New model from https://wandb.ai/wandb/huggingtweets/runs/3ms9u3u9
Browse files- README.md +12 -12
- config.json +3 -1
- pytorch_model.bin +2 -2
- tokenizer.json +0 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
language: en
|
3 |
-
thumbnail: https://
|
4 |
tags:
|
5 |
- huggingtweets
|
6 |
widget:
|
@@ -10,7 +10,7 @@ widget:
|
|
10 |
<div class="inline-flex flex-col" style="line-height: 1.5;">
|
11 |
<div class="flex">
|
12 |
<div
|
13 |
-
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/
|
14 |
</div>
|
15 |
<div
|
16 |
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
|
@@ -20,7 +20,7 @@ widget:
|
|
20 |
</div>
|
21 |
</div>
|
22 |
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">π€ AI BOT π€</div>
|
23 |
-
<div style="text-align: center; font-size: 16px; font-weight: 800">π
|
24 |
<div style="text-align: center; font-size: 14px;">@temeton_blue</div>
|
25 |
</div>
|
26 |
|
@@ -38,24 +38,24 @@ To understand how the model was developed, check the [W&B report](https://wandb.
|
|
38 |
|
39 |
## Training data
|
40 |
|
41 |
-
The model was trained on tweets from π
|
42 |
|
43 |
-
| Data | π
|
44 |
| --- | --- |
|
45 |
-
| Tweets downloaded |
|
46 |
-
| Retweets |
|
47 |
-
| Short tweets |
|
48 |
-
| Tweets kept |
|
49 |
|
50 |
-
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/
|
51 |
|
52 |
## Training procedure
|
53 |
|
54 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @temeton_blue's tweets.
|
55 |
|
56 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/
|
57 |
|
58 |
-
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/
|
59 |
|
60 |
## How to use
|
61 |
|
1 |
---
|
2 |
language: en
|
3 |
+
thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
|
4 |
tags:
|
5 |
- huggingtweets
|
6 |
widget:
|
10 |
<div class="inline-flex flex-col" style="line-height: 1.5;">
|
11 |
<div class="flex">
|
12 |
<div
|
13 |
+
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1484527879094517763/L1oelBjg_400x400.jpg')">
|
14 |
</div>
|
15 |
<div
|
16 |
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
|
20 |
</div>
|
21 |
</div>
|
22 |
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">π€ AI BOT π€</div>
|
23 |
+
<div style="text-align: center; font-size: 16px; font-weight: 800">π Normiespawn π</div>
|
24 |
<div style="text-align: center; font-size: 14px;">@temeton_blue</div>
|
25 |
</div>
|
26 |
|
38 |
|
39 |
## Training data
|
40 |
|
41 |
+
The model was trained on tweets from π Normiespawn π.
|
42 |
|
43 |
+
| Data | π Normiespawn π |
|
44 |
| --- | --- |
|
45 |
+
| Tweets downloaded | 3209 |
|
46 |
+
| Retweets | 1231 |
|
47 |
+
| Short tweets | 299 |
|
48 |
+
| Tweets kept | 1679 |
|
49 |
|
50 |
+
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/xxy3jquc/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
|
51 |
|
52 |
## Training procedure
|
53 |
|
54 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @temeton_blue's tweets.
|
55 |
|
56 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3ms9u3u9) for full transparency and reproducibility.
|
57 |
|
58 |
+
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3ms9u3u9/artifacts) is logged and versioned.
|
59 |
|
60 |
## How to use
|
61 |
|
config.json
CHANGED
@@ -17,7 +17,9 @@
|
|
17 |
"n_inner": null,
|
18 |
"n_layer": 12,
|
19 |
"n_positions": 1024,
|
|
|
20 |
"resid_pdrop": 0.1,
|
|
|
21 |
"scale_attn_weights": true,
|
22 |
"summary_activation": null,
|
23 |
"summary_first_dropout": 0.1,
|
@@ -35,7 +37,7 @@
|
|
35 |
}
|
36 |
},
|
37 |
"torch_dtype": "float32",
|
38 |
-
"transformers_version": "4.
|
39 |
"use_cache": true,
|
40 |
"vocab_size": 50257
|
41 |
}
|
17 |
"n_inner": null,
|
18 |
"n_layer": 12,
|
19 |
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
"scale_attn_weights": true,
|
24 |
"summary_activation": null,
|
25 |
"summary_first_dropout": 0.1,
|
37 |
}
|
38 |
},
|
39 |
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.17.0",
|
41 |
"use_cache": true,
|
42 |
"vocab_size": 50257
|
43 |
}
|
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:b913855e716247a23e124115cd44571a0e9a9fe741277d611973f4c8f868e012
|
3 |
+
size 510404393
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
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 sha256:6da00cde730b319b24d54993ca2532fdaa5c86189ed0570b39dc50f993294c47
|
3 |
+
size 3055
|