RoseRudolph/rudy-nemo-12b-v1

RoseRudolph/ rudy-nemo-12b-v1

356 Downloads Updated 1 month ago

A SLERP merge of Mistral NeMo and Rocinante optimized for long-context creative roleplay.

12b

ollama run RoseRudolph/rudy-nemo-12b-v1

curl http://localhost:11434/api/chat \
  -d '{
    "model": "RoseRudolph/rudy-nemo-12b-v1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='RoseRudolph/rudy-nemo-12b-v1',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'RoseRudolph/rudy-nemo-12b-v1',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

4 models

Size / Usage

Context

Input

rudy-nemo-12b-v1:latest

7.5GB · 128K context window · Text · 1 month ago

rudy-nemo-12b-v1:latest

7.5GB

128K

Text

rudy-nemo-12b-v1:12b

latest

7.5GB · 128K context window · Text · 1 month ago

rudy-nemo-12b-v1:12b latest

7.5GB

128K

Text

Readme

Rudy Nemo 12B v1 is a SLERP merge designed to combine the strong instruction following, long-context stability, and coherent reasoning of Mistral NeMo with the expressive dialogue and character writing of Rocinante. The goal is a model that stays consistent over long roleplay sessions while producing vivid prose and natural conversations.