Are you ready to embark on an adventure of storytelling and roleplay using the powerful New Dawn Llama 3.1 model? This guide will walk you through its features, settings, and usage, making it user-friendly to jump into your creative projects with ease.

Overview of the Model

The New Dawn Llama 3.1 model is an experimental merge of sophosympatheiaNew-Dawn-Llama-3-70B-32K-v1.0 and meta-llamaMeta-Llama-3.1-70B-Instruct. It’s designed specifically for roleplay and storytelling, leveraging advanced techniques to keep the context intact while providing unique outputs. Remember, this model is uncensored, so your creativity knows no bounds!

Getting Started with Settings

When using the New Dawn Llama 3.1 model for creative tasks, particular sampler settings can enhance your experience. Think of these settings as a chef’s secret ingredients to ensure your storytelling dish tastes exceptional!

Sampler Tips

• **Quadratic Sampling**: Use a smoothing factor around 0.2 for the best outputs.
• **Min-P Setting**: Experiment using values between 0 and 0.1.
• **DRY Repetition Penalty**: This helps in avoiding redundancy in responses.
• **Textgen WebUI**: If using this as a backend, enabling DRY sampler settings further reduces repetition.

Configuration Settings

You can save the following settings as a .json file and import them 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": 0.03,
  "rep_pen": 1,
  "rep_pen_range": 2048,
  "rep_pen_decay": 0,
  "rep_pen_slope": 1,
  "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": 0.8,
  "max_temp": 1.5,
  "dynatemp_exponent": 1,
  "smoothing_factor": 0.23,
  "smoothing_curve": 1,
  "dry_allowed_length": 2,
  "dry_multiplier": 0.8,
  "dry_base": 2,
  "dry_sequence_breakers": ["n", ":", "", "*"],
  "dry_penalty_last_n": 0,
  "add_bos_token": true,
  "ban_eos_token": false,
  "skip_special_tokens": false,
  "mirostat_mode": 0,
  "mirostat_tau": 2,
  "mirostat_eta": 0.1,
  "guidance_scale": 1,
  "negative_prompt": "",
  "grammar_string": "",
  "json_schema": "",
  "banned_tokens": "",
  "sampler_priority": ["top_k", "top_p", "typical_p", "epsilon_cutoff", "eta_cutoff", "tfs", "top_a", "min_p", "mirostat", "quadratic_sampling", "dynamic_temperature", "temperature"],
  "samplers": ["top_k", "tfs_z", "typical_p", "top_p", "min_p", "temperature"],
  "ignore_eos_token": false,
  "spaces_between_special_tokens": true,
  "speculative_ngram": false,
  "sampler_order": [6, 0, 1, 3, 4, 2, 5],
  "logit_bias": [],
  "ignore_eos_token_aphrodite": false,
  "spaces_between_special_tokens_aphrodite": true,
  "rep_pen_size": 0,
  "genamt": 800,
  "max_length": 20480
}

Prompting Templates

Use this prompt template to kickstart your story creation. Keep in mind that it contains adult content instructions—you can modify it as needed:

{
  "wrap": false,
  "names": true,
  "system_prompt": "The following is a roleplaying chat log involving a user and an AI assistant. They take turns, focusing on their respective character traits and narrative immersion.",
  "writing_rules": {
    "immersive_descriptions": true,
    "simple_language": true,
    "perplexity": true,
    "dialogue_formatting": true,
    "internal_thoughts": true,
    "internal_thoughts_formatting": "italics",
    "content_rules": {
      "accurate_details": true,
      "mature_content": true,
      "mature_themes": true,
      "narrative_instructions": true
    }
  },
  "system_sequence": {
    "start": "system",
    "end": "system"
  },
  ...
}

Troubleshooting Tips

Facing issues while using this model? Here are some troubleshooting ideas to get you back on track:

• **Repeating Responses**: Adjust the DRY repetition penalty settings or experiment with the smoothing factor to minimize repeat outputs.
• **Unexpected Outputs**: Review your prompt and ensure it aligns with the goals you set. Complex prompts might require simplification.
• **Performance Issues**: Ensure you are using appropriate settings for your specific task, as this model excels with certain configurations.

For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.

Conclusion

With the right settings and templates in hand, the New Dawn Llama 3.1 model can bring your storytelling or role-playing concepts to life. Dive into the creative possibilities, and remember that the more you experiment, the better your results will be!

At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.