New model from https://wandb.ai/wandb/huggingtweets/runs/vgga859n
Browse files- README.md +6 -6
- config.json +1 -1
- pytorch_model.bin +2 -2
- tokenizer.json +6 -3
- training_args.bin +2 -2
README.md
CHANGED
@@ -42,20 +42,20 @@ The model was trained on tweets from Rebecca Fiebrink.
|
|
42 |
|
43 |
| Data | Rebecca Fiebrink |
|
44 |
| --- | --- |
|
45 |
-
| Tweets downloaded |
|
46 |
-
| Retweets |
|
47 |
| Short tweets | 116 |
|
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 @rebeccafiebrink'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 |
|
|
|
42 |
|
43 |
| Data | Rebecca Fiebrink |
|
44 |
| --- | --- |
|
45 |
+
| Tweets downloaded | 2010 |
|
46 |
+
| Retweets | 735 |
|
47 |
| Short tweets | 116 |
|
48 |
+
| Tweets kept | 1159 |
|
49 |
|
50 |
+
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/4esn0lor/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 @rebeccafiebrink's tweets.
|
55 |
|
56 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/vgga859n) for full transparency and reproducibility.
|
57 |
|
58 |
+
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/vgga859n/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": "4.19.2",
|
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 sha256:7905d43a6fc701d413855e8199dad17aef8adbf3a7b48299686ce7dafa2ec444
|
3 |
+
size 510396521
|
tokenizer.json
CHANGED
@@ -17,17 +17,20 @@
|
|
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",
|
|
|
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",
|
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 sha256:38f578a4d4511bc96b0dcf1fc001321971bfa0ad7273c99ab2c9ed3eb38ef3a3
|
3 |
+
size 3247
|