Delta-Vector / Rei-V2-12B

huggingface.co
Total runs: 32
24-hour runs: 0
7-day runs: 7
30-day runs: 19
Model's Last Updated: March 31 2025
text-generation

Introduction of Rei-V2-12B

Model Details of Rei-V2-12B

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
  • For Hparams for this model we experimented with Grad clipping otherwise known as max_grad_norm
  • Calculated via checking the model arch distribution's we divised 3 different values, knowing the weight distribution for Mistral is 0.1.
  • If you would consult the graph, you'd notice a few things, First and foremost is that setting gradient-clip too high can be deterimental to the model as the logs and testing show that the model was overfit, Meanwhile setting it too low can also cause problems as the 1e-4 run appears to be underfit, The best one was by far the 0.001 clip which resulted in non-overfit, non-underfit model.
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

⚠️ 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.

Rei-12B | V2

Runs of Delta-Vector Rei-V2-12B on huggingface.co

32
Total runs
0
24-hour runs
2
3-day runs
7
7-day runs
19
30-day runs

More Information About Rei-V2-12B huggingface.co Model

Rei-V2-12B huggingface.co

Rei-V2-12B huggingface.co is an AI model on huggingface.co that provides Rei-V2-12B's model effect (), which can be used instantly with this Delta-Vector Rei-V2-12B model. huggingface.co supports a free trial of the Rei-V2-12B model, and also provides paid use of the Rei-V2-12B. Support call Rei-V2-12B model through api, including Node.js, Python, http.

Delta-Vector Rei-V2-12B online free

Rei-V2-12B huggingface.co is an online trial and call api platform, which integrates Rei-V2-12B's modeling effects, including api services, and provides a free online trial of Rei-V2-12B, you can try Rei-V2-12B online for free by clicking the link below.

Delta-Vector Rei-V2-12B online free url in huggingface.co:

https://huggingface.co/Delta-Vector/Rei-V2-12B

Rei-V2-12B install

Rei-V2-12B is an open source model from GitHub that offers a free installation service, and any user can find Rei-V2-12B on GitHub to install. At the same time, huggingface.co provides the effect of Rei-V2-12B install, users can directly use Rei-V2-12B installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Rei-V2-12B install url in huggingface.co:

https://huggingface.co/Delta-Vector/Rei-V2-12B

Url of Rei-V2-12B

Provider of Rei-V2-12B huggingface.co

Delta-Vector
ORGANIZATIONS

Other API from Delta-Vector

huggingface.co

Total runs: 41
Run Growth: 15
Growth Rate: 36.59%
Updated:December 31 2024
huggingface.co

Total runs: 36
Run Growth: 11
Growth Rate: 30.56%
Updated:December 31 2024