Instructions to use 11-47/Continuum-0.1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 11-47/Continuum-0.1B with Transformers:

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

pipe = pipeline("text-generation", model="11-47/Continuum-0.1B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("11-47/Continuum-0.1B", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use 11-47/Continuum-0.1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "11-47/Continuum-0.1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "11-47/Continuum-0.1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/11-47/Continuum-0.1B

SGLang

How to use 11-47/Continuum-0.1B 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 "11-47/Continuum-0.1B" \
    --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": "11-47/Continuum-0.1B",
		"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 "11-47/Continuum-0.1B" \
        --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": "11-47/Continuum-0.1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 11-47/Continuum-0.1B with Docker Model Runner:
```
docker model run hf.co/11-47/Continuum-0.1B
```

Continuum-0.1B / README.md

11-47

Upload README.md with huggingface_hub

35773de verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

2.09 kB

metadata

license: apache-2.0
language:
  - en
tags:
  - continuum
  - hybrid-mind
  - self-evolving
  - causal-lm
  - meta-learning
  - continual-learning
  - emotional-intelligence
  - multimodal
  - memory
  - reinforcement-learning
model-index:
  - name: Continuum-0.1B
    results: []
pipeline_tag: text-generation
library_name: transformers

Continuum-0.1B — The Hybrid Mind

Continuum-0.1B is a ~111M-parameter self-evolving Small Language Model built from scratch by 11-47 / WithInUsAI. It unifies 25 autonomous Hybrid-Mind subsystems into a single decoder-only transformer forward pass.

Architecture

Component	Spec
Type	Decoder-only transformer
Parameters	~111M (tied embeddings)
Context	64 096 tokens (64K + seed)
Layers	12
Hidden size	768
FFN	SwiGLU, intermediate=2048
Attention	GQA (12Q / 4KV heads)
Position	NTK-aware RoPE θ=500 000
Norm	Pre-norm RMSNorm
Dtype	BFloat16

Training

Hardware: 2x T4 GPUs (Kaggle) via DataParallel
Steps: 3000 (effective batch 16 × 2048 tokens)
Resume: Auto-resumes from HF Hub checkpoint if kernel restarts

Datasets

Dataset	Source
Claude Opus Mythos 5K	`WithinUsAI/claude_opus_mythos_5k`
Claude Opus 4.8 Distill	`WithinUsAI/claude_opus_4.8_distill`
Claude Mythos Distill	`WithinUsAI/claude_mythos_distill`
Opus 4.7 Thinking Max Distill (25K)	`WithinUsAI/Opus4.7_thinking_max_distill_god_seed_25k`
Claude Opus 4.7 Distilled	`WithinUsAI/claude_Opus_4.7_Distilled`
Mythos Preview 5K v2	`11-47/cluade_mythos_preview_5k_v2`
Claude Opus 4.8 Max Thinking 5K v2	`11-47/claude_opus_4.8_max_thinking_5k_v2`

Quick Start

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("11-47/Continuum-0.1B", trust_remote_code=True)
model     = AutoModelForCausalLM.from_pretrained(
    "11-47/Continuum-0.1B",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)

License

Apache 2.0