New model from https://wandb.ai/wandb/huggingtweets/runs/uxqtp9fw

README.md

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: http://www.huggingtweets.com/zackfox/1655048563971/predictions.png
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
@@ -42,20 +42,20 @@ The model was trained on tweets from Zack Fox.
 
 | Data | Zack Fox |
 | --- | --- |
-| Tweets downloaded | 950 |
-| Retweets | 143 |
-| Short tweets | 303 |
-| Tweets kept | 504 |
+| Tweets downloaded | 1238 |
+| Retweets | 198 |
+| Short tweets | 405 |
+| Tweets kept | 635 |
 
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2dfumi9u/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/dln0z2za/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 @zackfox's tweets.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1mpcixky) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/uxqtp9fw) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1mpcixky/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/uxqtp9fw/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "gpt2-medium",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -12,11 +12,13 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
+  "n_embd": 1024,
+  "n_head": 16,
   "n_inner": null,
-  "n_layer": 12,
+  "n_layer": 24,
   "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": true,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -37,7 +39,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.19.4",
+  "transformers_version": "4.28.1",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.28.1"
+}

merges.txt

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

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d2e892bc5ffe37376e4783e3f0dfd61094ccb56cf031fab8b0926ec2c70c923
-size 510396521
+oid sha256:80ba5d0f72f15c471c482e51e5d01299a021f447f87c3fa41f13523463f622e6
+size 1444569373

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.json

@@ -39,6 +39,7 @@
     "continuing_subword_prefix": "",
     "end_of_word_suffix": "",
     "fuse_unk": false,
+    "byte_fallback": false,
     "vocab": {
       "!": 0,
       "\"": 1,

tokenizer_config.json

@@ -1 +1,9 @@
-{"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"}
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee5f52af76cc4816e0e7b2df8b01c5f31af20baf5c55924e51040bffa5d2c344
-size 3183
+oid sha256:61331b27db1928658b9ae7e7cd97d3b79eb5f6f4ddb79609de384290aae3c969
+size 3579