New model from https://wandb.ai/wandb/huggingtweets/runs/2g6ndbxy

README.md

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: https://www.huggingtweets.com/elonmusk/1620769488795/predictions.png
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
@@ -44,18 +44,18 @@ The model was trained on tweets from Elon Musk.
 | --- | --- |
 | Tweets downloaded | 3249 |
 | Retweets | 210 |
-| Short tweets | 800 |
-| Tweets kept | 2239 |
+| Short tweets | 801 |
+| Tweets kept | 2238 |
 
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1dfjqq2l/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3ja3jqgu/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 
 ## Training procedure
 
 The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @elonmusk's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1p1bqvt3) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2g6ndbxy) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1p1bqvt3/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2g6ndbxy/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -19,6 +19,7 @@
   "n_layer": 12,
   "n_positions": 1024,
   "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
   "summary_proj_to_labels": true,
@@ -34,7 +35,7 @@
       "top_p": 0.95
     }
   },
-  "transformers_version": "4.5.1",
+  "transformers_version": "4.6.0",
   "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a8954eb206a5353c2ac20e1139eacbfa7693479594e6adba5e8f4e6cd489390
+oid sha256:e58c94195d8b374c831f5398022eed8a688776c320c3a003b848a6bc8fcfd54a
 size 510408315

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f1c17236e3d04af62206e7b2afdcf30a1d66cce1ef91b808400ac5e1a78a9cc
-size 2351
+oid sha256:875b2aba5650c95f8640b99a9a4b4eb2163e837e476c3923f38117b254237ad9
+size 2415