New model from https://wandb.ai/wandb/huggingtweets/runs/3p3knp6q
Browse files- README.md +10 -8
- config.json +3 -0
- merges.txt +1 -1
- pytorch_model.bin +2 -2
- special_tokens_map.json +1 -1
- tokenizer_config.json +1 -1
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
language: en
|
3 |
-
thumbnail:
|
4 |
tags:
|
5 |
- huggingtweets
|
6 |
widget:
|
@@ -19,7 +19,7 @@ widget:
|
|
19 |
<section class='prose'>
|
20 |
|
21 |
<div>
|
22 |
-
<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('
|
23 |
</div>
|
24 |
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Weights & Biases 🤖 AI Bot </div>
|
25 |
<div style="font-size: 15px; color: #657786">@weights_biases bot</div>
|
@@ -51,11 +51,11 @@ The model was trained on [@weights_biases's tweets](https://twitter.com/weights_
|
|
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>
|
@@ -63,20 +63,20 @@ The model was trained on [@weights_biases's tweets](https://twitter.com/weights_
|
|
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 @weights_biases'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 |
|
@@ -109,3 +109,5 @@ 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:
|
|
|
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/1101567690014056448/XxZqLgwb_400x400.png')">
|
23 |
</div>
|
24 |
<div style="margin-top: 8px; font-size: 19px; font-weight: 800">Weights & Biases 🤖 AI Bot </div>
|
25 |
<div style="font-size: 15px; color: #657786">@weights_biases bot</div>
|
|
|
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'>1206</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'>516</td>
|
59 |
</tr>
|
60 |
<tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
|
61 |
<td style='border-width:0'>Short tweets</td>
|
|
|
63 |
</tr>
|
64 |
<tr style='border-width:0'>
|
65 |
<td style='border-width:0'>Tweets kept</td>
|
66 |
+
<td style='border-width:0'>680</td>
|
67 |
</tr>
|
68 |
</tbody>
|
69 |
</table>
|
70 |
|
71 |
+
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1wvlor6a/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 @weights_biases's tweets.
|
76 |
|
77 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3p3knp6q) for full transparency and reproducibility.
|
78 |
|
79 |
+
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3p3knp6q/artifacts) is logged and versioned.
|
80 |
|
81 |
## Intended uses & limitations
|
82 |
|
|
|
109 |
</section>
|
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",
|
@@ -32,5 +34,6 @@
|
|
32 |
"top_p": 0.95
|
33 |
}
|
34 |
},
|
|
|
35 |
"vocab_size": 50257
|
36 |
}
|
|
|
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",
|
|
|
34 |
"top_p": 0.95
|
35 |
}
|
36 |
},
|
37 |
+
"use_cache": true,
|
38 |
"vocab_size": 50257
|
39 |
}
|
merges.txt
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
#version: 0.2
|
2 |
Ġ t
|
3 |
Ġ a
|
4 |
h e
|
|
|
1 |
+
#version: 0.2 - Trained by `huggingface/tokenizers`
|
2 |
Ġ t
|
3 |
Ġ a
|
4 |
h e
|
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:f60ce3abc869818727ef4500ff02ccb68d6ceaab49910cf3373fab0da400a091
|
3 |
+
size 510406560
|
special_tokens_map.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"bos_token":
|
|
|
1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"model_max_length": 1024}
|
|
|
1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "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:cafc10cf02b4add6b368c7bf9c13798b893a368721e6ec67c453642787af09f3
|
3 |
+
size 1775
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|