Use YAML for presets and settings

.gitignore

@@ -22,6 +22,7 @@ venv/
 *.log
 
 settings.json
+settings.yaml
 notification.mp3
 img_bot*
 img_me*

README.md

@@ -207,7 +207,7 @@ Optionally, you can use the following command-line flags:
 | `--lora-dir LORA_DIR`                      | Path to directory with all the loras. |
 | `--model-menu`                             | Show a model menu in the terminal when the web UI is first launched. |
 | `--no-stream`                              | Don't stream the text output in real time. |
-| `--settings SETTINGS_FILE`                 | Load the default interface settings from this json file. See `settings-template.json` for an example. If you create a file called `settings.json`, this file will be loaded by default without the need to use the `--settings` flag. |
+| `--settings SETTINGS_FILE`                 | Load the default interface settings from this yaml file. See `settings-template.yaml` for an example. If you create a file called `settings.yaml`, this file will be loaded by default without the need to use the `--settings` flag. |
 | `--extensions EXTENSIONS [EXTENSIONS ...]` | The list of extensions to load. If you want to load more than one extension, write the names separated by spaces. |
 | `--verbose`                                | Print the prompts to the terminal. |
 

modules/chat.py

@@ -641,7 +641,7 @@ def save_character(name, greeting, context, picture, filename, instruct=False):
     data = {k: v for k, v in data.items() if v}  # Strip falsy
     filepath = Path(f'{folder}/{filename}.yaml')
     with filepath.open('w') as f:
-        yaml.dump(data, f)
+        yaml.dump(data, f, sort_keys=False)
 
     logger.info(f'Wrote {filepath}')
     path_to_img = Path(f'{folder}/{filename}.png')

modules/shared.py

@@ -65,18 +65,9 @@ settings = {
     'chat_generation_attempts_min': 1,
     'chat_generation_attempts_max': 10,
     'default_extensions': [],
-    'chat_default_extensions': ["gallery"],
-    'presets': {
-        'default': 'Default',
-        '.*(alpaca|llama|llava|vicuna)': "LLaMA-Precise",
-        '.*pygmalion': 'NovelAI-Storywriter',
-        '.*RWKV.*\.pth': 'Naive',
-        '.*moss': 'MOSS',
-    },
-    'prompts': {
-        'default': 'QA',
-        '.*(gpt4chan|gpt-4chan|4chan)': 'GPT-4chan',
-    }
+    'chat_default_extensions': ['gallery'],
+    'preset': 'LLaMA-Precise',
+    'prompt': 'QA',
 }
 
 
@@ -103,7 +94,7 @@ parser.add_argument("--model-dir", type=str, default='models/', help="Path to di
 parser.add_argument("--lora-dir", type=str, default='loras/', help="Path to directory with all the loras")
 parser.add_argument('--model-menu', action='store_true', help='Show a model menu in the terminal when the web UI is first launched.')
 parser.add_argument('--no-stream', action='store_true', help='Don\'t stream the text output in real time.')
-parser.add_argument('--settings', type=str, help='Load the default interface settings from this json file. See settings-template.json for an example. If you create a file called settings.json, this file will be loaded by default without the need to use the --settings flag.')
+parser.add_argument('--settings', type=str, help='Load the default interface settings from this yaml file. See settings-template.yaml for an example. If you create a file called settings.yaml, this file will be loaded by default without the need to use the --settings flag.')
 parser.add_argument('--extensions', type=str, nargs="+", help='The list of extensions to load. If you want to load more than one extension, write the names separated by spaces.')
 parser.add_argument('--verbose', action='store_true', help='Print the prompts to the terminal.')
 

modules/utils.py

@@ -29,7 +29,7 @@ def get_available_models():
 
 
 def get_available_presets():
-    return sorted(set((k.stem for k in Path('presets').glob('*.txt'))), key=natural_keys)
+    return sorted(set((k.stem for k in Path('presets').glob('*.yaml'))), key=natural_keys)
 
 
 def get_available_prompts():

presets/Contrastive Search.txt

@@ -1,3 +0,0 @@
-do_sample=False
-penalty_alpha=0.6
-top_k=4

presets/Contrastive Search.yaml

@@ -0,0 +1,3 @@
+do_sample: False
+penalty_alpha: 0.6
+top_k: 4

presets/Debug-deterministic.txt

@@ -1 +0,0 @@
-do_sample=False

presets/Debug-deterministic.yaml

@@ -0,0 +1 @@
+do_sample: False

presets/Default.txt

@@ -1,6 +0,0 @@
-do_sample=True
-top_p=0.5
-top_k=40
-temperature=0.7
-repetition_penalty=1.2
-typical_p=1.0

presets/Default.yaml

@@ -0,0 +1,6 @@
+do_sample: true
+top_p: 0.5
+top_k: 40
+temperature: 0.7
+repetition_penalty: 1.2
+typical_p: 1.0

presets/Kobold-Godlike.txt

@@ -1,6 +0,0 @@
-do_sample=True
-top_p=0.5
-top_k=0
-temperature=0.7
-repetition_penalty=1.1
-typical_p=0.19

presets/Kobold-Godlike.yaml

@@ -0,0 +1,6 @@
+do_sample: true
+top_p: 0.5
+top_k: 0
+temperature: 0.7
+repetition_penalty: 1.1
+typical_p: 0.19

presets/Kobold-Liminal Drift.txt

@@ -1,6 +0,0 @@
-do_sample=True
-top_p=1.0
-top_k=0
-temperature=0.66
-repetition_penalty=1.1
-typical_p=0.6

presets/Kobold-Liminal Drift.yaml

@@ -0,0 +1,6 @@
+do_sample: true
+top_p: 1.0
+top_k: 0
+temperature: 0.66
+repetition_penalty: 1.1
+typical_p: 0.6

presets/LLaMA-Precise.txt

@@ -1,6 +0,0 @@
-do_sample=True
-top_p=0.1
-top_k=40
-temperature=0.7
-repetition_penalty=1.18
-typical_p=1.0

presets/LLaMA-Precise.yaml

@@ -0,0 +1,6 @@
+do_sample: true
+top_p: 0.1
+top_k: 40
+temperature: 0.7
+repetition_penalty: 1.18
+typical_p: 1.0

presets/MOSS.txt

@@ -1,3 +0,0 @@
-temperature=0.7
-top_p=0.8
-repetition_penalty=1.02

presets/MOSS.yaml

@@ -0,0 +1,3 @@
+temperature: 0.7
+top_p: 0.8
+repetition_penalty: 1.02

presets/Naive.txt

@@ -1,4 +0,0 @@
-do_sample=True
-temperature=0.7
-top_p=0.85
-top_k=50

presets/Naive.yaml

@@ -0,0 +1,4 @@
+do_sample: true
+temperature: 0.7
+top_p: 0.85
+top_k: 50

presets/NovelAI-Best Guess.txt

@@ -1,6 +0,0 @@
-do_sample=True
-top_p=0.9
-top_k=100
-temperature=0.8
-repetition_penalty=1.15
-typical_p=1.0

presets/NovelAI-Best Guess.yaml

@@ -0,0 +1,6 @@
+do_sample: true
+top_p: 0.9
+top_k: 100
+temperature: 0.8
+repetition_penalty: 1.15
+typical_p: 1.0

presets/NovelAI-Decadence.txt

@@ -1,6 +0,0 @@
-do_sample=True
-top_p=1.0
-top_k=100
-temperature=2
-repetition_penalty=1
-typical_p=0.97

presets/NovelAI-Decadence.yaml

@@ -0,0 +1,6 @@
+do_sample: true
+top_p: 1.0
+top_k: 100
+temperature: 2
+repetition_penalty: 1
+typical_p: 0.97

presets/NovelAI-Genesis.txt

@@ -1,6 +0,0 @@
-do_sample=True
-top_p=0.98
-top_k=0
-temperature=0.63
-repetition_penalty=1.05
-typical_p=1.0

presets/NovelAI-Genesis.yaml

@@ -0,0 +1,6 @@
+do_sample: true
+top_p: 0.98
+top_k: 0
+temperature: 0.63
+repetition_penalty: 1.05
+typical_p: 1.0

presets/NovelAI-Lycaenidae.txt

@@ -1,6 +0,0 @@
-do_sample=True
-top_p=0.85
-top_k=12
-temperature=2
-repetition_penalty=1.15
-typical_p=1.0

presets/NovelAI-Lycaenidae.yaml

@@ -0,0 +1,6 @@
+do_sample: true
+top_p: 0.85
+top_k: 12
+temperature: 2
+repetition_penalty: 1.15
+typical_p: 1.0

presets/NovelAI-Ouroboros.txt

@@ -1,6 +0,0 @@
-do_sample=True
-top_p=1.0
-top_k=100
-temperature=1.07
-repetition_penalty=1.05
-typical_p=1.0

presets/NovelAI-Ouroboros.yaml

@@ -0,0 +1,6 @@
+do_sample: true
+top_p: 1.0
+top_k: 100
+temperature: 1.07
+repetition_penalty: 1.05
+typical_p: 1.0

presets/NovelAI-Pleasing Results.txt

@@ -1,6 +0,0 @@
-do_sample=True
-top_p=1.0
-top_k=0
-temperature=0.44
-repetition_penalty=1.15
-typical_p=1.0

presets/NovelAI-Pleasing Results.yaml

@@ -0,0 +1,6 @@
+do_sample: true
+top_p: 1.0
+top_k: 0
+temperature: 0.44
+repetition_penalty: 1.15
+typical_p: 1.0

presets/NovelAI-Sphinx Moth.txt

@@ -1,6 +0,0 @@
-do_sample=True
-top_p=0.18
-top_k=30
-temperature=2.0
-repetition_penalty=1.15
-typical_p=1.0

presets/NovelAI-Sphinx Moth.yaml

@@ -0,0 +1,6 @@
+do_sample: true
+top_p: 0.18
+top_k: 30
+temperature: 2.0
+repetition_penalty: 1.15
+typical_p: 1.0

presets/NovelAI-Storywriter.txt

@@ -1,6 +0,0 @@
-do_sample=True
-top_p=0.73
-top_k=0
-temperature=0.72
-repetition_penalty=1.1
-typical_p=1.0

presets/NovelAI-Storywriter.yaml

@@ -0,0 +1,6 @@
+do_sample: true
+top_p: 0.73
+top_k: 0
+temperature: 0.72
+repetition_penalty: 1.1
+typical_p: 1.0

presets/Verbose (Beam Search).txt

@@ -1,9 +0,0 @@
-num_beams=10
-min_length=200
-length_penalty=1.4
-no_repeat_ngram_size=2
-early_stopping=True
-temperature=0.7
-top_k=150
-top_p=0.92
-repetition_penalty=4.5

presets/Verbose (Beam Search).yaml

@@ -0,0 +1,9 @@
+num_beams: 10
+min_length: 200
+length_penalty: 1.4
+no_repeat_ngram_size: 2
+early_stopping: true
+temperature: 0.7
+top_k: 150
+top_p: 0.92
+repetition_penalty: 4.5

server.py

@@ -103,12 +103,11 @@ def load_preset_values(preset_menu, state, return_dict=False):
         'mirostat_eta': 0.1,
     }
 
-    with open(Path(f'presets/{preset_menu}.txt'), 'r') as infile:
-        preset = infile.read()
-    for i in preset.splitlines():
-        i = i.rstrip(',').strip().split('=')
-        if len(i) == 2 and i[0].strip() != 'tokens':
-            generate_params[i[0].strip()] = eval(i[1].strip())
+    with open(Path(f'presets/{preset_menu}.yaml'), 'r') as infile:
+        preset = yaml.safe_load(infile)
+
+    for k in preset:
+        generate_params[k] = preset[k]
 
     generate_params['temperature'] = min(1.99, generate_params['temperature'])
     if return_dict:
@@ -301,7 +300,7 @@ def save_model_settings(model, state):
             shared.model_config[model_regex][k] = state[k]
 
         with open(p, 'w') as f:
-            f.write(yaml.dump(user_config))
+            f.write(yaml.dump(user_config, sort_keys=False))
 
         yield (f"Settings for {model} saved to {p}")
 
@@ -551,11 +550,8 @@ def create_interface():
 
     # Defining some variables
     gen_events = []
-    default_preset = shared.settings['presets'][next((k for k in shared.settings['presets'] if re.match(k.lower(), shared.model_name.lower())), 'default')]
-    if len(shared.lora_names) == 1:
-        default_text = load_prompt(shared.settings['prompts'][next((k for k in shared.settings['prompts'] if re.match(k.lower(), shared.lora_names[0].lower())), 'default')])
-    else:
-        default_text = load_prompt(shared.settings['prompts'][next((k for k in shared.settings['prompts'] if re.match(k.lower(), shared.model_name.lower())), 'default')])
+    default_preset = shared.settings['preset']
+    default_text = load_prompt(shared.settings['prompt'])
     title = 'Text generation web UI'
 
     # Authentication variables
@@ -1016,16 +1012,19 @@ if __name__ == "__main__":
     settings_file = None
     if shared.args.settings is not None and Path(shared.args.settings).exists():
         settings_file = Path(shared.args.settings)
+    elif Path('settings.yaml').exists():
+        settings_file = Path('settings.yaml')
     elif Path('settings.json').exists():
         settings_file = Path('settings.json')
 
     if settings_file is not None:
         logger.info(f"Loading settings from {settings_file}...")
-        new_settings = json.loads(open(settings_file, 'r').read())
+        file_contents = open(settings_file, 'r', encoding='utf-8').read()
+        new_settings = json.loads(file_contents) if settings_file.suffix == "json" else yaml.safe_load(file_contents)
         for item in new_settings:
             shared.settings[item] = new_settings[item]
 
-    # Set default model settings based on settings.json
+    # Set default model settings based on settings file
     shared.model_config['.*'] = {
         'wbits': 'None',
         'model_type': 'None',

settings-template.json

@@ -1,47 +0,0 @@
-{
-    "dark_theme": false,
-    "autoload_model": true,
-    "max_new_tokens": 200,
-    "max_new_tokens_min": 1,
-    "max_new_tokens_max": 2000,
-    "seed": -1,
-    "character": "None",
-    "name1": "You",
-    "name2": "Assistant",
-    "context": "This is a conversation with your Assistant. It is a computer program designed to help you with various tasks such as answering questions, providing recommendations, and helping with decision making. You can ask it anything you want and it will do its best to give you accurate and relevant information.",
-    "greeting": "",
-    "turn_template": "",
-    "custom_stopping_strings": "",
-    "stop_at_newline": false,
-    "add_bos_token": true,
-    "ban_eos_token": false,
-    "skip_special_tokens": true,
-    "truncation_length": 2048,
-    "truncation_length_min": 0,
-    "truncation_length_max": 8192,
-    "mode": "chat",
-    "chat_style": "cai-chat",
-    "instruction_template": "None",
-    "chat-instruct_command": "Continue the chat dialogue below. Write a single reply for the character \"<|character|>\".\n\n<|prompt|>",
-    "chat_prompt_size": 2048,
-    "chat_prompt_size_min": 0,
-    "chat_prompt_size_max": 2048,
-    "chat_generation_attempts": 1,
-    "chat_generation_attempts_min": 1,
-    "chat_generation_attempts_max": 10,
-    "default_extensions": [],
-    "chat_default_extensions": [
-        "gallery"
-    ],
-    "presets": {
-        "default": "Default",
-        ".*(alpaca|llama|llava|vicuna)": "LLaMA-Precise",
-        ".*pygmalion": "NovelAI-Storywriter",
-        ".*RWKV.*\.pth": "Naive",
-        ".*moss": "MOSS"
-    },
-    "prompts": {
-        "default": "QA",
-        ".*(gpt4chan|gpt-4chan|4chan)": "GPT-4chan"
-    }
-}

settings-template.yaml

@@ -0,0 +1,42 @@
+dark_theme: false
+autoload_model: true
+max_new_tokens: 200
+max_new_tokens_min: 1
+max_new_tokens_max: 2000
+seed: -1
+character: None
+name1: You
+name2: Assistant
+context: This is a conversation with your Assistant. It is a computer program designed
+  to help you with various tasks such as answering questions, providing recommendations,
+  and helping with decision making. You can ask it anything you want and it will do
+  its best to give you accurate and relevant information.
+greeting: ''
+turn_template: ''
+custom_stopping_strings: ''
+stop_at_newline: false
+add_bos_token: true
+ban_eos_token: false
+skip_special_tokens: true
+truncation_length: 2048
+truncation_length_min: 0
+truncation_length_max: 8192
+mode: chat
+chat_style: cai-chat
+instruction_template: None
+chat-instruct_command: 'Continue the chat dialogue below. Write a single reply for
+  the character "<|character|>".
+
+
+  <|prompt|>'
+chat_prompt_size: 2048
+chat_prompt_size_min: 0
+chat_prompt_size_max: 2048
+chat_generation_attempts: 1
+chat_generation_attempts_min: 1
+chat_generation_attempts_max: 10
+default_extensions: []
+chat_default_extensions:
+- gallery
+preset: LLaMA-Precise
+prompt: QA