New model from https://wandb.ai/wandb/huggingtweets/runs/1wqrxml6

README.md

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: https://www.huggingtweets.com/nytimes/1635223960388/predictions.png
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
@@ -43,19 +43,19 @@ The model was trained on tweets from The New York Times.
 | Data | The New York Times |
 | --- | --- |
 | Tweets downloaded | 3250 |
-| Retweets | 503 |
-| Short tweets | 0 |
-| Tweets kept | 2747 |
+| Retweets | 461 |
+| Short tweets | 5 |
+| Tweets kept | 2784 |
 
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/19jlccdf/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/1slz5aji/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 @nytimes's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/23hnup9i) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1wqrxml6) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/23hnup9i/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1wqrxml6/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -17,7 +17,9 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
@@ -35,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.11.3",
+  "transformers_version": "4.21.2",
   "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff499736245e605199e3f08bd54334400f80d6e01abce9382502a7f3108ead3e
-size 510403817
+oid sha256:69e43240ca23bd8b6e30036818257439d9ec3453f4be6ff93ba9beb0430c2d87
+size 510396521

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_config.json

@@ -1 +1,10 @@
-{"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|>",
+  "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 sha256:08460aa6cbc9bc56b765719a206173329dc21152daeab21a0a8ece24a5a6ea96
-size 2863
+oid sha256:478033189c6c30f31960ab1a7975d846de382081954c4ec03064a6d4d3b1c9ba
+size 3311