New model from https://wandb.ai/wandb/huggingtweets/runs/1ohzggkp

README.md

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: https://www.huggingtweets.com/claireredacted/1627169377783/predictions.png
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
@@ -42,20 +42,20 @@ The model was trained on tweets from Claire.
 
 | Data | Claire |
 | --- | --- |
-| Tweets downloaded | 3239 |
-| Retweets | 525 |
-| Short tweets | 627 |
-| Tweets kept | 2087 |
+| Tweets downloaded | 3232 |
+| Retweets | 518 |
+| Short tweets | 616 |
+| Tweets kept | 2098 |
 
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/15xpfb4p/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/14yfbvkx/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 @claireredacted's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/9fd0hyu0) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1ohzggkp) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/9fd0hyu0/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1ohzggkp/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -36,7 +36,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.9.0",
+  "transformers_version": "4.9.1",
   "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef7a995832a6cd23958c340d2c59ff7661bd542e4cffebf9fa6d8cbec3a246db
+oid sha256:7f4f636636788f1fabd8ca2ab81203acd8a84a8eecdfa1d09a0fe6ee5e4dfb2c
 size 510403817

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:900027cfecea6ddbf15446d0e3b7101e13667eb5c7e2a1eb2be0ff942b629151
+oid sha256:e099e5a4bf03111cc70d8f64f67d17e624d01cfb51b3acda38f9adbae626424f
 size 2671