New model from https://wandb.ai/wandb/huggingtweets/runs/gm17doqq

README.md

@@ -47,15 +47,15 @@ The model was trained on tweets from Elon Musk.
 | Short tweets | 1115 |
 | Tweets kept | 1901 |
 
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/rmv6hxmq/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/1m3c0mn7/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 @elonmusk's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/wan7uya3) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/gm17doqq) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/wan7uya3/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/gm17doqq/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -37,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.27.2",
+  "transformers_version": "4.24.0.dev0",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json

@@ -1,6 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
-  "transformers_version": "4.27.2"
-}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51e471a3a6a73e9e8270424c7a81974e65a923057bae2a431c7e98372bb8494b
-size 510398013
+oid sha256:0340e86f4a76ca998b1631bd176cb51d0c9bead3a65acdea40473b9da499a243
+size 510394089

tokenizer.json

@@ -17,20 +17,17 @@
   "pre_tokenizer": {
     "type": "ByteLevel",
     "add_prefix_space": false,
-    "trim_offsets": true,
-    "use_regex": true
+    "trim_offsets": true
   },
   "post_processor": {
     "type": "ByteLevel",
     "add_prefix_space": true,
-    "trim_offsets": false,
-    "use_regex": true
+    "trim_offsets": false
   },
   "decoder": {
     "type": "ByteLevel",
     "add_prefix_space": true,
-    "trim_offsets": true,
-    "use_regex": true
+    "trim_offsets": true
   },
   "model": {
     "type": "BPE",

tokenizer_config.json

@@ -3,6 +3,7 @@
   "bos_token": "<|endoftext|>",
   "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 sha256:6cde787a2fbd9df1a939c06f2b0b4b133f2dac821a02794431421a5bf7d54eab
-size 3579
+oid sha256:409dc0d1441186d1ad300e9b92230d970de379574cfd9691156f44008acef3cc
+size 3375