boris commited on
Commit
2985b9a
•
1 Parent(s): 18aa9b9

New model from https://wandb.ai/wandb/huggingtweets/runs/9hospm9e

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  language: en
3
- thumbnail: http://www.huggingtweets.com/ottorothmund/1660829280637/predictions.png
4
  tags:
5
  - huggingtweets
6
  widget:
@@ -10,7 +10,7 @@ widget:
10
  <div class="inline-flex flex-col" style="line-height: 1.5;">
11
  <div class="flex">
12
  <div
13
- style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://pbs.twimg.com/profile_images/1559959367339986944/wkKO36WM_400x400.jpg&#39;)">
14
  </div>
15
  <div
16
  style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;&#39;)">
@@ -20,7 +20,7 @@ widget:
20
  </div>
21
  </div>
22
  <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
23
- <div style="text-align: center; font-size: 16px; font-weight: 800">☀︎ OTTO ☀︎</div>
24
  <div style="text-align: center; font-size: 14px;">@ottorothmund</div>
25
  </div>
26
 
@@ -38,24 +38,24 @@ To understand how the model was developed, check the [W&B report](https://wandb.
38
 
39
  ## Training data
40
 
41
- The model was trained on tweets from ☀︎ OTTO ☀︎.
42
 
43
- | Data | ☀︎ OTTO ☀︎ |
44
  | --- | --- |
45
- | Tweets downloaded | 3141 |
46
- | Retweets | 607 |
47
- | Short tweets | 827 |
48
- | Tweets kept | 1707 |
49
 
50
- [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1nlj0t1c/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 @ottorothmund's tweets.
55
 
56
- Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/335e1woo) for full transparency and reproducibility.
57
 
58
- At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/335e1woo/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:
 
10
  <div class="inline-flex flex-col" style="line-height: 1.5;">
11
  <div class="flex">
12
  <div
13
+ style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://pbs.twimg.com/profile_images/1640242374264729600/egMDKzZ6_400x400.jpg&#39;)">
14
  </div>
15
  <div
16
  style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;&#39;)">
 
20
  </div>
21
  </div>
22
  <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
23
+ <div style="text-align: center; font-size: 16px; font-weight: 800">OTTO ☀︎</div>
24
  <div style="text-align: center; font-size: 14px;">@ottorothmund</div>
25
  </div>
26
 
 
38
 
39
  ## Training data
40
 
41
+ The model was trained on tweets from OTTO ☀︎.
42
 
43
+ | Data | OTTO ☀︎ |
44
  | --- | --- |
45
+ | Tweets downloaded | 3182 |
46
+ | Retweets | 515 |
47
+ | Short tweets | 672 |
48
+ | Tweets kept | 1995 |
49
 
50
+ [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2ageyj8t/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 @ottorothmund's tweets.
55
 
56
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/9hospm9e) for full transparency and reproducibility.
57
 
58
+ At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/9hospm9e/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": "4.21.1",
41
  "use_cache": true,
42
  "vocab_size": 50257
43
  }
 
37
  }
38
  },
39
  "torch_dtype": "float32",
40
+ "transformers_version": "4.27.3",
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": "4.27.3"
6
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98b2c2c403ca2a221d9ae18b7307cf32ceba3d525fc04c949f0abae14bed0f70
3
- size 510396521
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a8825631d453cc4643ca81caa88d3ff4c8eea211b67607bba1753e289566e8c
3
+ size 510398013
tokenizer_config.json CHANGED
@@ -3,7 +3,6 @@
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|>"
 
3
  "bos_token": "<|endoftext|>",
4
  "eos_token": "<|endoftext|>",
5
  "model_max_length": 1024,
 
6
  "special_tokens_map_file": null,
7
  "tokenizer_class": "GPT2Tokenizer",
8
  "unk_token": "<|endoftext|>"
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d46dd1223daa740bb97a092afbef1d7a6708511ba7a14cd057b0bba53552d04
3
- size 3311
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ccbc84a8b527c19159061d852448a5e7f2ebc64a4feb014857fd0a5d537ab5e
3
+ size 3579