <td style='border-width:0'>322</td>
59
+ </tr>
60
+ <tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
61
+ <td style='border-width:0'>Short tweets</td>
62
+ <td style='border-width:0'>74</td>
63
+ </tr>
64
+ <tr style='border-width:0'>
65
+ <td style='border-width:0'>Tweets kept</td>
66
+ <td style='border-width:0'>858</td>
67
+ </tr>
68
+ </tbody>
69
+ </table>
70
+
71
+ [Explore the data](https://app.wandb.ai/wandb/huggingtweets-dev/runs/6of2mk3b/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
72
 
73
  ## Training procedure
74
 
75
  The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @thom_wolf's tweets.
76
 
77
+ Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets-dev/runs/wpyus8pt) for full transparency and reproducibility.
78
+
79
+ At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets-dev/runs/wpyus8pt/artifacts) is logged and versioned.
80
 
81
  ## Intended uses & limitations
82
 
83
+ ### How to use
84
 
85
  You can use this model directly with a pipeline for text generation:
86
 
87
+ <pre><code><span style="color:#03A9F4">from</span> transformers <span style="color:#03A9F4">import</span> pipeline
88
+ generator = pipeline(<span style="color:#FF9800">'text-generation'</span>,
89
+ model=<span style="color:#FF9800">'huggingtweets/thom_wolf'</span>)
90
+ generator(<span style="color:#FF9800">"My dream is"</span>, num_return_sequences=<span style="color:#8BC34A">5</span>)</code></pre>
 
91
 
92
+
93
+ ### Limitations and bias
94
 
95
  The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
96
 
 
100
 
101
  *Built by Boris Dayma*
102
 
103
+ </section>
104
+
105
  [![Follow](https://img.shields.io/twitter/follow/borisdayma?style=social)](https://twitter.com/borisdayma)
106
 
107
+ <section class='prose'>
108
  For more details, visit the project repository.
109
+ </section>
110
 
111
  [![GitHub stars](https://img.shields.io/github/stars/borisdayma/huggingtweets?style=social)](https://github.com/borisdayma/huggingtweets)