New model from https://wandb.ai/wandb/huggingtweets/runs/emrh1w8h
Browse files- README.md +7 -7
- dummy_config.json +0 -38
- pytorch_model.bin +1 -1
- tokenizer_config.json +1 -1
- dummy.bin → training_args.bin +2 -2
README.md
CHANGED
@@ -51,11 +51,11 @@ The model was trained on [@borisdayma's tweets](https://twitter.com/borisdayma).
|
|
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 [@borisdayma's tweets](https://twitter.com/borisdayma).
|
|
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://wandb.ai/wandb/huggingtweets/runs/
|
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 @borisdayma's tweets.
|
76 |
|
77 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/
|
78 |
|
79 |
-
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/
|
80 |
|
81 |
## Intended uses & limitations
|
82 |
|
@@ -110,4 +110,4 @@ For more details, visit the project repository.
|
|
110 |
|
111 |
[![GitHub stars](https://img.shields.io/github/stars/borisdayma/huggingtweets?style=social)](https://github.com/borisdayma/huggingtweets)
|
112 |
|
113 |
-
<!--- random size file
|
|
|
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'>328</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'>48</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'>277</td>
|
67 |
</tr>
|
68 |
</tbody>
|
69 |
</table>
|
70 |
|
71 |
+
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/14fatfln/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 @borisdayma's tweets.
|
76 |
|
77 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/emrh1w8h) for full transparency and reproducibility.
|
78 |
|
79 |
+
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/emrh1w8h/artifacts) is logged and versioned.
|
80 |
|
81 |
## Intended uses & limitations
|
82 |
|
|
|
110 |
|
111 |
[![GitHub stars](https://img.shields.io/github/stars/borisdayma/huggingtweets?style=social)](https://github.com/borisdayma/huggingtweets)
|
112 |
|
113 |
+
<!--- random size file -->
|
dummy_config.json
DELETED
@@ -1,38 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "gpt2",
|
3 |
-
"activation_function": "gelu_new",
|
4 |
-
"architectures": [
|
5 |
-
"GPT2LMHeadModel"
|
6 |
-
],
|
7 |
-
"attn_pdrop": 0.1,
|
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",
|
15 |
-
"n_ctx": 1024,
|
16 |
-
"n_embd": 768,
|
17 |
-
"n_head": 12,
|
18 |
-
"n_inner": null,
|
19 |
-
"n_layer": 12,
|
20 |
-
"n_positions": 1024,
|
21 |
-
"resid_pdrop": 0.1,
|
22 |
-
"summary_activation": null,
|
23 |
-
"summary_first_dropout": 0.1,
|
24 |
-
"summary_proj_to_labels": true,
|
25 |
-
"summary_type": "cls_index",
|
26 |
-
"summary_use_proj": true,
|
27 |
-
"task_specific_params": {
|
28 |
-
"text-generation": {
|
29 |
-
"do_sample": true,
|
30 |
-
"max_length": 160,
|
31 |
-
"min_length": 10,
|
32 |
-
"prefix": "<|endoftext|>",
|
33 |
-
"temperature": 1.0,
|
34 |
-
"top_p": 0.95
|
35 |
-
}
|
36 |
-
},
|
37 |
-
"vocab_size": 50257
|
38 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510406559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c82b4e933357a4aa5623439a8ea3766e20924a84f2f2b09633b9c131d58a34bd
|
3 |
size 510406559
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "name_or_path": "gpt2"}
|
dummy.bin → training_args.bin
RENAMED
@@ -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:ab9d96e8d537ca1424cec406b178ec09c3eae5d1c9b5493abbcda05bf9dd6c8a
|
3 |
+
size 1775
|