New model from https://wandb.ai/wandb/huggingtweets/runs/3papp840

README.md

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo_share.png?raw=true
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
@@ -19,7 +19,7 @@ widget:
 <section class='prose'>
 
 <div>
-<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('http://pbs.twimg.com/profile_images/1197606280082280448/d1HEh7Lh_400x400.jpg')">
+<div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1320840184494108674/d7A64nIG_400x400.jpg')">
 </div>
 <div style="margin-top: 8px; font-size: 19px; font-weight: 800">Charles 🎉 Frye 🤖 AI Bot </div>
 <div style="font-size: 15px; color: #657786">@charles_irl bot</div>
@@ -35,7 +35,7 @@ The model uses the following pipeline.
 
 ![pipeline](https://github.com/borisdayma/huggingtweets/blob/master/img/pipeline.png?raw=true)
 
-To understand how the model was developed, check the [W&B report](https://bit.ly/2TGXMZf).
+To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
 
 ## Training data
 
@@ -51,32 +51,32 @@ The model was trained on [@charles_irl's tweets](https://twitter.com/charles_irl
 <tbody style='border-width:0'>
 <tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
 <td style='border-width:0'>Tweets downloaded</td>
-<td style='border-width:0'>780</td>
+<td style='border-width:0'>1207</td>
 </tr>
 <tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
 <td style='border-width:0'>Retweets</td>
-<td style='border-width:0'>168</td>
+<td style='border-width:0'>249</td>
 </tr>
 <tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
 <td style='border-width:0'>Short tweets</td>
-<td style='border-width:0'>22</td>
+<td style='border-width:0'>47</td>
 </tr>
 <tr style='border-width:0'>
 <td style='border-width:0'>Tweets kept</td>
-<td style='border-width:0'>590</td>
+<td style='border-width:0'>911</td>
 </tr>
 </tbody>
 </table>
 
-[Explore the data](https://app.wandb.ai/wandb/huggingtweets/runs/3g45moaj/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/1osnjxmi/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 @charles_irl's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets/runs/2omraa20) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3papp840) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets/runs/2omraa20/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3papp840/artifacts) is logged and versioned.
 
 ## Intended uses & limitations
 
@@ -102,7 +102,7 @@ In addition, the data present in the user's tweets further affects the text gene
 
 </section>
 
-[![Follow](https://img.shields.io/twitter/follow/borisdayma?style=social)](https://twitter.com/borisdayma)
+[![Follow](https://img.shields.io/twitter/follow/borisdayma?style=social)](https://twitter.com/intent/follow?screen_name=borisdayma)
 
 <section class='prose'>
 For more details, visit the project repository.

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -7,6 +8,7 @@
   "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",
@@ -32,5 +34,7 @@
       "top_p": 0.95
     }
   },
+  "transformers_version": "4.2.0",
+  "use_cache": true,
   "vocab_size": 50257
 }

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2
+#version: 0.2 - Trained by `huggingface/tokenizers`
 Ġ t
 Ġ a
 h e

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:781a51f9c7f110460d427fa53ebbd8b123cbd51c775f04dccd5ab18f02c9bf13
-size 510408315
+oid sha256:bd0563c013557ffea64aa7a506a7dce4583e8f7014ac75c9305dd6513f832cd3
+size 510406559

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}

tokenizer_config.json

@@ -1 +1 @@
-{"model_max_length": 1024}
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "name_or_path": "gpt2"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a79c2df2cdf86448780f28021b3314537b2df10c5641745037c6b52b81f195e
+size 2031