New model from https://wandb.ai/wandb/huggingtweets/runs/r9ejkubu

README.md

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: https://www.huggingtweets.com/ai_hexcrawl/1625854393329/predictions.png
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
@@ -10,7 +10,7 @@ widget:
 <div class="inline-flex flex-col" style="line-height: 1.5;">
     <div class="flex">
         <div
-			style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://pbs.twimg.com/profile_images/1391882949650440200/lmEKl2ZQ_400x400.jpg&#39;)">
+			style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://pbs.twimg.com/profile_images/1467327234365181953/gFho8YCv_400x400.jpg&#39;)">
         </div>
         <div
             style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;&#39;)">
@@ -42,20 +42,20 @@ The model was trained on tweets from AI Hexcrawl.
 
 | Data | AI Hexcrawl |
 | --- | --- |
-| Tweets downloaded | 384 |
-| Retweets | 11 |
-| Short tweets | 0 |
-| Tweets kept | 373 |
+| Tweets downloaded | 1164 |
+| Retweets | 42 |
+| Short tweets | 2 |
+| Tweets kept | 1120 |
 
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2g5e7kn3/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/vdxugbwr/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 @ai_hexcrawl's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/395id7uq) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/r9ejkubu) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/395id7uq/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/r9ejkubu/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": "4.8.2",
+  "torch_dtype": "float32",
+  "transformers_version": "4.14.1",
   "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6075da1dbf503a5f56b1bf72716503049285d599ba39d4829161ccf0954ab06a
+oid sha256:bdccef3c584674acdbd0154c94d49c770024f64169451725bf13aaea99772f94
 size 510403817

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42e3950b8479152b331465dc5e2217232f46ec73cc8ef9a9b57340bedac3a648
-size 2671
+oid sha256:634f191e4833686f3ff61a4602134e0214fe47c1bef84170ac47ad16aa2d50c6
+size 2927