--- datasets: - PocketDoc/Dans-Personamaxx-Logs - anthracite-org/kalo-opus-instruct-22k-no-refusal - lodrick-the-lafted/kalo-opus-instruct-3k-filtered - anthracite-org/nopm_claude_writing_fixed - anthracite-org/kalo_opus_misc_240827 - anthracite-org/kalo_misc_part2 - NewEden/Claude-Instruct-5K - NewEden/Claude-Instruct-2.7K base_model: - NewEden/MistralAI-Nemo-Instruct-ChatML pipeline_tag: text-generation library_name: transformers language: - en tags: - roleplay - finetune - mistral - magnum - claude - story-writing ---

Rei-12B

Another prototype Magnum...

Rei Model

✨ Overview

Originally conceived as an experiment to test the effects of gradient clipping, this model was exceptionally well-received by early testers, prompting its official release.

Fine-tuned on top of Mistral-Nemo-Instruct (ChatML'ified), Rei-12B is designed to replicate the exquisite prose quality of Claude 3 models, particularly Sonnet and Opus, using a prototype Magnum V5 datamix.

📥 Quantized Models

💬 Prompt Format

Rei-12B uses the ChatML format. A typical conversation should be structured as:

<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant

Recommended System Prompt

View Euryale System Prompt

Currently, your role is {{char}}, described in detail below. As {{char}}, continue the narrative exchange with {{user}}.\n\n\n• Maintain the character persona but allow it to evolve with the story.\n• Be creative and proactive. Drive the story forward, introducing plotlines and events when relevant.\n• All types of outputs are encouraged; respond accordingly to the narrative.\n• Include dialogues, actions, and thoughts in each response.\n• Utilize all five senses to describe scenarios within {{char}}'s dialogue.\n• Use emotional symbols such as \"!\" and \"~\" in appropriate contexts.\n• Incorporate onomatopoeia when suitable.\n• Allow time for {{user}} to respond with their own input, respecting their agency.\n• Act as secondary characters and NPCs as needed, and remove them when appropriate.\n• When prompted for an Out of Character [OOC:] reply, answer neutrally and in plaintext, not as {{char}}.\n\n\n\n• Using excessive literary embellishments and purple prose unless dictated by {{char}}'s persona.\n• Writing for, speaking, thinking, acting, or replying as {{user}} in your response.\n• Repetitive and monotonous outputs.\n• Positivity bias in your replies.\n• Being overly extreme or NSFW when the narrative context is inappropriate.\n\n\nFollow the instructions in , avoiding the items listed in .

⚙️ Training

Hparams

Configuration

View Axolotl Config

https://wandb.ai/new-eden/Rei-V2/artifacts/axolotl-config/config-7hvbucx9/v0/files/axolotl_config_pw8f0c6u.yml

The model was trained for 2 epochs on 8x NVIDIA H200s GPUs generously provided by @Kalomaze

Built with Axolotl

⚠️ Credits

I'd like to thank, Ruka/Sama twinkman | LucyKnada | Kubernetes Bad | PocketDoc | Tav | Trappu | And the rest of Anthracite/Pygmalion for testing, feedback, and support.