New model from https://wandb.ai/wandb/huggingtweets/runs/00b9i1fj
Browse files- README.md +7 -7
- config.json +1 -1
- generation_config.json +6 -0
- merges.txt +1 -1
- pytorch_model.bin +2 -2
- special_tokens_map.json +5 -1
- tokenizer.json +9 -5
- tokenizer_config.json +9 -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:
|
@@ -42,20 +42,20 @@ The model was trained on tweets from Dwayne Johnson.
|
|
42 |
|
43 |
| Data | Dwayne Johnson |
|
44 |
| --- | --- |
|
45 |
-
| Tweets downloaded |
|
46 |
-
| Retweets |
|
47 |
-
| Short tweets |
|
48 |
| Tweets kept | 2433 |
|
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 @therock'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:
|
|
|
42 |
|
43 |
| Data | Dwayne Johnson |
|
44 |
| --- | --- |
|
45 |
+
| Tweets downloaded | 3186 |
|
46 |
+
| Retweets | 651 |
|
47 |
+
| Short tweets | 102 |
|
48 |
| Tweets kept | 2433 |
|
49 |
|
50 |
+
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/ut9satny/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 @therock's tweets.
|
55 |
|
56 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/00b9i1fj) for full transparency and reproducibility.
|
57 |
|
58 |
+
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/00b9i1fj/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": "4.28.1",
|
41 |
"use_cache": true,
|
42 |
"vocab_size": 50257
|
43 |
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.28.1"
|
6 |
+
}
|
merges.txt
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
#version: 0.2
|
2 |
Ġ t
|
3 |
Ġ a
|
4 |
h e
|
|
|
1 |
+
#version: 0.2
|
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 sha256:04b9274a4256d735690f7db65dd1c59d9fff46cbc9755c4ec09bbff382f99999
|
3 |
+
size 510398013
|
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",
|
@@ -36,6 +39,7 @@
|
|
36 |
"continuing_subword_prefix": "",
|
37 |
"end_of_word_suffix": "",
|
38 |
"fuse_unk": false,
|
|
|
39 |
"vocab": {
|
40 |
"!": 0,
|
41 |
"\"": 1,
|
|
|
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",
|
|
|
39 |
"continuing_subword_prefix": "",
|
40 |
"end_of_word_suffix": "",
|
41 |
"fuse_unk": false,
|
42 |
+
"byte_fallback": false,
|
43 |
"vocab": {
|
44 |
"!": 0,
|
45 |
"\"": 1,
|
tokenizer_config.json
CHANGED
@@ -1 +1,9 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 1024,
|
7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
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 sha256:4de7e69830ec3f4d893a990ed14268491eb5ddb6c4750ea810482927a2e36284
|
3 |
+
size 3579
|