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

huggingface.co
Total runs: 38
24-hour runs: 3
7-day runs: 10
30-day runs: 23
Model's Last Updated: May 05 2025

Introduction of Rei-V3-KTO-12B

Model Details of Rei-V3-KTO-12B

Rei-12B

Another prototype Magnum... (This time with RL!)

Rei Model
✨ Overview

Taking the previous 12B trained with Subseqence Loss - This model is meant to refine the base's sharp edges and increase coherency, intelligence and prose while replicating the prose of the Claude models Opus and Sonnet

Fine-tuned on top of Rei-V3-12B-Base , Rei-12B is designed to replicate the 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
  • For Hparams for this model we used a grad clip of 1e-4 as it was proven to the best value for Mistral-12B based models, and also to prevent Rewards/Chosen from flat-lining as Hermes-genned data is... The biggest piece of dogshit.
Configuration
View Axolotl Config

https://wandb.ai/new-eden/KTO/artifacts/axolotl-config/config-eyt7d5i9/v0/files/axolotl_config_jvjuci1x.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 | KTO

Runs of Delta-Vector Rei-V3-KTO-12B on huggingface.co

38
Total runs
3
24-hour runs
5
3-day runs
10
7-day runs
23
30-day runs

More Information About Rei-V3-KTO-12B huggingface.co Model

Rei-V3-KTO-12B huggingface.co

Rei-V3-KTO-12B huggingface.co is an AI model on huggingface.co that provides Rei-V3-KTO-12B's model effect (), which can be used instantly with this Delta-Vector Rei-V3-KTO-12B model. huggingface.co supports a free trial of the Rei-V3-KTO-12B model, and also provides paid use of the Rei-V3-KTO-12B. Support call Rei-V3-KTO-12B model through api, including Node.js, Python, http.

Delta-Vector Rei-V3-KTO-12B online free

Rei-V3-KTO-12B huggingface.co is an online trial and call api platform, which integrates Rei-V3-KTO-12B's modeling effects, including api services, and provides a free online trial of Rei-V3-KTO-12B, you can try Rei-V3-KTO-12B online for free by clicking the link below.

Delta-Vector Rei-V3-KTO-12B online free url in huggingface.co:

https://huggingface.co/Delta-Vector/Rei-V3-KTO-12B

Rei-V3-KTO-12B install

Rei-V3-KTO-12B is an open source model from GitHub that offers a free installation service, and any user can find Rei-V3-KTO-12B on GitHub to install. At the same time, huggingface.co provides the effect of Rei-V3-KTO-12B install, users can directly use Rei-V3-KTO-12B installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Rei-V3-KTO-12B install url in huggingface.co:

https://huggingface.co/Delta-Vector/Rei-V3-KTO-12B

Url of Rei-V3-KTO-12B

Provider of Rei-V3-KTO-12B huggingface.co

Delta-Vector
ORGANIZATIONS

Other API from Delta-Vector

huggingface.co

Total runs: 32
Run Growth: 8
Growth Rate: 25.00%
Updated:December 31 2024
huggingface.co

Total runs: 32
Run Growth: 9
Growth Rate: 28.13%
Updated:December 31 2024