New model from https://wandb.ai/wandb/huggingtweets/runs/00b9i1fj

README.md

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: http://www.huggingtweets.com/therock/1644245282576/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 Dwayne Johnson.
 
 | Data | Dwayne Johnson |
 | --- | --- |
-| Tweets downloaded | 3243 |
-| Retweets | 747 |
-| Short tweets | 63 |
+| Tweets downloaded | 3186 |
+| Retweets | 651 |
+| Short tweets | 102 |
 | Tweets kept | 2433 |
 
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/f2c9p353/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/ut9satny/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 @therock's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/n5fgasyj) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/00b9i1fj) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/n5fgasyj/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/00b9i1fj/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -37,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.16.2",
+  "transformers_version": "4.28.1",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.28.1"
+}

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 sha256:6825cd6de7599a388a3da661569e6e7eac119460cba37311c0bee72a69b442b4
-size 510403817
+oid sha256:04b9274a4256d735690f7db65dd1c59d9fff46cbc9755c4ec09bbff382f99999
+size 510398013

special_tokens_map.json

@@ -1 +1,5 @@
-{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

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",
@@ -36,6 +39,7 @@
     "continuing_subword_prefix": "",
     "end_of_word_suffix": "",
     "fuse_unk": false,
+    "byte_fallback": false,
     "vocab": {
       "!": 0,
       "\"": 1,

tokenizer_config.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e0d842b8e724ccfe535c7f5ca986eae0b0bb6adbebc14eb45c2399e9e881fd3
-size 2991
+oid sha256:4de7e69830ec3f4d893a990ed14268491eb5ddb6c4750ea810482927a2e36284
+size 3579