New model from https://wandb.ai/wandb/huggingtweets/runs/3eul8k9p
Browse files- README.md +8 -8
- config.json +1 -1
- pytorch_model.bin +1 -1
- special_tokens_map.json +5 -1
- tokenizer_config.json +10 -1
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
language: en
|
| 3 |
-
thumbnail: http://www.huggingtweets.com/mrbeast/
|
| 4 |
tags:
|
| 5 |
- huggingtweets
|
| 6 |
widget:
|
|
@@ -42,20 +42,20 @@ The model was trained on tweets from MrBeast.
|
|
| 42 |
|
| 43 |
| Data | MrBeast |
|
| 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 @mrbeast'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: http://www.huggingtweets.com/mrbeast/1663629759679/predictions.png
|
| 4 |
tags:
|
| 5 |
- huggingtweets
|
| 6 |
widget:
|
|
|
|
| 42 |
|
| 43 |
| Data | MrBeast |
|
| 44 |
| --- | --- |
|
| 45 |
+
| Tweets downloaded | 3249 |
|
| 46 |
+
| Retweets | 119 |
|
| 47 |
+
| Short tweets | 725 |
|
| 48 |
+
| Tweets kept | 2405 |
|
| 49 |
|
| 50 |
+
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/40pv6lvp/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 @mrbeast's tweets.
|
| 55 |
|
| 56 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3eul8k9p) for full transparency and reproducibility.
|
| 57 |
|
| 58 |
+
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3eul8k9p/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": "4.22.1",
|
| 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 510396521
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88505b4edf638860576bb86c274dbd744deac787bd2ab1b2cd3cef23f4397c09
|
| 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_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:ea67706ee43fa449e0c69e2ac80920ac47ea87812b39bfdd2b910a79410e6101
|
| 3 |
+
size 3375
|