WoWQuestTextGenerator

.gitattributes

@@ -29,3 +29,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+model/scheduler.pt filter=lfs diff=lfs merge=lfs -text
+model/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+model/training_args.bin filter=lfs diff=lfs merge=lfs -text
+model/rng_state.pth filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,8 +1,8 @@
 ---
-title: WoWQuestTextGenerator
-emoji: 🏃
-colorFrom: blue
-colorTo: blue
+title: WoW Quest Generator
+emoji: 🧝‍♀️
+colorFrom: green
+colorTo: orange
 sdk: gradio
 sdk_version: 3.1.7
 app_file: app.py

app.py

@@ -0,0 +1,82 @@
+import gradio as gr
+from transformers import pipeline
+import random
+import re
+
+title = "WoW Quest Text Generator"
+description = "Tap on the \"Submit\" button to generate a random quest text."
+article = "<p>Fine tuned <a href=\"https://huggingface.co/EleutherAI/gpt-neo-125M\">EleutherAI/gpt-neo-125M</a> upon a formatted <a href=\"https://github.com/TrinityCore/TrinityCore\"> TrinityCore – TDB_full_world_927.22082_2022_08_21 Dataset</a></p><p>This generator is fan made and is not affiliated in any way with Blizzard and/or any other company</p>"
+
+model_id = "./model"
+text_generator = pipeline("text-generation", model=model_id, tokenizer=model_id)
+max_length = 192
+top_k = 40
+top_p = 0.92
+temperature = 1.0
+
+random.seed(None)
+
+wow_class_list = ["Death Knight", "Demon Hunter", "Druid", "Hunter", "Mage", "Monk", "Paladin", "Priest", "Rogue", "Shaman", "Warrior", "Warlock"]
+wow_race_list = ["Blood Elf", "Human", "Tauren", "Orc", "Kul Tiran", "Void Elf", "Troll", "Vulpera", "Night Elf", "Zandalari Troll", "Worgen", "Undead", "Goblin", "Highmountain Tauren", "Nightborne", "Dwarf", "Draenei", "Gnome", "Lightforged Draenei", "Pandaren", "Maghar Orc", "Mechagnome", "Dark Iron Dwarf"]
+wow_silly_name_list = ["Glitterstorm", "Sunderwear", "Arrowdynamic", "Sapntap", "Crossblesser", "Praystation", "Healium", "Shocknorris", "Alestrom", "Harryportal", "Merlìn", "Wreckquiem", "Owlcapone"]
+
+suggested_text_list = ["Greetings $r", "$c I need your help", "Good to see you $n", "Hey $gBoy:Girl; "]
+
+def parseGenderTokens(text):
+    regex = r"\$[gG]([^:]+):([^;]+);"
+    matches = re.finditer(regex, text, re.MULTILINE)
+    parsed_string = ""
+    prev_index = 0
+    group_num = 0
+    random_group = -1    
+    for matchNum, match in enumerate(matches, start=1):    
+        parsed_string += text[prev_index:match.start()]            
+        if random_group == -1:
+            group_num = len(match.groups())
+            random_group = random.randint(1, group_num)
+        parsed_string += match.group(random_group)
+        prev_index = match.end(group_num) + 1
+    parsed_string += text[prev_index:]
+    return parsed_string
+
+def parseSpecialCharacters(text, wow_class_item, wow_race_item, wow_silly_name_item):
+    parsedText = text.replace("$B", "\n").replace("$b", "\n").replace("$c", wow_class_item).replace("$C", wow_class_item).replace("$r", wow_race_item).replace("$R", wow_race_item).replace("$n", wow_silly_name_item).replace("$N", wow_silly_name_item)
+    return parseGenderTokens(parsedText)
+
+def text_generation(input_text = None):
+    if input_text == None or len(input_text) == 0:
+        input_text = "<|startoftext|>"
+    else:        
+        if input_text.startswith("<|startoftext|>") == False:            
+            input_text ="<|startoftext|>" + input_text
+    generated_text = text_generator(input_text,
+    max_length=max_length,
+    top_k=top_k, 
+    top_p=top_p,
+    temperature=temperature,
+    do_sample=True,
+    repetition_penalty=2.0,
+    bos_token="<|startoftext|>",
+    eos_token="<|endoftext|>", 
+    pad_token="<|pad|>",
+    unknown_token = "<|unknown|>",
+    num_return_sequences=1)
+    parsed_text = generated_text[0]["generated_text"].replace("<|startoftext|>", "").replace("\r","").replace("\n\n", "\n").replace("\t", " ").replace("<|pad|>", " * ").replace("\"\"", "\"")
+    wow_class_item = random.choice(wow_class_list)
+    wow_race_item = random.choice(wow_race_list)
+    wow_silly_name_item = random.choice(wow_silly_name_list)
+    parsed_text = parseSpecialCharacters(parsed_text, wow_class_item, wow_race_item, wow_silly_name_item)
+    parsed_text = parsed_text.replace("\\n", "\n")
+    return parsed_text
+
+gr.Interface(
+    text_generation,    
+    [gr.inputs.Textbox(lines=1, label="Enter strating text or leave blank")],
+    outputs=[gr.outputs.Textbox(type="auto", label="Generated quest text")],
+    title=title,
+    description=description,
+    article=article,
+    examples=suggested_text_list,
+    theme="default",
+    allow_flagging=False,
+).launch()

model/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|pad|>": 50258,
+  "<|startoftext|>": 50257
+}

model/config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-125M",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      6
+    ]
+  ],
+  "bos_token_id": 50256,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 12,
+  "num_layers": 12,
+  "resid_dropout": 0,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.2",
+  "use_cache": true,
+  "vocab_size": 50259,
+  "window_size": 256
+}

model/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:131c0394c90e7a276a2d60646fb35bd626b0cd949afb946eb9816340a1ca9c45
+size 1001693889

model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06a36064aa3b3fcbc6379befed64965c4a20bde5b343cdaefa0edc0cdd54ea6c
+size 551191249

model/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03a3c1141f8bebf59967bea65fa021fcc2ad8a3d7753ae183d1d946d3f5b6d8e
+size 14503

model/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a433fc7c4fe2e22525674ece37e19e095986d7600708d2a528f0478472b251
+size 623

model/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

model/tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 2048,
+  "name_or_path": "EleutherAI/gpt-neo-125M",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unknown_token": "<|unknown|>"
+}

model/trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.2171372930866602,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9075899457861016e-05,
+      "loss": 2.0374,
+      "step": 250
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.753573188762938e-05,
+      "loss": 1.6902,
+      "step": 500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.599556431739773e-05,
+      "loss": 1.6269,
+      "step": 750
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.445539674716609e-05,
+      "loss": 1.6167,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.2915229176934454e-05,
+      "loss": 1.568,
+      "step": 1250
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.137506160670281e-05,
+      "loss": 1.5706,
+      "step": 1500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.983489403647117e-05,
+      "loss": 1.558,
+      "step": 1750
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 3.829472646623953e-05,
+      "loss": 1.5502,
+      "step": 2000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 3.675455889600789e-05,
+      "loss": 1.534,
+      "step": 2250
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.5214391325776246e-05,
+      "loss": 1.5069,
+      "step": 2500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.367422375554461e-05,
+      "loss": 1.5202,
+      "step": 2750
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.213405618531297e-05,
+      "loss": 1.4854,
+      "step": 3000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.059388861508132e-05,
+      "loss": 1.4739,
+      "step": 3250
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.905372104484968e-05,
+      "loss": 1.4941,
+      "step": 3500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.751355347461804e-05,
+      "loss": 1.4642,
+      "step": 3750
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.59733859043864e-05,
+      "loss": 1.4524,
+      "step": 4000
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.4433218334154756e-05,
+      "loss": 1.3755,
+      "step": 4250
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.2893050763923117e-05,
+      "loss": 1.3779,
+      "step": 4500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 2.1352883193691475e-05,
+      "loss": 1.3758,
+      "step": 4750
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.9812715623459833e-05,
+      "loss": 1.3637,
+      "step": 5000
+    }
+  ],
+  "max_steps": 8216,
+  "num_train_epochs": 2,
+  "total_flos": 2861768122887168.0,
+  "trial_name": null,
+  "trial_params": null
+}

model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8fc79109b17bd5de5f6f4ae5ff262a057de0e111539bc97ae382655514eb717
+size 3247

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+torch
+transformers
+tokenizers
+