New model from https://wandb.ai/wandb/huggingtweets/runs/1hdne87l

README.md

@@ -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/1365566121592692736/KP8KDo2-_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/1523268231833739266/foV-CaZh_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;)">
@@ -20,7 +20,7 @@ widget:
         </div>
     </div>
     <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
-    <div style="text-align: center; font-size: 16px; font-weight: 800">KitsuneSpirit🦊💝 VTuber ~</div>
+    <div style="text-align: center; font-size: 16px; font-weight: 800">KitsuneSpirit Mei 💝🦊「 YOKOMESHI 」</div>
     <div style="text-align: center; font-size: 14px;">@kitsune__spirit</div>
 </div>
 
@@ -38,24 +38,24 @@ To understand how the model was developed, check the [W&B report](https://wandb.
 
 ## Training data
 
-The model was trained on tweets from KitsuneSpirit🦊💝 VTuber ~.
+The model was trained on tweets from KitsuneSpirit Mei 💝🦊「 YOKOMESHI 」.
 
-| Data | KitsuneSpirit🦊💝 VTuber ~ |
+| Data | KitsuneSpirit Mei 💝🦊「 YOKOMESHI 」 |
 | --- | --- |
-| Tweets downloaded | 3250 |
-| Retweets | 65 |
-| Short tweets | 998 |
-| Tweets kept | 2187 |
+| Tweets downloaded | 3248 |
+| Retweets | 67 |
+| Short tweets | 820 |
+| Tweets kept | 2361 |
 
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3qfz2kzl/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/3uiy3sjw/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 @kitsune__spirit's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2mrv13gz) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1hdne87l) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2mrv13gz/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1hdne87l/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 +17,10 @@
   "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,
   "summary_proj_to_labels": true,
@@ -34,7 +36,8 @@
       "top_p": 0.95
     }
   },
-  "transformers_version": "4.5.1",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
   "use_cache": true,
   "vocab_size": 50257
 }

flax_model.msgpack

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:28fcdf07c27ad79d29d75bebc4bddd942244415483f2ae815a0a2d3121aa3066
-size 497764120

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94ba9af93f0bdc263de61bde194436aa99fdf7c12b6e96c0bb13ee5c8814f55a
-size 510408315
+oid sha256:4f200f3210752f90ef8a868267f6fc83d3bc4db01342c42ba769e268b7508951
+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"}
+{
+  "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:f47ee23e9e468d6e1f4c29cd9912693c607bc4b7e0d2e7504a9ff9abb1a08cad
-size 2351
+oid sha256:d528180985a75b774a15bdd51cfd92807ccc5ab10250c3e2c3bd1a84ebda92c5
+size 3311