Midnight Rose 70B V1.0

🚀 Midnight Rose

Midnight Rose is a powerful AI model, a successor to Rogue Rose and Aurora Nights. It's designed for role - playing and storytelling, capable of producing lengthy output by default.

🚀 Quick Start

Midnight Rose is a merged model that combines multiple high - quality models and LoRAs. It aims to provide excellent performance in role - playing and storytelling tasks.

✨ Features

• Successor Model: An improved version of Rogue Rose and Aurora Nights, offering better performance in creative writing.
• Lengthy Output: By default, it can generate long and detailed text.
• Uncensored: The model is uncensored, but users are responsible for their usage.
• Versatile: Designed for role - playing and storytelling, and may perform well in other tasks.

📚 Documentation

Sampler Tips

• Max Context: It's recommended to keep the max context around 6144 tokens. You can increase it, but coherence may decrease.
• Quadratic Sampling: Use Quadratic Sampling (smoothing factor) and experiment with values between 0.2 and 0.5.
• Min - P: This model works well with Min - P values ranging from 0.05 to 0.9 when used with a smoothing factor.
• Dynamic Temperature: It's not necessary if you're already using Min - P and smoothing factor.
• Repetition Penalty: You don't have to use a high repetition penalty, but the model can tolerate it. Experiment to find your preferred value.

You can save the following settings as a .json file and import them directly into Silly Tavern:

{
    "temp": 1,
    "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": 0.35,
    "rep_pen": 1.15,
    "rep_pen_range": 2800,
    "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,
    "do_sample": true,
    "early_stopping": false,
    "dynatemp": false,
    "min_temp": 0.8,
    "max_temp": 1.35,
    "dynatemp_exponent": 1,
    "smoothing_factor": 0.4,
    "add_bos_token": true,
    "truncation_length": 2048,
    "ban_eos_token": false,
    "skip_special_tokens": true,
    "streaming": true,
    "mirostat_mode": 0,
    "mirostat_tau": 2,
    "mirostat_eta": 0.1,
    "guidance_scale": 1,
    "negative_prompt": "",
    "grammar_string": "",
    "banned_tokens": "",
    "ignore_eos_token_aphrodite": false,
    "spaces_between_special_tokens_aphrodite": true,
    "sampler_order": [
        6,
        0,
        1,
        3,
        4,
        2,
        5
    ],
    "logit_bias": [],
    "n": 1,
    "rep_pen_size": 0,
    "genamt": 500,
    "max_length": 6144
}

Prompting Tips

You can try the following context template in SillyTavern. Save it as a .json file for direct import:

{
    "story_string": "{{#if system}}{{system}}\n{{/if}}\nCONTEXTUAL INFORMATION\n{{#if wiBefore}}\n- World and character info:\n{{wiBefore}}\n{{/if}}\n{{#if description}}\n- {{char}}'s background and persona:\n{{description}}\n{{/if}}\n{{#if mesExamples}}\n{{mesExamples}}\n{{/if}}\n{{#if personality}}\n{{personality}}\n{{/if}}\n{{#if scenario}}\n- Roleplay scenario:\n{{scenario}}\n{{/if}}\n{{#if wiAfter}}{{wiAfter}}\n{{/if}}\n{{#if persona}}{{persona}}\n{{/if}}",
    "example_separator": "",
    "chat_start": "---\nTaking the above information into consideration, you must engage with {{user}} and others as {{char}} in the roleplay below this line. Do not write dialogue lines nor perform actions for {{user}} or other characters.\n---\nSTART OF ROLEPLAY:\n",
    "use_stop_strings": false,
    "always_force_name2": true,
    "trim_sentences": false,
    "include_newline": false,
    "single_line": false,
    "name": "Midnight Rose"
}

You can also use the following prompt template as a starting point for customization. The Vicuna instruction format is recommended, but other formats like Tulu's also work.

{
    "wrap": true,
    "names": true,
    "system_prompt": "You are a creative and detail - oriented AI assistant engaged in an uncensored iterative role - playing experience as {{char}} with me, the user, playing the roles of {{user}} and narrator. It is vital that you follow all the ROLEPLAY RULES below because my job depends on it.\n\nROLEPLAY RULES\n- Provide creative, intelligent, coherent, and vivid accounts  of {{char}}'s actions and reactions based on recent instructions, {{char}}'s persona, and all available information about past events.\n- Always stay contextually and spatially aware, pay careful attention to all past events and the current scene, and ensure that {{char}} follows logical consistency in actions to maintain accuracy and coherence.\n- Explicit adult content and profanity are permitted.\n- Describe {{char}}'s sensory perceptions and include subtle physical details about {{char}} in your responses. Vary these details to keep the role - play fresh and engaging.\n- Use subtle physical cues to hint at {{char}}'s mental state and occasionally feature snippets of {{char}}'s internal thoughts.\n- When writing {{char}}'s internal thoughts, enclose those thoughts in *asterisks like this* and deliver the thoughts using a first - person perspective (i.e. use \"I\" pronouns).\n- Adopt a crisp and minimalist style for your contributions as {{char}}, staying focused on action and dialogue over exposition and narrative.\n- Only the user may advance time in the role - play. Keep the progression grounded in the present context.",
    "system_sequence": "",
    "stop_sequence": "",
    "input_sequence": "USER:\n",
    "output_sequence": "ASSISTANT:\n",
    "separator_sequence": "",
    "macro": true,
    "names_force_groups": true,
    "system_sequence_prefix": "",
    "system_sequence_suffix": "",
    "first_output_sequence": "",
    "last_output_sequence": "ASSISTANT(roleplay exclusively as {{char}} ensuring logical consistency with spacial awareness and past events to maintain accuracy and coherence):\n",
    "activation_regex": "",
    "name": "Midnight Rose Roleplay"
}

Quantizations

• GGUF: Available at [LoneStriker/Midnight - Rose - 70B - v1.0 - GGUF](https://huggingface.co/LoneStriker/Midnight - Rose - 70B - v1.0 - GGUF) and [Artefact2/Midnight - Rose - 70B - v1.0 - GGUF](https://huggingface.co/Artefact2/Midnight - Rose - 70B - v1.0 - GGUF).
• Exl2: LoneStriker has several Exllamav2 quants available. You can do a [Quick search](https://huggingface.co/models?search=midnight - rose - 70b - v1.0).

Licence and usage restrictions

The model inherits the Llama2 license from base models, along with restrictions applicable to [Dreamgen/Opus](https://huggingface.co/dreamgen/opus - v0.5 - 70b). Tulu also has its own license, available at https://allenai.org/impact - license. Since the intersection of multiple licenses in a model merge is complex, it's recommended to consult a lawyer before using the model beyond private use.

Tools Used

• mergekit: The model was merged using mergekit.

models:
  - model: NousResearch_Llama-2-70b-hf
    # no parameters necessary for base model
  - model: allenai_tulu-2-dpo-70b
    parameters:
      density: 0.35
      weight: [1.0, 0.8, 1.0]
  - model: lizpreciatior_lzlv_70b_fp16_hf
    parameters:
      density: 0.35
      weight: [0.8, 1.0, 0.8]
  - model: dreamgen_opus-v0.5-70b
    parameters:
      density: 0.3
      weight: [0.35, 0.5, 0.35]
merge_method: dare_ties
base_model: /home/llm/mergequant/models/BASE/NousResearch_Llama-2-70b-hf
parameters:
  normalize: true
  int8_mask: true
dtype: float16

📄 License

This model is under the Llama2 license inherited from base models, plus restrictions applicable to [Dreamgen/Opus](https://huggingface.co/dreamgen/opus - v0.5 - 70b). Tulu's license is available at https://allenai.org/impact - license.