Delta-Vector/Rei-12B-V3-Base

Rei-12B

Another prototype Magnum... (This time with Weird loss function(that ruins VRAM usage!!!)!)

✨ Overview

A Model meant to replicate the style of Claude models Opus and Sonnet, Taking the previous Rei-12B and training it with a Custom Subseqence Loss function.

Fine-tuned on top of Mistral-Nemo-Instruct (ChatML'ified)

📥 Quantized Models

GGUF Quant(Coming soon!)

💬 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

• normal training cares about reducing overall error for the full context, but late context is easier to reduce and most tokens are not early tokensm, A mod to the loss function cares about reducing error for all context lengths, which leads to more emphasis on improving early context performance
• You can find the modeling mod here: https://huggingface.co/datasets/Delta-Vector/Configs/blob/main/modeling_mistral.py

Configuration

View Axolotl Config(Same config as the Previous Rei)

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

The model was trained for 1 epochs on 8x NVIDIA H100s GPUs generously provided by @Kalomaze

⚠️ Credits

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

Rei-12B | V3