Organize internals (#6646)

modules/ui.py

@@ -102,55 +102,55 @@ else:
 
 def list_model_elements():
     elements = [
-        'loader',
         'filter_by_loader',
+        'loader',
         'cpu_memory',
-        'auto_devices',
-        'disk',
-        'cpu',
-        'bf16',
-        'load_in_4bit',
-        'load_in_8bit',
-        'torch_compile',
-        'trust_remote_code',
-        'no_use_fast',
-        'use_flash_attention_2',
-        'use_eager_attention',
-        'compute_dtype',
-        'quant_type',
-        'use_double_quant',
-        'cfg_cache',
-        'no_flash_attn',
-        'no_xformers',
-        'no_sdpa',
-        'num_experts_per_token',
-        'cache_type',
-        'autosplit',
-        'enable_tp',
+        'n_gpu_layers',
         'threads',
         'threads_batch',
         'n_batch',
-        'no_mmap',
-        'mlock',
-        'no_mul_mat_q',
-        'n_gpu_layers',
-        'tensor_split',
+        'hqq_backend',
         'n_ctx',
-        'gpu_split',
         'max_seq_len',
-        'compress_pos_emb',
+        'cache_type',
+        'tensor_split',
+        'gpu_split',
         'alpha_value',
         'rope_freq_base',
-        'numa',
-        'logits_all',
-        'no_offload_kqv',
-        'row_split',
-        'tensorcores',
-        'flash_attn',
-        'streaming_llm',
+        'compress_pos_emb',
+        'compute_dtype',
+        'quant_type',
         'attention_sink_size',
-        'hqq_backend',
+        'num_experts_per_token',
+        'tensorcores',
+        'load_in_8bit',
+        'load_in_4bit',
+        'torch_compile',
+        'flash_attn',
+        'use_flash_attention_2',
+        'streaming_llm',
+        'auto_devices',
+        'cpu',
+        'disk',
+        'row_split',
+        'no_offload_kqv',
+        'no_mul_mat_q',
+        'no_mmap',
+        'mlock',
+        'numa',
+        'use_double_quant',
+        'use_eager_attention',
+        'bf16',
+        'autosplit',
+        'enable_tp',
+        'no_flash_attn',
+        'no_xformers',
+        'no_sdpa',
+        'cfg_cache',
         'cpp_runner',
+        'logits_all',
+        'trust_remote_code',
+        'no_use_fast',
     ]
 
     if is_torch_xpu_available():
@@ -165,87 +165,87 @@ def list_model_elements():
 
 def list_interface_input_elements():
     elements = [
-        'max_new_tokens',
-        'auto_max_new_tokens',
-        'max_tokens_second',
-        'max_updates_second',
-        'prompt_lookup_num_tokens',
-        'seed',
         'temperature',
-        'temperature_last',
-        'dynamic_temperature',
         'dynatemp_low',
         'dynatemp_high',
         'dynatemp_exponent',
         'smoothing_factor',
         'smoothing_curve',
-        'top_p',
         'min_p',
+        'top_p',
         'top_k',
         'typical_p',
-        'epsilon_cutoff',
-        'eta_cutoff',
-        'repetition_penalty',
-        'presence_penalty',
-        'frequency_penalty',
-        'repetition_penalty_range',
-        'encoder_repetition_penalty',
-        'no_repeat_ngram_size',
-        'dry_multiplier',
-        'dry_base',
-        'dry_allowed_length',
-        'dry_sequence_breakers',
         'xtc_threshold',
         'xtc_probability',
-        'do_sample',
+        'epsilon_cutoff',
+        'eta_cutoff',
+        'tfs',
+        'top_a',
+        'dry_multiplier',
+        'dry_allowed_length',
+        'dry_base',
+        'repetition_penalty',
+        'frequency_penalty',
+        'presence_penalty',
+        'encoder_repetition_penalty',
+        'no_repeat_ngram_size',
+        'repetition_penalty_range',
         'penalty_alpha',
+        'guidance_scale',
         'mirostat_mode',
         'mirostat_tau',
         'mirostat_eta',
-        'grammar_string',
-        'negative_prompt',
-        'guidance_scale',
-        'add_bos_token',
+        'max_new_tokens',
+        'prompt_lookup_num_tokens',
+        'max_tokens_second',
+        'max_updates_second',
+        'do_sample',
+        'dynamic_temperature',
+        'temperature_last',
+        'auto_max_new_tokens',
         'ban_eos_token',
-        'custom_token_bans',
-        'sampler_priority',
-        'truncation_length',
-        'custom_stopping_strings',
+        'add_bos_token',
         'skip_special_tokens',
         'stream',
         'static_cache',
-        'tfs',
-        'top_a',
+        'truncation_length',
+        'seed',
+        'sampler_priority',
+        'custom_stopping_strings',
+        'custom_token_bans',
+        'negative_prompt',
+        'dry_sequence_breakers',
+        'grammar_string',
     ]
 
     # Chat elements
     elements += [
-        'textbox',
-        'start_with',
-        'character_menu',
         'history',
         'search_chat',
         'unique_id',
+        'textbox',
+        'start_with',
+        'mode',
+        'chat_style',
+        'chat-instruct_command',
+        'character_menu',
+        'name2',
+        'context',
+        'greeting',
         'name1',
         'user_bio',
-        'name2',
-        'greeting',
-        'context',
-        'mode',
         'custom_system_message',
         'instruction_template_str',
         'chat_template_str',
-        'chat_style',
-        'chat-instruct_command',
     ]
 
     # Notebook/default elements
     elements += [
-        'textbox-notebook',
         'textbox-default',
-        'output_textbox',
+        'textbox-notebook',
         'prompt_menu-default',
         'prompt_menu-notebook',
+        'output_textbox',
     ]
 
     # Model elements