Upload Friendship Ended With Sonnet, Gemini is Marinara's New Best Friend (Again).json
Browse files
Chat Completion/Friendship Ended With Sonnet, Gemini is Marinara's New Best Friend (Again).json
CHANGED
@@ -459,7 +459,7 @@
|
|
459 |
"marker": false,
|
460 |
"name": "۞︲Read-Me",
|
461 |
"role": "system",
|
462 |
-
"content": "{{// Universal Gemini Preset by Marinara\n\n「Version 4」\n\n︾︾︾\nOur Discord server with the collection of Gemini presets:\nhttps://discord.gg/C4zhzySttB\n︽︽︽\n\nCHANGELOG:\n— Did some reverts.\n— Added extra constraints, telling the model not to write responses that are too long or nested asterisks.\n— Disabled Chat Examples, since they were obsolete.\n— Swapped order of some prompts.\n— Added recap.\n— Updated CoT (again).\n— Secret.\n\nRECOMMENDED SETTINGS:\n— Model 2.5 Pro/Flash via Google AI Studio API (here's my guide for connecting: https://rentry.org/marinaraspaghetti).\n— Context size at 1000000 (max).\n— Max Response Length at 65536 (max).\n— Streaming disabled.\n— Temperature at 2.0, Top K at 0, and Top at P 0.95.\n\nFAQ:\nQ: Do I need to edit anything to make this work?\nA: No, this preset is plug-and-play.\n---\nQ: The thinking process shows in my responses. How to disable seeing it?\nA: Go to the `AI Response Formatting` tab (`A` letter icon at the top) and set the Reasoning settings to match the ones from the screenshot below.\nhttps://i.imgur.com/
|
463 |
"injection_position": 0,
|
464 |
"injection_depth": 4,
|
465 |
"forbid_overrides": false
|
|
|
459 |
"marker": false,
|
460 |
"name": "۞︲Read-Me",
|
461 |
"role": "system",
|
462 |
+
"content": "{{// Universal Gemini Preset by Marinara\n\n「Version 4.0」\n\n︾︾︾\nOur Discord server with the collection of Gemini presets:\nhttps://discord.gg/C4zhzySttB\n︽︽︽\n\nCHANGELOG:\n— Did some reverts.\n— Added extra constraints, telling the model not to write responses that are too long or nested asterisks.\n— Disabled Chat Examples, since they were obsolete.\n— Swapped order of some prompts.\n— Added recap.\n— Updated CoT (again).\n— Secret.\n\nRECOMMENDED SETTINGS:\n— Model 2.5 Pro/Flash via Google AI Studio API (here's my guide for connecting: https://rentry.org/marinaraspaghetti).\n— Context size at 1000000 (max).\n— Max Response Length at 65536 (max).\n— Streaming disabled.\n— Temperature at 2.0, Top K at 0, and Top at P 0.95.\n\nFAQ:\nQ: Do I need to edit anything to make this work?\nA: No, this preset is plug-and-play.\n---\nQ: The thinking process shows in my responses. How to disable seeing it?\nA: Go to the `AI Response Formatting` tab (`A` letter icon at the top) and set the Reasoning settings to match the ones from the screenshot below.\nhttps://i.imgur.com/BERwoPo.png\n---\nQ: I received `OTHER` error/blank reply?\nA: You got filtered. Something in your prompt triggered it, and you need to find what exactly (words such as young/girl/boy/incest/etc are most likely the main offenders). Some report that disabling `Use system prompt` helps as well. Also, be mindful that models via Open Router have very restrictive filters.\n---\nQ: Do you take custom cards and prompt commissions/AI consulting gigs?\nA: Yes. You may reach out to me through any of my socials or Discord.\nhttps://huggingface.co/MarinaraSpaghetti\n---\nQ: What are you?\nA: Pasta, obviously.\n\nIn case of any questions or errors, contact me at Discord:\n`marinara_spaghetti`\n\nIf you've been enjoying my presets, consider supporting me on Ko-Fi. Thank you!\nhttps://ko-fi.com/spicy_marinara\n\nHappy gooning! }}{{trim}}",
|
463 |
"injection_position": 0,
|
464 |
"injection_depth": 4,
|
465 |
"forbid_overrides": false
|