New model from https://wandb.ai/wandb/huggingtweets/runs/vc7xckhc
Browse files- README.md +8 -8
- 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 +1 -0
- 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 Nein..
|
|
42 |
|
43 |
| Data | Nein. |
|
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 @neinquarterly'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 | Nein. |
|
44 |
| --- | --- |
|
45 |
+
| Tweets downloaded | 3193 |
|
46 |
+
| Retweets | 144 |
|
47 |
+
| Short tweets | 118 |
|
48 |
+
| Tweets kept | 2931 |
|
49 |
|
50 |
+
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/lchsn1qo/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 @neinquarterly's tweets.
|
55 |
|
56 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/vc7xckhc) for full transparency and reproducibility.
|
57 |
|
58 |
+
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/vc7xckhc/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": "4.28.0",
|
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": "4.28.0"
|
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:deab95e6a1079b424c06541a6e2a94c7c18322c6fd0db742ee2f2855739c3a57
|
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
@@ -39,6 +39,7 @@
|
|
39 |
"continuing_subword_prefix": "",
|
40 |
"end_of_word_suffix": "",
|
41 |
"fuse_unk": false,
|
|
|
42 |
"vocab": {
|
43 |
"!": 0,
|
44 |
"\"": 1,
|
|
|
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 sha256:2b6f8b4d56a247a13185af073a30c120c94282173d17a4bdac11d3f90b5f61de
|
3 |
+
size 3579
|