New model from https://wandb.ai/wandb/huggingtweets/runs/1qnuqwim
Browse files- README.md +9 -9
- config.json +2 -0
- pytorch_model.bin +1 -1
- tokenizer_config.json +1 -1
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
language: en
|
3 |
-
thumbnail: https://
|
4 |
tags:
|
5 |
- huggingtweets
|
6 |
widget:
|
@@ -51,32 +51,32 @@ The model was trained on [@realdonaldtrump's tweets](https://twitter.com/realdon
|
|
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'>
|
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'>
|
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'>
|
63 |
</tr>
|
64 |
<tr style='border-width:0'>
|
65 |
<td style='border-width:0'>Tweets kept</td>
|
66 |
-
<td style='border-width:0'>
|
67 |
</tr>
|
68 |
</tbody>
|
69 |
</table>
|
70 |
|
71 |
-
[Explore the data](https://
|
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 @realdonaldtrump's tweets.
|
76 |
|
77 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://
|
78 |
|
79 |
-
At the end of training, [the final model](https://
|
80 |
|
81 |
## Intended uses & limitations
|
82 |
|
@@ -110,4 +110,4 @@ For more details, visit the project repository.
|
|
110 |
|
111 |
[![GitHub stars](https://img.shields.io/github/stars/borisdayma/huggingtweets?style=social)](https://github.com/borisdayma/huggingtweets)
|
112 |
|
113 |
-
<!--- random size file
|
|
|
1 |
---
|
2 |
language: en
|
3 |
+
thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
|
4 |
tags:
|
5 |
- huggingtweets
|
6 |
widget:
|
|
|
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'>200</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'>97</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'>28</td>
|
63 |
</tr>
|
64 |
<tr style='border-width:0'>
|
65 |
<td style='border-width:0'>Tweets kept</td>
|
66 |
+
<td style='border-width:0'>75</td>
|
67 |
</tr>
|
68 |
</tbody>
|
69 |
</table>
|
70 |
|
71 |
+
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1ftixkhd/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 @realdonaldtrump's tweets.
|
76 |
|
77 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1qnuqwim) for full transparency and reproducibility.
|
78 |
|
79 |
+
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1qnuqwim/artifacts) is logged and versioned.
|
80 |
|
81 |
## Intended uses & limitations
|
82 |
|
|
|
110 |
|
111 |
[![GitHub stars](https://img.shields.io/github/stars/borisdayma/huggingtweets?style=social)](https://github.com/borisdayma/huggingtweets)
|
112 |
|
113 |
+
<!--- random size file -->
|
config.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"activation_function": "gelu_new",
|
3 |
"architectures": [
|
4 |
"GPT2LMHeadModel"
|
@@ -7,6 +8,7 @@
|
|
7 |
"bos_token_id": 50256,
|
8 |
"embd_pdrop": 0.1,
|
9 |
"eos_token_id": 50256,
|
|
|
10 |
"initializer_range": 0.02,
|
11 |
"layer_norm_epsilon": 1e-05,
|
12 |
"model_type": "gpt2",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
|
|
8 |
"bos_token_id": 50256,
|
9 |
"embd_pdrop": 0.1,
|
10 |
"eos_token_id": 50256,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
"initializer_range": 0.02,
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510406559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5258211d66959b052fd64ad8d0657440bcc09d8ca748ca483002dcd49e0f8ad
|
3 |
size 510406559
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"model_max_length": 1024}
|
|
|
1 |
+
{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "name_or_path": "gpt2"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:731ad8a156369ccde974252e9b78013abb8b6551a1cb327133664a504f02f4df
|
3 |
+
size 1839
|