New model from https://wandb.ai/wandb/huggingtweets/runs/16ugp9hy
Browse files- README.md +21 -57
- config.json +1 -1
- pytorch_model.bin +2 -2
- tokenizer_config.json +1 -1
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,28 +1,17 @@
|
|
1 |
---
|
2 |
language: en
|
3 |
-
thumbnail: https://
|
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/1256841238298292232/ycqwaMI2_400x400.jpg')">
|
23 |
</div>
|
24 |
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Naval 🤖 AI Bot </div>
|
25 |
-
<div style="font-size: 15px
|
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://
|
39 |
|
40 |
## Training data
|
41 |
|
42 |
The model was trained on [@naval's tweets](https://twitter.com/naval).
|
43 |
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
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'>3233</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'>128</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'>660</td>
|
63 |
-
</tr>
|
64 |
-
<tr style='border-width:0'>
|
65 |
-
<td style='border-width:0'>Tweets kept</td>
|
66 |
-
<td style='border-width:0'>2445</td>
|
67 |
-
</tr>
|
68 |
-
</tbody>
|
69 |
-
</table>
|
70 |
-
|
71 |
-
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/216kkfw1/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 @naval's tweets.
|
76 |
|
77 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/
|
78 |
|
79 |
-
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/
|
80 |
|
81 |
-
##
|
82 |
-
|
83 |
-
### How to use
|
84 |
|
85 |
You can use this model directly with a pipeline for text generation:
|
86 |
|
87 |
-
|
88 |
-
|
89 |
-
|
90 |
-
|
91 |
-
|
|
|
92 |
|
93 |
-
|
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/1256841238298292232/ycqwaMI2_400x400.jpg')">
|
12 |
</div>
|
13 |
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Naval 🤖 AI Bot </div>
|
14 |
+
<div style="font-size: 15px">@naval 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 [@naval's tweets](https://twitter.com/naval).
|
32 |
|
33 |
+
| Data | Quantity |
|
34 |
+
| --- | --- |
|
35 |
+
| Tweets downloaded | 3250 |
|
36 |
+
| Retweets | 138 |
|
37 |
+
| Short tweets | 657 |
|
38 |
+
| Tweets kept | 2455 |
|
39 |
+
|
40 |
+
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/p7s0zjvq/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 @naval's tweets.
|
45 |
|
46 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/16ugp9hy) for full transparency and reproducibility.
|
47 |
|
48 |
+
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/16ugp9hy/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/naval')
|
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
@@ -34,7 +34,7 @@
|
|
34 |
"top_p": 0.95
|
35 |
}
|
36 |
},
|
37 |
-
"transformers_version": "4.
|
38 |
"use_cache": true,
|
39 |
"vocab_size": 50257
|
40 |
}
|
|
|
34 |
"top_p": 0.95
|
35 |
}
|
36 |
},
|
37 |
+
"transformers_version": "4.5.0",
|
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:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90c048ed711139d1f9ee281cf55af4db8c215076919defa0264040575e46d885
|
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:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09c45893a1e3cdd86347fe4d633021ce4cecafb6e5bbeac27d2f593d5daa6322
|
3 |
+
size 2351
|