Instructions to use aimeri/spoomplesmaxx-mockingbird-36B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aimeri/spoomplesmaxx-mockingbird-36B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="aimeri/spoomplesmaxx-mockingbird-36B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aimeri/spoomplesmaxx-mockingbird-36B")
model = AutoModelForCausalLM.from_pretrained("aimeri/spoomplesmaxx-mockingbird-36B", device_map="auto")
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-mockingbird-36B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aimeri/spoomplesmaxx-mockingbird-36B"
# 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-mockingbird-36B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aimeri/spoomplesmaxx-mockingbird-36B

SGLang

How to use aimeri/spoomplesmaxx-mockingbird-36B 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-mockingbird-36B" \
    --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-mockingbird-36B",
		"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-mockingbird-36B" \
        --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-mockingbird-36B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aimeri/spoomplesmaxx-mockingbird-36B with Docker Model Runner:
```
docker model run hf.co/aimeri/spoomplesmaxx-mockingbird-36B
```

spoomplesmaxx-mockingbird-36B

File size: 35,630 Bytes

---
license: apache-2.0
base_model: ByteDance-Seed/Seed-OSS-36B-Base-woSyn
library_name: transformers
pipeline_tag: text-generation
tags:
  - roleplay
  - creative-writing
language:
  - en
---
<!doctype html>
<html lang="en">
    <head>
        <meta charset="UTF-8" />
        <meta name="viewport" content="width=device-width, initial-scale=1.0" />
        <title>SpoomplesMaxx Mockingbird 36B</title>
    </head>
    <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-image {
            display: inline-block;
            text-align: left;
            font-size: clamp(2px, 0.4vw, 12px);
            font-family: monospace;
            margin: 1em 0;
            background-color: #1a1a1a;
            padding: 1em;
            border-radius: 4px;
            color: #3dc862;
            overflow-x: auto;
            line-height: 1;
            max-width: 100%;
            white-space: pre;
        }
        .terminal-screen pre.code-block {
            display: inline-block;
            text-align: left;
            font-size: clamp(10px, 1.3vw, 14px);
            font-family: monospace;
            margin: 1em 0;
            background-color: #1a1a1a;
            padding: 1em;
            border-radius: 4px;
            color: #3dc862;
            overflow-x: auto;
            line-height: 1;
            max-width: 100%;
            white-space: pre;
        }
        .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>
    <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-Mockingbird-36B</h2>
                            <h3>"Fat Mockingbird"</h3>
                            <pre class="code-block-image">
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▒▒▒▒▒▒▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▒▒▒▓▓▓▓▓▓▒▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒▒▒░░░░░░░▒░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒▒▒▒▓▒▓▓▓▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒▒▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒▒▒▒▒▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▒▒▒▒▒▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▒▒▒▒▒▒▒▒▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒▒▒▒▒▒▒▒▒▒▒▒▓▓▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒░▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▒▒▒▒▒░▒▒▒░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░▒░░░░░░░▓▓▓▓▓▓▒▓▓▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓░▓░▒░░░░░░░░░▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░▓░░░░░░▓▓▓▓▓▓▒▒▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▒░░▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░░░░▓░░░░░▒▓░░▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░▓░░▓░░░░░░░▒▒▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░░░░░░░░▒▒▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░▒▒▒▒▒▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▒▒▒▒▒▒▒▒▒▒▒▒▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▓▓░▓▓▓▒░░▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓░░░░░░░▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓░▒░░░▒░▓░▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░░░░░░░░░░░░▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▒░▓▓▓▓▓▓▓▓░▓▓▓▓▓▓░░░░░░░▓▓▓▓▓░░░░░░░░▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▒░░░░▓▓▓▓▓▓▓▓▓░░░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓░▒░░░░░░▓▓▓▓▓░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░▓░░▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓░░▒▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▒░░░░░░░▓▓▓▓▓░░░▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▒▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓░░░░░▒▓░░▓░░░▒░▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▒▓▓▓▓▓▓▓▓▓░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓░░▓▓▒░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓░░░▒░░░▓░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
                            </pre>
                        </div>
                        <p>
                            <strong>"Many-Tongued"</strong> — <em>Mimus
                            polyglottos</em>, the many-tongued mimic. A bird
                            with no song of its own and therefore all of them:
                            it will do the cardinal, the car alarm, the creaky
                            gate, and a frog if it hears one. First of the
                            mimids, the family that follows the corvids.
                        </p>
                        <p>
                            The corvids (jackdaw, magpie, whiskeyjack) were
                            generalists with a roleplay bent. mockingbird flips
                            the recipe: <strong>a model that is 100% about
                            roleplay, trained mostly on things that are not
                            roleplay.</strong> That is not a contradiction — it
                            is the finding. Measured across the strongest open
                            RP lineage I know
                            (<a href="https://huggingface.co/PocketDoc/Dans-PersonalityEngine-V1.3.0-24b">Dans-PersonalityEngine</a>),
                            roughly 590K of its rows are
                            task/reasoning/assistant/world-knowledge data
                            against ~150K of actual roleplay. RP is the
                            product; RP is not the corpus. The RP data teaches
                            the register. Everything else teaches the mind
                            behind it.
                        </p>
                        <p>
                            Built on <strong>Seed-OSS-36B-Base-woSyn</strong> —
                            the base ByteDance trained <em>without</em>
                            synthetic instruction data. The wildest 36B
                            available: nobody else's assistant habits, nobody
                            else's turn-taking tics. A blank throat, ready to
                            mimic.
                        </p>
                        <h3>Who this is for</h3>
                        <p>
                            36B dense is a lot of model, and no friend to the
                            VRAM-challenged — something I'm genuinely sorry
                            about. But the target here was the best-quality RP
                            under 70B, and every choice in this card spends
                            toward that target. It won't be for everyone, and
                            it doesn't have to be: whiskeyjack exists for
                            exactly that reason. The mimids are an experiment
                            in RP quality, exclusively. The 3-bit quants
                            (~18GB) are as small as this one gets.
                        </p>
                        <h3>Prompt format</h3>
                        <p>
                            Native Seed convention. No new tokens were harmed
                            in the making of this model.
                        </p>
                        <pre class="code-block">
FORM     &lt;seed:bos&gt;system\n{card}&lt;seed:eos&gt;&lt;seed:bos&gt;user\n{text}&lt;seed:eos&gt;&lt;seed:bos&gt;assistant\n{reply}&lt;seed:eos&gt;
STOPS    &lt;seed:eos&gt;
ROLES    system / user / assistant

EXAMPLE
&lt;seed:bos&gt;system
You are Bram Hollis, keeper of the Wayward Lantern...&lt;seed:eos&gt;&lt;seed:bos&gt;user
*I push the door open, dripping wet* Got room for one more?&lt;seed:eos&gt;&lt;seed:bos&gt;assistant
</pre>
                        <p>
                            The template ships embedded
                            (<code>chat_template.jinja</code> +
                            <code>tokenizer_config.json</code>), so vLLM,
                            llama.cpp, and the quants pick it up without
                            ceremony. Anything that can serve Seed-OSS-Instruct
                            serves mockingbird.
                        </p>
                        <div class="notice">
                            <h3>No thinking. Ever.</h3>
                            <p>
                                mockingbird never emits
                                <code>&lt;seed:think&gt;</code> and was never
                                trained on reasoning traces
                            </p>
                        </div>
                        <h3>Tool calling</h3>
                        <p>
                            The corpus includes the full Toolmaxx family
                            (58,095 conversations), rendered with tool
                            responses as a plain <code>tool</code> role turn:
                        </p>
                        <pre class="code-block">
&lt;seed:bos&gt;tool\n{tool output}&lt;seed:eos&gt;
</pre>
                        <div class="notice">
                            <h3>Not the Seed-OSS-Instruct tool DSL.</h3>
                            <p>
                                No <code>&lt;seed:tool_call&gt;</code> tokens,
                                no <code>&lt;function=...&gt;</code> markup.
                                Tool competence here is corpus-taught and
                                conversational, not a structured calling API.
                                If you need strict function calling, put a
                                schema in the card and validate what comes back
                            </p>
                        </div>
                        <h3>Key details</h3>
                        <pre class="code-block">
BASE       ByteDance-Seed/Seed-OSS-36B-Base-woSyn  (Apache 2.0)
PARAMS     36B dense · 64 layers · GQA 8 KV heads · head_dim 128
VOCAB      155,136 · native Seed control tokens · zero added tokens
CTX        trained at 24,576 packed · base RoPE to 512K
CORPUS     667,332 conversations · ~1.3B supervised chars · 43% RP share
THINKING   none, by construction
LANGUAGE   English (non-English filtered at ingest)
</pre>
                        <h3>Training</h3>
                        <p>
                            Full-parameter SFT,
                            <a href="https://github.com/axolotl-ai-cloud/axolotl">Axolotl</a>,
                            8×B200. One stage, no annealing games:
                        </p>
                        <pre class="code-block">
STEPS     584 run of 910 planned (funding cliff) · this release = step 450
SEQ       24,576 · sample packing (99.94% efficiency)
BATCH     64 global (micro 1 × accum 8 × 8 GPUs)
OPT       AdamW · lr 8e-6 cosine · 3% warmup · wd 0.01 · bf16
STACK     FSDP2 full-shard · activation checkpointing · Cut Cross Entropy

VAL PPL   base 4.272 → step 100: 4.094 (min) → step 550: 4.179
</pre>
                        <p>
                            Val perplexity bottoms out early and drifts up; it
                            did not pick this checkpoint. Selection ran the
                            other way: every 50th checkpoint through a seeded
                            multi-turn loop/stall battery (×5 repeats), a
                            20-arm sampler sweep across the finalists
                            (400/450/500) at 16K context, and blind-judged
                            episodes on real character cards. Step 450 won on
                            both instruments: the highest battery pass rate in
                            the whole sweep matrix at its shipped sampler, and
                            the most coherent judged episodes. Earlier
                            checkpoints still loop; later ones need
                            temperatures where coherence frays.
                        </p>
                        <p>
                            The corpus is the PersonalityEngine V1.3.0 public
                            list — all 42 non-gated sets, ingested verbatim —
                            plus my own lanes on top: 16,714 carded RP
                            conversations (anthracite c2, Gryphe Aesir,
                            PJMixers, bluemoon), 8,872 think-stripped RP logs,
                            and a 385-conversation anti-repetition lane built
                            to reconstruct the gated RepRemover idea: find the
                            turn that repeats an earlier turn, cut there,
                            rewrite the continuation to advance the scene,
                            accept only if it clears a Jaccard 0.35 gate
                            against every prior turn.
                        </p>
                        <div class="notice">
                            <h3>The corpus was cleaned so the model doesn't have to be.</h3>
                            <p>
                                Dropped at ingest, with receipts:
                                <code>Name:</code>-style fiction-transcript
                                openers (up to 18.2% of one source — the
                                classic RP defect), mid-scene policy refusals
                                and jailbreak-compliance preambles (851 + 452
                                conversations - not really needed for this
                                model), non-English rows, exact duplicates
                                across lanes (5,332). Conversations longer than
                                the context window were split at turn
                                boundaries with the card re-carried, not
                                truncated (one Personamaxx-VN row was a single
                                4.85M-char turn; it did not make the cut).
                            </p>
                        </div>
                        <h3>Sampling</h3>
                        <p>
                            The shipped <code>generation_config.json</code> is
                            the measured optimum, not a guess — it won a 20-arm
                            sweep (temperature × top_p × min_p × penalties, ×5
                            seeded battery runs per arm, plus blind-judged
                            episodes):
                        </p>
                        <pre class="code-block">
temperature 1.0 · top_p 0.9 · no penalties
</pre>
                        <p>
                            The usable window is narrow and hotter than RP
                            muscle memory expects: <strong>~0.95–1.05</strong>.
                            Below ~0.85 the model collapses into verbatim
                            self-repetition (at 0.7 it re-emits its previous
                            turn nearly word for word). Above ~1.15
                            turn-endings slip and the prose goes dreamlike.
                            min_p alone (0.05, top_p off) truncates harder than
                            top_p 0.9 and loops <em>more</em>, not less. This
                            is not a temperature-0.7 model.
                        </p>
                        <div class="notice">
                            <h3>Never use repetition, presence, or frequency penalties.</h3>
                            <p>
                                The Seed template ends every message with
                                <code>&lt;seed:eos&gt;</code>, so a multi-turn
                                chat has dozens of them in context.
                                Context-wide penalties tax that token directly:
                                the model stops being able to end its turn, the
                                penalty then strip-mines the English
                                vocabulary, and generation falls into the base
                                model's untrained Chinese tokens
                                (<code>爹爹爹爹爹…</code> — it is exactly as
                                bad as it looks). If you need anti-repetition,
                                use DRY or XTC, which leave special tokens
                                alone. The corpus's anti-repetition lane plus
                                temperature 1.0 is the intended mechanism.
                            </p>
                        </div>
                        <p>
                            Give it a proper card and it will give you a proper
                            character: the model was fed real character cards
                            (median ~3K chars, p90 ~8.5K) as system messages.
                        </p>
                        <h3>Quickstart</h3>
                        <pre class="code-block">
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "aimeri/spoomplesmaxx-mockingbird-36B"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, torch_dtype="bfloat16", device_map="auto")

messages = [
    {"role": "system", "content": "You are Bram Hollis, keeper of the "
        "Wayward Lantern, a roadside inn on the edge of the fen. Gruff, "
        "observant, superstitious. Third person, *asterisk action beats*."},
    {"role": "user", "content": "*I push the door open, dripping wet* "
        "Got room for one more tonight?"},
]
ids = tok.apply_chat_template(messages, add_generation_prompt=True,
    return_tensors="pt").to(model.device)
out = model.generate(ids, max_new_tokens=400, temperature=1.0, top_p=0.9,
    do_sample=True)
print(tok.decode(out[0][ids.shape[-1]:], skip_special_tokens=True))
</pre>
                        <p>Quants:
                            <a href="https://huggingface.co/aimeri/spoomplesmaxx-mockingbird-36B-mlx-3bit">MLX 3-bit</a> (15GB, Apple silicon) ·
                            <a href="https://huggingface.co/aimeri/spoomplesmaxx-mockingbird-36B-GGUF">GGUF static Q3–Q5</a> ·
                            <a href="https://huggingface.co/aimeri/spoomplesmaxx-mockingbird-36B-i1-GGUF">GGUF imatrix</a>
                            (weighted on the model’s own corpus — prefer these at 3–4 bit;
                            i1-Q3_K_M is the 18GB target, i1-IQ3_XXS squeezes to 14GB)</p>
                        <p>This one already knows your character better than you do.</p>
                        <p>
                            <em>mockingbird is a roleplay and creative-writing
                            model for adults. It stays in character by design —
                            its corpus was scrubbed of mid-scene refusals — so
                            bring your own moderation where your deployment
                            needs it. Not an assistant, not an oracle, not for
                            anything safety-critical.</em>
                        </p>
                        <p>
                            <em>mimids 01 · trained 2026-08 · checkpoints
                            published live at
                            <a href="https://huggingface.co/aimeri/mockingbird-v1-seedoss-ckpts">mockingbird-v1-seedoss-ckpts</a>
                            · Apache 2.0</em>
                        </p>
                    </div>
                </div>
            </div>
        </div>
    </div>

</html>