New model from https://wandb.ai/wandb/huggingtweets/runs/1jnu1ceq

README.md

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: https://www.huggingtweets.com/conceptualjames/1629230421949/predictions.png
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
@@ -20,7 +20,7 @@ widget:
         </div>
     </div>
     <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
-    <div style="text-align: center; font-size: 16px; font-weight: 800">James Lindsay, modern Sunzi with a bigger sword</div>
+    <div style="text-align: center; font-size: 16px; font-weight: 800">James Lindsay, manipulated media</div>
     <div style="text-align: center; font-size: 14px;">@conceptualjames</div>
 </div>
 
@@ -38,24 +38,24 @@ To understand how the model was developed, check the [W&B report](https://wandb.
 
 ## Training data
 
-The model was trained on tweets from James Lindsay, modern Sunzi with a bigger sword.
+The model was trained on tweets from James Lindsay, manipulated media.
 
-| Data | James Lindsay, modern Sunzi with a bigger sword |
+| Data | James Lindsay, manipulated media |
 | --- | --- |
-| Tweets downloaded | 3244 |
-| Retweets | 1400 |
-| Short tweets | 534 |
-| Tweets kept | 1310 |
+| Tweets downloaded | 3226 |
+| Retweets | 1436 |
+| Short tweets | 520 |
+| Tweets kept | 1270 |
 
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1v9wifii/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/1sj5ihe6/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 @conceptualjames's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/14ghf52z) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1jnu1ceq) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/14ghf52z/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1jnu1ceq/artifacts) is logged and versioned.
 
 ## How to use
 

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:185d306791a9c394303989a73c84e6dbfcb558f886f882c65cad0ea5433c764e
+oid sha256:b47222fa45e911956adb8a10c75a958c8645f93351dffd09294bb9e8437cc9fa
 size 510403817

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77171d6bb5cc1b6fb2897e6d8fc3fa668f73067ff0f8ebe6948b037b1c3452f5
+oid sha256:0447c832cdcf34e63b51ed76238b39ebcf58a2f8132789f96754c4ce74a0e811
 size 2671