New model from https://wandb.ai/wandb/huggingtweets/runs/i4y4qpk0

README.md

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: http://www.huggingtweets.com/cobratate/1674653451025/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 Andrew Tate.
 
 | Data | Andrew Tate |
 | --- | --- |
-| Tweets downloaded | 938 |
-| Retweets | 353 |
-| Short tweets | 148 |
-| Tweets kept | 437 |
+| Tweets downloaded | 3191 |
+| Retweets | 1336 |
+| Short tweets | 361 |
+| Tweets kept | 1494 |
 
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/83ddh315/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/lv5mfcaj/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 @cobratate's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/5usxslxq) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/i4y4qpk0) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/5usxslxq/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/i4y4qpk0/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -37,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.26.0",
+  "transformers_version": "4.28.0",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.26.0"
+  "transformers_version": "4.28.0"
 }

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2 - Trained by `huggingface/tokenizers`
+#version: 0.2
 Ġ t
 Ġ a
 h e

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c6f7b10ec4a05226c7fb73fa6e33f3e24484ee873e6cf4921ae92970bc7a6be
+oid sha256:1fef74b8bc87e630a07d6f708a1aef5ce90f0628810bf948aecfd9246e0cd3e6
 size 510398013

tokenizer.json

@@ -39,6 +39,7 @@
     "continuing_subword_prefix": "",
     "end_of_word_suffix": "",
     "fuse_unk": false,
+    "byte_fallback": false,
     "vocab": {
       "!": 0,
       "\"": 1,

tokenizer_config.json

@@ -1,10 +1,9 @@
 {
   "add_prefix_space": false,
   "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
-  "name_or_path": "gpt2",
-  "special_tokens_map_file": null,
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3f6e5fbb73440a77f226f548b1b2c55ec55e6862a4bdceb8edc8ccf0b0b59dc
-size 3515
+oid sha256:43d79beca1fc888121108331456460ec1caa0ee6c1ec782cf515d3bd2e899032
+size 3579