boris commited on
Commit
9040dc0
Β·
1 Parent(s): f429afa

New model from https://wandb.ai/wandb/huggingtweets/runs/18w54tsa

Browse files
Files changed (3) hide show
  1. README.md +18 -18
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -10,18 +10,18 @@ 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/1442634650703237120/mXIcYtIs_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;)">
17
  </div>
18
  <div
19
- 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">πŸ€– AI BOT πŸ€–</div>
23
- <div style="text-align: center; font-size: 16px; font-weight: 800">Elon Musk</div>
24
- <div style="text-align: center; font-size: 14px;">@elonmusk</div>
25
  </div>
26
 
27
  I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
@@ -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 Elon Musk.
42
 
43
- | Data | Elon Musk |
44
- | --- | --- |
45
- | Tweets downloaded | 2600 |
46
- | Retweets | 137 |
47
- | Short tweets | 736 |
48
- | Tweets kept | 1727 |
49
 
50
- [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1n0eya9d/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 @elonmusk's tweets.
55
 
56
- Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/24qg3mrl) for full transparency and reproducibility.
57
 
58
- At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/24qg3mrl/artifacts) is logged and versioned.
59
 
60
  ## How to use
61
 
@@ -64,7 +64,7 @@ You can use this model directly with a pipeline for text generation:
64
  ```python
65
  from transformers import pipeline
66
  generator = pipeline('text-generation',
67
- model='huggingtweets/elonmusk')
68
  generator("My dream is", num_return_sequences=5)
69
  ```
70
 
 
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/1442763644606029828/CeUlNL6L_400x400.jpg&#39;)">
14
  </div>
15
  <div
16
+ 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/1468633629274218502/LGrXJ5Fg_400x400.jpg&#39;)">
17
  </div>
18
  <div
19
+ 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/1446914192825454592/cGOslAWZ_400x400.jpg&#39;)">
20
  </div>
21
  </div>
22
+ <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">πŸ€– AI CYBORG πŸ€–</div>
23
+ <div style="text-align: center; font-size: 16px; font-weight: 800">Zeneca_33 🍌 & Jacob Martin & TΞtranodΞ (πŸ’Ž, πŸ’Ž) & dcbuilder.eth πŸ¦‡πŸ”ŠπŸΌ (3,3)(πŸ§‹,πŸ§‹)β”»β”³πŸ¦€</div>
24
+ <div style="text-align: center; font-size: 14px;">@dcbuild3r-tetranode-thenftattorney-zeneca_33</div>
25
  </div>
26
 
27
  I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
 
38
 
39
  ## Training data
40
 
41
+ The model was trained on tweets from Zeneca_33 🍌 & Jacob Martin & TΞtranodΞ (πŸ’Ž, πŸ’Ž) & dcbuilder.eth πŸ¦‡πŸ”ŠπŸΌ (3,3)(πŸ§‹,πŸ§‹)β”»β”³πŸ¦€.
42
 
43
+ | Data | Zeneca_33 🍌 | Jacob Martin | TΞtranodΞ (πŸ’Ž, πŸ’Ž) | dcbuilder.eth πŸ¦‡πŸ”ŠπŸΌ (3,3)(πŸ§‹,πŸ§‹)β”»β”³πŸ¦€ |
44
+ | --- | --- | --- | --- | --- |
45
+ | Tweets downloaded | 3250 | 3250 | 3247 | 3250 |
46
+ | Retweets | 7 | 58 | 736 | 318 |
47
+ | Short tweets | 537 | 390 | 555 | 646 |
48
+ | Tweets kept | 2706 | 2802 | 1956 | 2286 |
49
 
50
+ [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1562a0v6/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 @dcbuild3r-tetranode-thenftattorney-zeneca_33's tweets.
55
 
56
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/18w54tsa) for full transparency and reproducibility.
57
 
58
+ At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/18w54tsa/artifacts) is logged and versioned.
59
 
60
  ## How to use
61
 
 
64
  ```python
65
  from transformers import pipeline
66
  generator = pipeline('text-generation',
67
+ model='huggingtweets/dcbuild3r-tetranode-thenftattorney-zeneca_33')
68
  generator("My dream is", num_return_sequences=5)
69
  ```
70
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdbc4e8484aa84a4e591a681a7be368a5be5f9e82f18a5baeae59352156299c0
3
  size 510403817
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:029c46aebc867fcf96b5a1ab143c33c87bdcae37175340136b4b0c8cd3377bb7
3
  size 510403817
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5562d95cab56e027b6a20e9e95404625a31c92880b6ce8f2c24312ba096f02d
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:270732eda0350d4779b9ff78b862e41a5e3cb453386e5bc571fd3b5d3311dc42
3
  size 2927