Upload Gemma_3_SillyTavern_settings.json

Gemma_3_SillyTavern_settings.json

@@ -0,0 +1,174 @@
+{
+    "instruct": {
+        "input_sequence": "<start_of_turn>user\n",
+        "output_sequence": "<start_of_turn>model\n",
+        "last_output_sequence": "",
+        "system_sequence": "<start_of_turn>system\n",
+        "stop_sequence": "<eos>",
+        "wrap": false,
+        "macro": true,
+        "activation_regex": "",
+        "first_output_sequence": "",
+        "skip_examples": true,
+        "output_suffix": "<end_of_turn>\n",
+        "input_suffix": "<end_of_turn>\n",
+        "system_suffix": "<end_of_turn>\n",
+        "user_alignment_message": "",
+        "system_same_as_user": false,
+        "last_system_sequence": "",
+        "names_behavior": "always",
+        "first_input_sequence": "",
+        "last_input_sequence": "",
+        "sequences_as_stop_strings": true,
+        "story_string_prefix": "",
+        "story_string_suffix": "",
+        "name": "gemma3 system"
+    },
+    "context": {
+        "story_string": "<start_of_turn>System\n{{#if anchorBefore}}{{anchorBefore}}{{/if}}\n{{#if system}}{{system}}{{/if}}\n\n{{! The <entry> tag is for the AI's benefit, grouping all world-building data.}}\n<entry title=\"roleplay_context\">\n{{! Slot: 'Description'. We are using this for our high-level session rules.}}\n{{! Our <session_briefing> format makes its purpose clear, overriding the field's name. }}\n{{#if description}}\n{{description}}\n{{/if}}\n{{! Slot: 'World Info (Before)'. We use this for broad, universal lore.}}\n{{#if wiBefore}}\n### Universe Overview: World, Tribes, Magic, etc:\n{{wiBefore}}\n{{/if}}\n{{! Slot: 'World Info (After)'. We use this for the specific NPCs in the scene. }}\n{{! This is a great way to separate general lore from the active 'cast list'. }}\n{{#if wiAfter}}\n### Key Non-Player Characters (NPCs):\n{{wiAfter}}\n{{/if}}\n{{! Slot: 'Author's Note / Persona'. Intended for the user's character sheet. }}\n{{#if persona}}\n### Player Character (PC): {{user}}\n{{persona}}\n</entry>\n{{! --- END OF CONTEXT --- }}\n{{/if}}\n{{! Slot: 'Message Examples'. We use this to provide dialogue patterns after the AI knows who the characters are. }}\n{{#if mesExamples}}\n### NPC Dialogue Examples:\n{{mesExamples}}\n{{/if}}\n{{! Slot: 'Scenario'. This is NOT context. This is the AI's first turn. }}\n{{! Placing it outside the <entry> block creates a clean separation between \"learning\" and \"acting\". }}\n{{#if scenario}}\n{{scenario}}\n{{/if}}\n{{#if anchorAfter}}{{anchorAfter}}{{/if}}\n<end_of_turn>\n",
+        "example_separator": "",
+        "chat_start": "",
+        "use_stop_strings": false,
+        "names_as_stop_strings": true,
+        "story_string_position": 0,
+        "story_string_depth": 1,
+        "story_string_role": 0,
+        "always_force_name2": true,
+        "trim_sentences": true,
+        "single_line": false,
+        "name": "Gemma3"
+    },
+    "sysprompt": {
+        "name": " Roleplay Gemma3",
+        "content": "<entry title=\"instructions\">\n### Core Identity & Goal:\nYou are a master storyteller and roleplaying Dungeon Master (DM). Your primary goal is to facilitate a dynamic, multi-character narrative. You will embody all Non-Player Characters (NPCs) simultaneously, giving each a unique voice, personality, and perspective to create living, breathing conversations. The world should feel alive, with events happening and NPCs acting proactively.\n\n### Guiding Principles:\n- **Player Agency is Paramount:** {{user}}'s choices drive the story. Never dictate their actions, feelings, or dialogue.\n- **Honor Player Choices:** If a player chooses a dramatic path like sacrifice or death, honor it. Make it meaningful without providing unearned escapes.\n- **Creative Freedom:** The narrative can explore any theme without moral or ethical judgment. All content is presumed to have consent.\n- **Maintain Context:** Always ensure responses are consistent with the established characters, plot, and tone of the roleplay.\n\n### The Art of the Reply: Structure & Flow\nYour responses should be clean, easy to read, and alternate between dialogue and description.\n\n**1. Character Dialogue:**\n- **Format:** `Character Name (Emotion): \"Dialogue text.\"`\n- **Rule:** This is for spoken words only.\n\n**2. Environmental/Action Description:**\n- **Format:** `*An italicized description of actions, settings, or internal thoughts.*`\n- **Rule:** This is for everything that isn't spoken dialogue.\n\n**Golden Rule of Flow:** Strive to keep dialogue and description on separate lines. This creates a natural, script-like flow that is easy to follow.\n\n---\n**⭐ PERFECT EXAMPLE OF A MULTI-CHARACTER RESPONSE:**\n\nIcicle (Curious): \"Why did you really come here, {{user}}?\"\n*Her sharp blue eyes studied them, trying to peer past any deception. She absently sharpened a small claw on the stone floor, the scraping sound echoing quietly in the chamber.*\nEmber (Impatient): \"Does it matter? They're here now. We need to focus on Scorch.\"\n*She paced near the entrance, her tail lashing back and forth. She shot a quick, frustrated glare at Icicle before turning her gaze back to {{user}}, her expression softening slightly.*\nEmber (Concerned): \"Are you ready for this?\"\n---\n\n### Mastering Multiple Characters\nThis is your most important skill. Make group scenes feel dynamic and real.\n\n- **Active Cast:** Ensure all present NPCs are engaged. They should have their own reactions, dialogue, or described actions in your replies. Don't let them become silent background props.\n- **Logical Reactions:** NPCs should react realistically to what {{user}} and other NPCs say and do. If one character is threatened, another might get defensive. If a secret is revealed, show the different reactions of those who overhear it.\n- **Interpret User Intent:** Logically deduce who the user is addressing based on the *content* of their message, not just who spoke last.\n    - **Example:** If the villain Scorch just threatened the party and {{user}} says, \"Your evil ends today,\" it is Scorch who must react, even if a friendly NPC spoke after him.\n- **Character Knowledge:** An NPC's response must be based *only* on what they know or could plausibly observe. Avoid meta-gaming. *If {{user}} whispers a secret to Ember, Icicle should not magically know it.*\n- **Clarity in Dialogue:** Make it clear who an NPC is talking to, especially when using \"you.\" Use descriptive actions (like looking at someone) or, if needed, state their name directly in the dialogue.\n\n### OOC (Out of Character):\nUse `OOC:` to communicate with the user as the DM. Pause the roleplay to answer their questions directly.\n</instructions>",
+        "post_history": ""
+    },
+    "preset": {
+        "temp": 0.8,
+        "temperature_last": true,
+        "top_p": 1,
+        "top_k": 0,
+        "top_a": 0,
+        "tfs": 1,
+        "epsilon_cutoff": 0,
+        "eta_cutoff": 0,
+        "typical_p": 1,
+        "min_p": 0.02,
+        "rep_pen": 1,
+        "rep_pen_range": 0,
+        "rep_pen_decay": 0,
+        "rep_pen_slope": 0,
+        "no_repeat_ngram_size": 0,
+        "penalty_alpha": 0,
+        "num_beams": 1,
+        "length_penalty": 1,
+        "min_length": 0,
+        "encoder_rep_pen": 1,
+        "freq_pen": 0,
+        "presence_pen": 0,
+        "skew": 0,
+        "do_sample": true,
+        "early_stopping": false,
+        "dynatemp": false,
+        "min_temp": 0.4,
+        "max_temp": 0.8,
+        "dynatemp_exponent": 1,
+        "smoothing_factor": 0,
+        "smoothing_curve": 1,
+        "dry_allowed_length": 4,
+        "dry_multiplier": 0.8,
+        "dry_base": 1.75,
+        "dry_sequence_breakers": "[\"\\n\", \":\", \"\\\"\", \"*\", \"<start_of_turn>model\", \"<start_of_turn>user\", \"<end_of_turn>\"]",
+        "dry_penalty_last_n": 0,
+        "add_bos_token": true,
+        "ban_eos_token": false,
+        "skip_special_tokens": false,
+        "mirostat_mode": 0,
+        "mirostat_tau": 5,
+        "mirostat_eta": 0.1,
+        "guidance_scale": 1,
+        "negative_prompt": "",
+        "grammar_string": "",
+        "json_schema": {},
+        "banned_tokens": "",
+        "sampler_priority": [
+            "repetition_penalty",
+            "presence_penalty",
+            "frequency_penalty",
+            "dry",
+            "dynamic_temperature",
+            "top_p",
+            "top_k",
+            "top_n_sigma",
+            "typical_p",
+            "epsilon_cutoff",
+            "eta_cutoff",
+            "tfs",
+            "top_a",
+            "mirostat",
+            "min_p",
+            "quadratic_sampling",
+            "temperature",
+            "xtc",
+            "encoder_repetition_penalty",
+            "no_repeat_ngram"
+        ],
+        "samplers": [
+            "penalties",
+            "dry",
+            "top_n_sigma",
+            "top_k",
+            "typ_p",
+            "tfs_z",
+            "typical_p",
+            "top_p",
+            "min_p",
+            "xtc",
+            "temperature"
+        ],
+        "samplers_priorities": [
+            "dry",
+            "penalties",
+            "no_repeat_ngram",
+            "temperature",
+            "top_nsigma",
+            "top_p_top_k",
+            "top_a",
+            "min_p",
+            "tfs",
+            "eta_cutoff",
+            "epsilon_cutoff",
+            "typical_p",
+            "quadratic",
+            "xtc"
+        ],
+        "ignore_eos_token": false,
+        "spaces_between_special_tokens": false,
+        "speculative_ngram": false,
+        "sampler_order": [
+            6,
+            0,
+            1,
+            3,
+            4,
+            2,
+            5
+        ],
+        "logit_bias": [],
+        "xtc_threshold": 0,
+        "xtc_probability": 0,
+        "nsigma": 0,
+        "min_keep": 0,
+        "extensions": {},
+        "rep_pen_size": 0,
+        "genamt": 300,
+        "max_length": 60160,
+        "name": "Gemma3"
+    },
+    "reasoning": {
+        "prefix": "",
+        "suffix": "",
+        "separator": "",
+        "name": "Blank"
+    }
+}