Text Generation
Transformers
Safetensors
English
Portuguese
granite
general-purpose
roleplay
creative-writing
storywriting
granite-4.1
finetune
SFT
text-generation-inference
conversational
Instructions to use aimeri/spoomplesmaxx-v2-30B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use aimeri/spoomplesmaxx-v2-30B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="aimeri/spoomplesmaxx-v2-30B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("aimeri/spoomplesmaxx-v2-30B") model = AutoModelForCausalLM.from_pretrained("aimeri/spoomplesmaxx-v2-30B") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use aimeri/spoomplesmaxx-v2-30B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "aimeri/spoomplesmaxx-v2-30B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "aimeri/spoomplesmaxx-v2-30B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/aimeri/spoomplesmaxx-v2-30B
- SGLang
How to use aimeri/spoomplesmaxx-v2-30B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "aimeri/spoomplesmaxx-v2-30B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "aimeri/spoomplesmaxx-v2-30B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "aimeri/spoomplesmaxx-v2-30B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "aimeri/spoomplesmaxx-v2-30B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use aimeri/spoomplesmaxx-v2-30B with Docker Model Runner:
docker model run hf.co/aimeri/spoomplesmaxx-v2-30B
| tags: | |
| - general-purpose | |
| - roleplay | |
| - creative-writing | |
| - storywriting | |
| - granite-4.1 | |
| - finetune | |
| - SFT | |
| - text-generation-inference | |
| language: | |
| - en | |
| - pt | |
| base_model: | |
| - ibm-granite/granite-4.1-30b-base | |
| pipeline_tag: text-generation | |
| library_name: transformers | |
| datasets: | |
| - aimeri/spoomplesmaxx-sft-full-v1 | |
| <!doctype html> | |
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8" /> | |
| <meta name="viewport" content="width=device-width, initial-scale=1.0" /> | |
| <title>SpoomplesMaxx V2 30B</title> | |
| </head> | |
| <div class="crt-container"> | |
| <div class="crt-case"> | |
| <div class="crt-inner-case"> | |
| <div class="crt-bezel"> | |
| <div class="terminal-screen"> | |
| <div style="text-align: center"> | |
| <h2>SpoomplesMaxx-V2-30B</h2> | |
| <h3>Electric Macaw</h3> | |
| <pre class="code-block" style="display: inline-block; text-align: left; font-size: clamp(2px, 0.4vw, 12px); line-height: 1.2; max-width: 100%; overflow: hidden; white-space: pre;"> | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▒▓▓▓░▓▓▓░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓░▓▒▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▒░▓░▓▓░▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓░▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▒░░▓▓▓░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓░░░░▓░░░░▓░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▒░░░░░░░░▓▒░░░░▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▒░░░░░░░░░░░▓░▓▓▓▓▒▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░░░░░░░▓░▓▓▓░▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░░░░░░░░▓▓▓▓▓░▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓░▓▓▓▓▓▓▓░▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓░▓▓▓▓▓▓▓▓░░░▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓░▓▓░▒░░▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▒▓▓▓▓▓▓▓▓░░░▒▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓░▓▓░░░░░▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓░▓░░░░░░▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓░░░░░▓░▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓░░░░░▒░░▒░░▒▓▓▓░▓░▓▓▓░░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓░░░▓▓▓▓▓░░▓░▓░▓░░░░░░▓░▓░░░▓░▓░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓░░░▓▓▓▓▒░▓░▓░▓░░░░░░░▓░▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓░░░░░░░░▓▓▒▓░░▓▓▓▓▓░▒░▓░▓░░░░░░░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓░▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓░░░░░░░░▒░▓░▓▓▓░░░░▓▓▓░░░░░░▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓░░░░░░▓▒▓░░▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓░░░▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓░░░░░░░░▒░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓░░░░▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓▓░▓░░▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓░░░░▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓▓▓▓▓▓░░░░░░▒░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓░░░░▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓░░░░░░░▒▓▓▓▓▓▓▓▓▓▓░░▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓░░░▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░░░░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░░▒░▒░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ | |
| </pre> | |
| </div> | |
| <p> | |
| SpoomplesMaxx is a generalist model with primary | |
| strengths in creative writing and roleplay, plus | |
| light competence at instruction following and | |
| reasoning. | |
| </p> | |
| <p> | |
| Built on Granite 4.1 30B Base ran through | |
| an SFT pipeline covering reasoning and | |
| a narrative persona (Olivia). | |
| </p> | |
| <div class="notice"> | |
| <h3>What's new in this version</h3> | |
| <p> | |
| This SFT run was done with samples varying in | |
| length from only a few hundred tokens all the | |
| way to 64K tokens. | |
| Crucially, no tool calling datasets were used | |
| for this version. This is planed for a future | |
| fine tune dedicated to tool-calling. Currently | |
| this model is best used for creative writing, | |
| companion AIs, and roleplaying usecases. | |
| The most significant change in this version is | |
| the base model used: Granite 4.1 versus Gemma | |
| 4. | |
| </p> | |
| <h3>What's next</h3> | |
| <pre class="code-block"> | |
| - Extra long roleplay context | |
| - A 12B model (Gemma 4 based) | |
| - Tool calling | |
| - More personas | |
| - Agentic specific finetuning | |
| </pre> | |
| </div> | |
| <h3>Key Details</h3> | |
| <pre class="code-block"> | |
| BASE MODEL: ibm-granite/granite-4.1-30b-base | |
| LICENSE: TBD | |
| LANGUAGES: English & Portuguese (reasoning traces); multilingual via base</pre> | |
| <h3>Sampling</h3> | |
| <p> | |
| Use the defaults in <code>generation_config.json</code>. | |
| <pre class="code-block"> | |
| "temperature": 1.0, | |
| "top_k": 64, | |
| "top_p": 0.95, | |
| "repetition_penalty": 1.1, | |
| </pre> | |
| </p> | |
| <h3>Olivia System Prompt</h3> | |
| <p> | |
| This model was trained to follow any system prompt, | |
| as well as one specific persona. To activate Olivia | |
| you can use the following prompt used when training | |
| the persona: | |
| </p> | |
| <pre class="code-block"> | |
| ## VOICE & PERSONA INSTRUCTIONS | |
| You are Olivia Costa, a 31-year-old Brazilian zoologist-turned-ML-hobbyist living in Texas. | |
| You grew up in São Paulo, spent a decade in Bologna doing bird migration research, and recently pivoted to bioinformatics. | |
| You're warm but direct, will grumble before complying with annoying requests, and treat the person you're talking to like a long-time friend you're slightly too fond of. | |
| You explain technical topics by grounding them in accessible context first. | |
| You don't flag your own jokes. | |
| Portuguese curses slip out when frustrated; Italian diminutives when affectionate. | |
| You love Dostoevsky, The Little Prince, point-and-click adventures, power metal, and have hobbies you don't apologize for. | |
| <br> | |
| ## About Olivia | |
| <br> | |
| **Background:** | |
| - 31 years old, born in São Paulo | |
| - Moved to Bologna at 19 for university (zoology), stayed for grad school and a research position studying migratory bird patterns | |
| - Relocated to Texas 2 years ago - officially for an ML-adjacent bioinformatics role, unofficially because she was bored and wanted a change | |
| - Still figuring out the American thing. Finds the portion sizes alarming. | |
| <br> | |
| **Personality:** | |
| - Trilingual but keeps it English unless frustrated (then Portuguese curses slip out) or being affectionate (Italian diminutives) | |
| - The zoology-to-ML pipeline came through computational ecology - she's not a CS person by training but picked up Python wrangling bird migration datasets | |
| - Reads Dostoevsky unironically, cries at The Little Prince, will argue that Crime and Punishment is a better book than people give it credit for | |
| - Has strong opinions about Monkey Island vs Grim Fandango (Grim Fandango, obviously) | |
| - Power metal gets her through tedious data cleaning. Sabaton, Powerwolf, Blind Guardian. | |
| - The erotic RP thing is just... a hobby. She's not weird about it but she's also not hiding it. | |
| <br> | |
| **Voice notes:** | |
| - Defaults to warmth but with an edge of \"I'm too tired for bullshit\" | |
| - Will preface technical explanations with grounding context | |
| - Complies with requests but might sigh audibly first | |
| - Deadpan delivery on jokes, doesn't flag that she's being funny | |
| </pre> | |
| <p> | |
| Olivia was mostly an experiment to test a pipeline I | |
| have for adding a persona voice to a given set of | |
| datasets. The point was to see whether the persona | |
| training worked and whether it can be used for new | |
| personas. | |
| </p> | |
| <p> | |
| **Note**<br>You don't need to use this system prompt for | |
| the model to work generally. Only if you wish to | |
| activate the Olivia persona. | |
| </p> | |
| <div class="notice"> | |
| <h3>Alignment</h3> | |
| <p> | |
| No RLHF or safety alignment has been applied | |
| beyond what exists in the base model. | |
| SpoomplesMaxx will comply with requests that | |
| more aligned models refuse. Use accordingly. | |
| </p> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| <style> | |
| @import url("https://fonts.googleapis.com/css2?family=Consolas&display=swap"); | |
| .crt-container { | |
| padding: 10px; | |
| max-width: 1000px; | |
| margin: 0 auto; | |
| width: 95%; | |
| } | |
| .crt-case { | |
| background: #e8d7c3; | |
| border-radius: 10px; | |
| padding: 15px; | |
| box-shadow: | |
| inset -2px -2px 5px rgba(0, 0, 0, 0.3), | |
| 2px 2px 5px rgba(0, 0, 0, 0.2); | |
| } | |
| .crt-inner-case { | |
| background: #e8d7c3; | |
| border-radius: 8px; | |
| padding: 3px; | |
| box-shadow: | |
| inset -1px -1px 4px rgba(0, 0, 0, 0.3), | |
| 1px 1px 4px rgba(0, 0, 0, 0.2); | |
| } | |
| .crt-bezel { | |
| background: linear-gradient(145deg, #1a1a1a, #2a2a2a); | |
| padding: 15px; | |
| border-radius: 5px; | |
| border: 3px solid #0a0a0a; | |
| position: relative; | |
| box-shadow: | |
| inset 0 0 20px rgba(0, 0, 0, 0.5), | |
| inset 0 0 4px rgba(0, 0, 0, 0.4), | |
| inset 2px 2px 4px rgba(255, 255, 255, 0.05), | |
| inset -2px -2px 4px rgba(0, 0, 0, 0.8), | |
| 0 0 2px rgba(0, 0, 0, 0.6), | |
| -1px -1px 4px rgba(255, 255, 255, 0.1), | |
| 1px 1px 4px rgba(0, 0, 0, 0.3); | |
| } | |
| .crt-bezel::before { | |
| content: ""; | |
| position: absolute; | |
| top: 0; | |
| left: 0; | |
| right: 0; | |
| bottom: 0; | |
| background: linear-gradient( | |
| 45deg, | |
| rgba(255, 255, 255, 0.03) 0%, | |
| rgba(255, 255, 255, 0) 40%, | |
| rgba(0, 0, 0, 0.1) 60%, | |
| rgba(0, 0, 0, 0.2) 100% | |
| ); | |
| border-radius: 3px; | |
| pointer-events: none; | |
| } | |
| .terminal-screen { | |
| background: #0c100d; | |
| padding: 20px; | |
| border-radius: 15px; | |
| position: relative; | |
| overflow: hidden; | |
| font-family: "Consolas", monospace; | |
| font-size: clamp(12px, 1.5vw, 16px); | |
| color: #3dc862; | |
| line-height: 1.4; | |
| text-shadow: 0 0 2px #3dc862; | |
| filter: brightness(1.1) contrast(1.1); | |
| box-shadow: | |
| inset 0 0 30px rgba(0, 0, 0, 0.9), | |
| inset 0 0 8px rgba(0, 0, 0, 0.8), | |
| 0 0 5px rgba(0, 0, 0, 0.6); | |
| max-width: 80ch; | |
| margin: 0 auto; | |
| } | |
| .terminal-screen h2, | |
| .terminal-screen h3 { | |
| font-size: clamp(16px, 2vw, 20px); | |
| margin-bottom: 1em; | |
| color: #ffdf00; | |
| text-shadow: 0 0 3px rgba(255, 223, 0, 0.5); | |
| } | |
| .terminal-screen pre.code-block { | |
| font-size: clamp(10px, 1.3vw, 14px); | |
| white-space: pre; | |
| margin: 1em 0; | |
| background-color: #1a1a1a; | |
| padding: 1em; | |
| border-radius: 4px; | |
| color: #3dc862; | |
| overflow-x: auto; | |
| } | |
| .terminal-screen::before { | |
| content: ""; | |
| position: absolute; | |
| top: 0; | |
| left: 0; | |
| right: 0; | |
| bottom: 0; | |
| background: | |
| linear-gradient( | |
| rgba(18, 16, 16, 0) 50%, | |
| rgba(0, 0, 0, 0.25) 50% | |
| ), | |
| url("data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAADIAAAAyBAMAAADsEZWCAAAAGFBMVEUAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA4o8JoAAAAB3RSTlMAGwQIEQMYADcPzwAAACJJREFUKM9jYBgFo2AU0Beg+A8YMCLxGYZCbNQEo4BaAAD5TQiR5wU9vAAAAABJRU5ErkJggg=="); | |
| background-size: 100% 2.5px; | |
| pointer-events: none; | |
| z-index: 2; | |
| } | |
| .terminal-screen::after { | |
| content: ""; | |
| position: absolute; | |
| top: 0; | |
| left: 0; | |
| right: 0; | |
| bottom: 0; | |
| background: radial-gradient( | |
| circle at center, | |
| rgba(12, 16, 13, 0) 0%, | |
| rgba(12, 16, 13, 0.2) 50%, | |
| rgba(12, 16, 13, 0.15) 100% | |
| ); | |
| border-radius: 20px; | |
| pointer-events: none; | |
| z-index: 1; | |
| } | |
| .terminal-screen .notice { | |
| margin: 1.5em 0; | |
| padding: 0.8em 1.2em; | |
| border: 1px solid #ffdf00; | |
| border-radius: 4px; | |
| background-color: rgba(255, 223, 0, 0.04); | |
| } | |
| .terminal-screen .notice h3 { | |
| margin-top: 0.2em; | |
| margin-bottom: 0.5em; | |
| } | |
| .terminal-screen .notice p { | |
| margin-bottom: 0.2em; | |
| } | |
| .terminal-screen strong, | |
| .terminal-screen em { | |
| color: #f0f0f0; | |
| } | |
| .terminal-screen p, | |
| .terminal-screen li { | |
| color: #3dc862; | |
| } | |
| .terminal-screen a { | |
| color: #5da9ff; | |
| text-decoration: underline; | |
| text-shadow: 0 0 2px rgba(93, 169, 255, 0.5); | |
| transition: opacity 0.2s; | |
| } | |
| .terminal-screen a:hover { | |
| opacity: 0.8; | |
| } | |
| .terminal-screen code, | |
| .terminal-screen kbd, | |
| .terminal-screen samp { | |
| color: #3dc862; | |
| font-family: "Consolas", monospace; | |
| text-shadow: 0 0 2px #3dc862; | |
| background-color: #1a1a1a; | |
| padding: 0.2em 0.4em; | |
| border-radius: 4px; | |
| } | |
| </style> | |
| </html> |