added app files

app.py

@@ -0,0 +1,86 @@
+import gradio as gr
+
+import nltk
+import string
+from transformers import GPT2LMHeadModel, GPT2Tokenizer, GenerationConfig, set_seed
+import random
+
+response_length = 200
+
+sentence_detector = nltk.data.load('tokenizers/punkt/english.pickle')
+
+tokenizer = GPT2Tokenizer.from_pretrained("gpt2-medium")
+tokenizer.truncation_side = 'right'
+
+model = GPT2LMHeadModel.from_pretrained('checkpoint-10000')
+generation_config = GenerationConfig.from_pretrained('gpt2-medium')
+generation_config.max_new_tokens = response_length
+generation_config.pad_token_id = generation_config.eos_token_id
+
+
+outputs = []
+
+
+def generate_response(new_prompt):
+
+    global outputs
+    story_so_far = "\n".join(outputs[:int(1024 / response_length + 1)])
+
+    set_seed(random.randint(0, 4000000000))
+    inputs = tokenizer.encode(story_so_far + '\n' + new_prompt if story_so_far else new_prompt,
+                              return_tensors='pt', truncation=True,
+                              max_length=1024 - response_length)
+
+    output = model.generate(inputs, do_sample=True, generation_config=generation_config)
+    response = clean_paragraph(tokenizer.batch_decode(output)[0][((len(story_so_far) + 1) if story_so_far else 0):])
+    outputs.append(response)
+
+    return ((story_so_far + '\n' if story_so_far else '') + response).replace('\n', '\n\n')
+
+def undo():
+    global outputs
+    print(outputs)
+    outputs = outputs[:-1]
+    print(outputs)
+    return "\n".join(outputs).replace('\n', '\n\n')
+
+def clean_paragraph(entry):
+    paragraphs = entry.split('\n')
+
+    for i in range(len(paragraphs)):
+        split_sentences = nltk.tokenize.sent_tokenize(paragraphs[i], language='english')
+        if i == len(paragraphs) - 1 and split_sentences[:1][-1] not in string.punctuation:
+            paragraphs[i] = " ".join(split_sentences[:-1])
+
+    return capitalize_first_char("\n".join(paragraphs))
+
+def reset():
+    global outputs
+    outputs = []
+    return None
+
+def capitalize_first_char(entry):
+    for i in range(len(entry)):
+        if entry[i].isalpha():
+            return entry[:i] + entry[i].upper() + entry[i + 1:]
+    return entry
+
+with gr.Blocks() as demo:
+    story = gr.Textbox(interactive=False, lines=20)
+    story.style(show_copy_button=True)
+
+    prompt = gr.Textbox(placeholder="Continue the story here!", lines=3, max_lines=3)
+
+    with gr.Row():
+        gen_button = gr.Button('Generate')
+        undo_button = gr.Button("Undo")
+        res_button = gr.Button("Reset")
+
+    prompt.submit(generate_response, prompt, story, scroll_to_output=True)
+    gen_button.click(generate_response, prompt, story, scroll_to_output=True)
+    undo_button.click(undo, [], story, scroll_to_output=True)
+    res_button.click(reset, [], story, scroll_to_output=True)
+
+demo.launch(inbrowser=True)
+
+

checkpoint-10000/config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "gpt2-medium",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "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_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "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,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-10000/generation_config.json

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

checkpoint-10000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:714f3c35c4eaa81e750f7e2e5862edf3b104c6e8b8039cd6a5d3106805a5aced
+size 2838756549

checkpoint-10000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b4d10f7689cea0856cf9fa5ce274eb6006f9852b6cfaf137e93376448a3db9
+size 1444569373

checkpoint-10000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3edda5e835455fbfa5ef36857a5b651ac923bd4638899b1783d40cf864a4aea8
+size 14583

checkpoint-10000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cb5778788b3edc5a26f73ca723a7507e96882fb99aa3b4d3c8d3fdc4e953e3a
+size 14583

checkpoint-10000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55cba491a0505b8a12c6c03ade1fc3f2fc45ad345b948c4de63adeabcda228b2
+size 557

checkpoint-10000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cb16482cc67d8670df29f2476270f3d41c3a66021703a9c5d6dc8c2e59d5ce0
+size 627

checkpoint-10000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-10000/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-10000/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.195510803440319,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.05,
+      "learning_rate": 6.234097519017773e-05,
+      "loss": 2.9092,
+      "step": 2500
+    },
+    {
+      "epoch": 1.05,
+      "eval_loss": 2.7911548614501953,
+      "eval_runtime": 359.1547,
+      "eval_samples_per_second": 11.8,
+      "eval_steps_per_second": 2.951,
+      "step": 2500
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 6.137463890549805e-05,
+      "loss": 2.7715,
+      "step": 5000
+    },
+    {
+      "epoch": 2.1,
+      "eval_loss": 2.7525341510772705,
+      "eval_runtime": 358.9958,
+      "eval_samples_per_second": 11.805,
+      "eval_steps_per_second": 2.953,
+      "step": 5000
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 5.9557478454587004e-05,
+      "loss": 2.688,
+      "step": 7500
+    },
+    {
+      "epoch": 3.15,
+      "eval_loss": 2.737689256668091,
+      "eval_runtime": 359.124,
+      "eval_samples_per_second": 11.801,
+      "eval_steps_per_second": 2.952,
+      "step": 7500
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 5.6939618780421336e-05,
+      "loss": 2.6213,
+      "step": 10000
+    },
+    {
+      "epoch": 4.2,
+      "eval_loss": 2.728829860687256,
+      "eval_runtime": 359.1054,
+      "eval_samples_per_second": 11.802,
+      "eval_steps_per_second": 2.952,
+      "step": 10000
+    }
+  ],
+  "max_steps": 47660,
+  "num_train_epochs": 20,
+  "total_flos": 2.433430888256635e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:725092dcfad06c0f8f972968c8270418de57a1d4a00c388e757fdc1753aa5f9f
+size 3515

main.py

@@ -1,4 +0,0 @@
-import bot
-
-if __name__ == '__main__':
-    bot.run_discord_bot()