boris commited on
Commit
0542242
1 Parent(s): fc76e11

New model from https://wandb.ai/wandb/huggingtweets/runs/2ivs2zls

Browse files
Files changed (4) hide show
  1. README.md +7 -7
  2. config.json +1 -1
  3. pytorch_model.bin +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  language: en
3
- thumbnail: http://www.huggingtweets.com/donaldtusk/1657052510922/predictions.png
4
  tags:
5
  - huggingtweets
6
  widget:
@@ -42,20 +42,20 @@ The model was trained on tweets from Donald Tusk.
42
 
43
  | Data | Donald Tusk |
44
  | --- | --- |
45
- | Tweets downloaded | 910 |
46
  | Retweets | 194 |
47
- | Short tweets | 32 |
48
- | Tweets kept | 684 |
49
 
50
- [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3pclez81/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 @donaldtusk's tweets.
55
 
56
- Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3oogjdqv) for full transparency and reproducibility.
57
 
58
- At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3oogjdqv/artifacts) is logged and versioned.
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 | Donald Tusk |
44
  | --- | --- |
45
+ | Tweets downloaded | 928 |
46
  | Retweets | 194 |
47
+ | Short tweets | 35 |
48
+ | Tweets kept | 699 |
49
 
50
+ [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/pyk96dcl/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 @donaldtusk's tweets.
55
 
56
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2ivs2zls) for full transparency and reproducibility.
57
 
58
+ At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2ivs2zls/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": "4.20.1",
41
  "use_cache": true,
42
  "vocab_size": 50257
43
  }
 
37
  }
38
  },
39
  "torch_dtype": "float32",
40
+ "transformers_version": "4.21.2",
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 sha256:29b36060dda00700fe258ebc8724f25e16582a701e7cf57430b98def5d587993
3
  size 510396521
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e0655f0ab39814bb5aa82e664369c39345cfd84cbb636d0e17be255bae50e7
3
  size 510396521
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5645791a33c90a0d9e67ec5b3a7f2b16a87e4bc83bb37797328e058c31e1c3f2
3
  size 3311
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3da9b61a2baa36d131d0b531ccb5313cd903bad4e05953c47245f17ba33a10d5
3
  size 3311