boris commited on
Commit
7d6ce1f
1 Parent(s): b09dd70

New model from https://wandb.ai/wandb/huggingtweets/runs/ofr8h90y

Browse files
Files changed (5) hide show
  1. README.md +21 -57
  2. config.json +1 -0
  3. pytorch_model.bin +2 -2
  4. tokenizer_config.json +1 -1
  5. training_args.bin +2 -2
README.md CHANGED
@@ -1,28 +1,17 @@
1
  ---
2
  language: en
3
- thumbnail: https://www.huggingtweets.com/queenofbithynia/1608231511196/predictions.png
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('https://pbs.twimg.com/profile_images/1010627358879932416/0xVVQg3X_400x400.jpg')">
23
  </div>
24
  <div style="margin-top: 8px; font-size: 19px; font-weight: 800">the needle-felted head of joyce carol oates 🤖 AI Bot </div>
25
- <div style="font-size: 15px; color: #657786">@queenofbithynia bot</div>
26
  </div>
27
 
28
  I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
@@ -35,62 +24,41 @@ The model uses the following pipeline.
35
 
36
  ![pipeline](https://github.com/borisdayma/huggingtweets/blob/master/img/pipeline.png?raw=true)
37
 
38
- To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
39
 
40
  ## Training data
41
 
42
  The model was trained on [@queenofbithynia's tweets](https://twitter.com/queenofbithynia).
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'>3202</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'>16</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'>30</td>
63
- </tr>
64
- <tr style='border-width:0'>
65
- <td style='border-width:0'>Tweets kept</td>
66
- <td style='border-width:0'>3156</td>
67
- </tr>
68
- </tbody>
69
- </table>
70
-
71
- [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1am0g5eu/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 @queenofbithynia's tweets.
76
 
77
- Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2itrzc1n) for full transparency and reproducibility.
78
 
79
- At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2itrzc1n/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/queenofbithynia'</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
 
@@ -100,12 +68,8 @@ In addition, the data present in the user's tweets further affects the text gene
100
 
101
  *Built by Boris Dayma*
102
 
103
- </section>
104
-
105
  [![Follow](https://img.shields.io/twitter/follow/borisdayma?style=social)](https://twitter.com/intent/follow?screen_name=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)
1
  ---
2
  language: en
3
+ thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
4
  tags:
5
  - huggingtweets
6
  widget:
7
  - text: "My dream is"
8
  ---
9
 
 
 
 
 
 
 
 
 
 
 
 
10
  <div>
11
  <div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1010627358879932416/0xVVQg3X_400x400.jpg')">
12
  </div>
13
  <div style="margin-top: 8px; font-size: 19px; font-weight: 800">the needle-felted head of joyce carol oates 🤖 AI Bot </div>
14
+ <div style="font-size: 15px">@queenofbithynia bot</div>
15
  </div>
16
 
17
  I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
24
 
25
  ![pipeline](https://github.com/borisdayma/huggingtweets/blob/master/img/pipeline.png?raw=true)
26
 
27
+ To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
28
 
29
  ## Training data
30
 
31
  The model was trained on [@queenofbithynia's tweets](https://twitter.com/queenofbithynia).
32
 
33
+ | Data | Quantity |
34
+ | --- | --- |
35
+ | Tweets downloaded | 3250 |
36
+ | Retweets | 11 |
37
+ | Short tweets | 41 |
38
+ | Tweets kept | 3198 |
39
+
40
+ [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/26uw7qac/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
 
42
  ## Training procedure
43
 
44
  The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @queenofbithynia's tweets.
45
 
46
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/ofr8h90y) for full transparency and reproducibility.
47
 
48
+ At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/ofr8h90y/artifacts) is logged and versioned.
49
 
50
+ ## How to use
 
 
51
 
52
  You can use this model directly with a pipeline for text generation:
53
 
54
+ ```python
55
+ from transformers import pipeline
56
+ generator = pipeline('text-generation',
57
+ model='huggingtweets/queenofbithynia')
58
+ generator("My dream is", num_return_sequences=5)
59
+ ```
60
 
61
+ ## Limitations and bias
62
 
63
  The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
64
 
68
 
69
  *Built by Boris Dayma*
70
 
 
 
71
  [![Follow](https://img.shields.io/twitter/follow/borisdayma?style=social)](https://twitter.com/intent/follow?screen_name=borisdayma)
72
 
 
73
  For more details, visit the project repository.
 
74
 
75
  [![GitHub stars](https://img.shields.io/github/stars/borisdayma/huggingtweets?style=social)](https://github.com/borisdayma/huggingtweets)
config.json CHANGED
@@ -34,6 +34,7 @@
34
  "top_p": 0.95
35
  }
36
  },
 
37
  "use_cache": true,
38
  "vocab_size": 50257
39
  }
34
  "top_p": 0.95
35
  }
36
  },
37
+ "transformers_version": "4.5.1",
38
  "use_cache": true,
39
  "vocab_size": 50257
40
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ade8a41011b3d7f30977dbebcaf25b3285681bc52b22c6e027d10c70e997d73a
3
- size 510406560
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80ba0a52f4db6df6bdb6b8210510e2df751678577c6f9b78b746f03c73412da8
3
+ size 510408315
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "name_or_path": "gpt2"}
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a093b00e1beb41b4b61e2258fb06d7cf5d56dfcc7c3730659391a3400a85aab
3
- size 1903
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bd60214a6d86f41c33858fd340ecf7ee4cc8e9c4957481bd1803673e3af4963
3
+ size 2351