New model from https://wandb.ai/wandb/huggingtweets/runs/10x8dyea

README.md

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: https://www.huggingtweets.com/clamtime/1614098345455/predictions.png
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
@@ -8,7 +8,7 @@ widget:
 ---
 
 <div>
-<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1363504937406193668/mIjshP0L_400x400.jpg')">
+<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1384662289777893379/s2NlrjMS_400x400.jpg')">
 </div>
 <div style="margin-top: 8px; font-size: 19px; font-weight: 800">clementine!!!! 𓆏 🤖 AI Bot </div>
 <div style="font-size: 15px">@clamtime bot</div>
@@ -24,7 +24,7 @@ The model uses the following pipeline.
 
 ![pipeline](https://github.com/borisdayma/huggingtweets/blob/master/img/pipeline.png?raw=true)
 
-To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
+To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
 
 ## Training data
 
@@ -32,20 +32,20 @@ The model was trained on [@clamtime's tweets](https://twitter.com/clamtime).
 
 | Data | Quantity |
 | --- | --- |
-| Tweets downloaded | 2839 |
-| Retweets | 668 |
-| Short tweets | 474 |
-| Tweets kept | 1697 |
+| Tweets downloaded | 3169 |
+| Retweets | 711 |
+| Short tweets | 586 |
+| Tweets kept | 1872 |
 
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3exqwwz0/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/3qzb1bqs/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 @clamtime's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/zntnw76s) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/10x8dyea) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/zntnw76s/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/10x8dyea/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -34,7 +34,7 @@
       "top_p": 0.95
     }
   },
-  "transformers_version": "4.3.2",
+  "transformers_version": "4.5.1",
   "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b29d361f8f2677efe1ba18277062262dbc9416aef6dcf25984023c88606bd771
-size 510406560
+oid sha256:f4d84dbb5b4408c4542c35f3a006a557757ff1b52b114b524746999b3178988b
+size 510408315

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "name_or_path": "gpt2"}
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d8aabb6cdb7d85ae80d965fa123cb4c0ef295984c7f08d7a9facb7a4b27fd0
-size 2159
+oid sha256:6cc7249caa6617a4daa1128f9be664853fdff4c48fec9703c17145f3b3fa6fdf
+size 2351