New model from https://wandb.ai/wandb/huggingtweets/runs/200pdxti

Browse files

Files changed (7) hide show

README.md +8 -8
config.json +5 -2
flax_model.msgpack +0 -3
pytorch_model.bin +2 -2
tokenizer.json +0 -0
tokenizer_config.json +1 -1
training_args.bin +2 -2

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: https://www.huggingtweets.com/michelleobama/1620772050236/predictions.png
 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/1366747801435185155/hZGK5WFL_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 Michelle Obama.
 | Data | Michelle Obama |
 | --- | --- |
-| Tweets downloaded | 1713 |
-| Retweets | 403 |
 | Short tweets | 10 |
-| Tweets kept | 1300 |
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2m1uk0tq/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 @michelleobama's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2096emrq) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2096emrq/artifacts) is logged and versioned.
 ## How to use

 ---
 language: en
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 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/1507471015110139906/T9rDVcLd_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;)">
 | Data | Michelle Obama |
 | --- | --- |
+| Tweets downloaded | 1932 |
+| Retweets | 439 |
 | Short tweets | 10 |
+| Tweets kept | 1483 |
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2m7f8b6p/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 @michelleobama's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/200pdxti) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/200pdxti/artifacts) is logged and versioned.
 ## How to use

config.json CHANGED Viewed

@@ -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,
   "resid_pdrop": 0.1,
   "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",
   "use_cache": true,
   "vocab_size": 50257
 }

   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "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,
       "top_p": 0.95
     }
   },
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.4",
   "use_cache": true,
   "vocab_size": 50257
 }

flax_model.msgpack DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bd1b0aade6c13ce02b09f6893333f77a732a3daa08c588430c283bb90a69523b
-size 497764120

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42272f9364982ff9b34ce506c945770c7c77705d1ba95fe5251632c4471266ca
-size 510408315

 version https://git-lfs.github.com/spec/v1
+oid sha256:a72439a896d1e06c29d2030e71492d1e4aad07902d8fdb1e261ca2a7b9147c12
+size 510396521

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"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"}


1	+ {"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"}

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cb37e4547d8f65cad0aa598a1b2928799e34a191d9849f0514a11576c5e2526
-size 2351

 version https://git-lfs.github.com/spec/v1
+oid sha256:f2f56a25bef6f267b0f35b956ffa72e87e5ec5c8fb035d920db3fedf3a0fa78d
+size 3247