New model from https://wandb.ai/wandb/huggingtweets/runs/1zmxayjz
Browse files- README.md +11 -11
- config.json +1 -1
- pytorch_model.bin +2 -2
- special_tokens_map.json +5 -1
- tokenizer.json +8 -5
- tokenizer_config.json +10 -1
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
language: en
|
3 |
-
thumbnail:
|
4 |
tags:
|
5 |
- huggingtweets
|
6 |
widget:
|
@@ -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">Boris Dayma
|
24 |
<div style="text-align: center; font-size: 14px;">@borisdayma</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 Boris Dayma
|
42 |
|
43 |
-
| Data | Boris Dayma
|
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 @borisdayma'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:
|
|
|
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">Boris Dayma ποΈ</div>
|
24 |
<div style="text-align: center; font-size: 14px;">@borisdayma</div>
|
25 |
</div>
|
26 |
|
|
|
38 |
|
39 |
## Training data
|
40 |
|
41 |
+
The model was trained on tweets from Boris Dayma ποΈ.
|
42 |
|
43 |
+
| Data | Boris Dayma ποΈ |
|
44 |
| --- | --- |
|
45 |
+
| Tweets downloaded | 1371 |
|
46 |
+
| Retweets | 146 |
|
47 |
+
| Short tweets | 42 |
|
48 |
+
| Tweets kept | 1183 |
|
49 |
|
50 |
+
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/twsl1ya3/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 @borisdayma's tweets.
|
55 |
|
56 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1zmxayjz) for full transparency and reproducibility.
|
57 |
|
58 |
+
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1zmxayjz/artifacts) is logged and versioned.
|
59 |
|
60 |
## How to use
|
61 |
|
config.json
CHANGED
@@ -37,7 +37,7 @@
|
|
37 |
}
|
38 |
},
|
39 |
"torch_dtype": "float32",
|
40 |
-
"transformers_version": "4.
|
41 |
"use_cache": true,
|
42 |
"vocab_size": 50257
|
43 |
}
|
|
|
37 |
}
|
38 |
},
|
39 |
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.20.1",
|
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:bb3cfdc988890e4bb324033a18538dca5db4e495f9e09157c637208b3b220aac
|
3 |
+
size 510396521
|
special_tokens_map.json
CHANGED
@@ -1 +1,5 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
+
}
|
tokenizer.json
CHANGED
@@ -5,29 +5,32 @@
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 50256,
|
8 |
-
"special": true,
|
9 |
"content": "<|endoftext|>",
|
10 |
"single_word": false,
|
11 |
"lstrip": false,
|
12 |
"rstrip": false,
|
13 |
-
"normalized": false
|
|
|
14 |
}
|
15 |
],
|
16 |
"normalizer": null,
|
17 |
"pre_tokenizer": {
|
18 |
"type": "ByteLevel",
|
19 |
"add_prefix_space": false,
|
20 |
-
"trim_offsets": true
|
|
|
21 |
},
|
22 |
"post_processor": {
|
23 |
"type": "ByteLevel",
|
24 |
"add_prefix_space": true,
|
25 |
-
"trim_offsets": false
|
|
|
26 |
},
|
27 |
"decoder": {
|
28 |
"type": "ByteLevel",
|
29 |
"add_prefix_space": true,
|
30 |
-
"trim_offsets": true
|
|
|
31 |
},
|
32 |
"model": {
|
33 |
"type": "BPE",
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 50256,
|
|
|
8 |
"content": "<|endoftext|>",
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
}
|
15 |
],
|
16 |
"normalizer": null,
|
17 |
"pre_tokenizer": {
|
18 |
"type": "ByteLevel",
|
19 |
"add_prefix_space": false,
|
20 |
+
"trim_offsets": true,
|
21 |
+
"use_regex": true
|
22 |
},
|
23 |
"post_processor": {
|
24 |
"type": "ByteLevel",
|
25 |
"add_prefix_space": true,
|
26 |
+
"trim_offsets": false,
|
27 |
+
"use_regex": true
|
28 |
},
|
29 |
"decoder": {
|
30 |
"type": "ByteLevel",
|
31 |
"add_prefix_space": true,
|
32 |
+
"trim_offsets": true,
|
33 |
+
"use_regex": true
|
34 |
},
|
35 |
"model": {
|
36 |
"type": "BPE",
|
tokenizer_config.json
CHANGED
@@ -1 +1,10 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"model_max_length": 1024,
|
6 |
+
"name_or_path": "gpt2",
|
7 |
+
"special_tokens_map_file": null,
|
8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
+
}
|
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:e6e52772b2e67979d533ee66a93082c4c9a0f27d7edd2e93d1a4df18ff07a23f
|
3 |
+
size 3311
|