New model from https://wandb.ai/wandb/huggingtweets/runs/2ksyxrv3

README.md

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: http://www.huggingtweets.com/dril/1645344495533/predictions.png
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
@@ -10,7 +10,7 @@ widget:
 <div class="inline-flex flex-col" style="line-height: 1.5;">
     <div class="flex">
         <div
-			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/847818629840228354/VXyQHfn0_400x400.jpg&#39;)">
+			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/1510917391533830145/XW-zSFDJ_400x400.jpg&#39;)">
         </div>
         <div
             style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;&#39;)">
@@ -44,18 +44,18 @@ The model was trained on tweets from wint.
 | --- | --- |
 | Tweets downloaded | 3229 |
 | Retweets | 477 |
-| Short tweets | 300 |
-| Tweets kept | 2452 |
+| Short tweets | 303 |
+| Tweets kept | 2449 |
 
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2le36oi2/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/1z1b5oaz/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 @dril's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3lmxm66b) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2ksyxrv3) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3lmxm66b/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2ksyxrv3/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -37,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.16.2",
+  "transformers_version": "4.18.0",
   "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4be44a157f33e08516eefe8be87cbbd4f43dbfdd815d0931667416639cde6b51
-size 510403817
+oid sha256:32dd3c56d269f26e4e9b0423241bc644c88d33e6c0cc4e7b46356a388ac8f6be
+size 510396521

tokenizer.json

@@ -5,29 +5,32 @@
   "added_tokens": [
     {
       "id": 50256,
-      "special": true,
       "content": "<|endoftext|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,
   "pre_tokenizer": {
     "type": "ByteLevel",
     "add_prefix_space": false,
-    "trim_offsets": true
+    "trim_offsets": true,
+    "use_regex": true
   },
   "post_processor": {
     "type": "ByteLevel",
     "add_prefix_space": true,
-    "trim_offsets": false
+    "trim_offsets": false,
+    "use_regex": true
   },
   "decoder": {
     "type": "ByteLevel",
     "add_prefix_space": true,
-    "trim_offsets": true
+    "trim_offsets": true,
+    "use_regex": true
   },
   "model": {
     "type": "BPE",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf8954b17ca57cc4a2001b78b707ff6fefce35396c51d37b7440f2be8754146b
-size 2991
+oid sha256:ca91ec914b2f4dde2cf70faf7e0d06029cc85b09fd6622441bcf0b3d461426f2
+size 3055