New model from https://wandb.ai/wandb/huggingtweets/runs/x3nz24e9

README.md

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: http://www.huggingtweets.com/billgates/1662518741989/predictions.png
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
@@ -43,19 +43,19 @@ The model was trained on tweets from Bill Gates.
 | Data | Bill Gates |
 | --- | --- |
 | Tweets downloaded | 3250 |
-| Retweets | 181 |
-| Short tweets | 9 |
-| Tweets kept | 3060 |
+| Retweets | 176 |
+| Short tweets | 10 |
+| Tweets kept | 3064 |
 
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1lvv3kcj/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/2e81cpn8/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 @billgates's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3reshdl4) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/x3nz24e9) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3reshdl4/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/x3nz24e9/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -37,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.21.3",
+  "transformers_version": "4.25.1",
   "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaa4a3e9f9af3473975f4e5eaaf8c07831604c03ac9dc5bee7c4bb9cf88a6968
+oid sha256:09516e1fbba8f4ceae1eeb205e29daa451a0c0b3c3a62ec6a596f16add1093ce
 size 510396521

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ad537991bd96097cdb00a7278ad3d30c3e79db7d5cf1c9e1d3e4dcf0a646a8e
-size 3311
+oid sha256:a5673e06d21f6c17ec9ab89ca8e362d86a60aa41c0115c4481823c2f59038f2f
+size 3375