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

README.md

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: https://www.huggingtweets.com/wojespn/1624920443576/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 Adrian Wojnarowski.
 | Data | Adrian Wojnarowski |
 | --- | --- |
 | Tweets downloaded | 3250 |
-| Retweets | 776 |
-| Short tweets | 34 |
-| Tweets kept | 2440 |
+| Retweets | 672 |
+| Short tweets | 48 |
+| Tweets kept | 2530 |
 
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/21fnso5k/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/2cwc7lqa/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 @wojespn's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3faibj6b) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1nagaxwf) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3faibj6b/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1nagaxwf/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -8,7 +8,6 @@
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
-  "gradient_checkpointing": false,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
@@ -18,7 +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 +36,8 @@
       "top_p": 0.95
     }
   },
-  "transformers_version": "4.8.1",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
   "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d68ebf00901364cb2df0b44980d219a834a6479fc47706974506b465f601215b
+oid sha256:f8645e3aee060ef02dfe36f41eb2a6775fe5c738c569f4e8a054b2e7d1b385c8
 size 510403817

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5995a21a2ac8f1da871eaadbaf07c5db11fadc58794947f9c264a525120ea1
-size 2607
+oid sha256:c648ce0acc8692f2a09008ccd69e034b883dea56a8800f85b96a57773307157b
+size 2927