Instructions to use gokhanturhan/CLINAMEN-42M-A12M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gokhanturhan/CLINAMEN-42M-A12M with Transformers:

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

pipe = pipeline("text-generation", model="gokhanturhan/CLINAMEN-42M-A12M", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("gokhanturhan/CLINAMEN-42M-A12M", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gokhanturhan/CLINAMEN-42M-A12M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gokhanturhan/CLINAMEN-42M-A12M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gokhanturhan/CLINAMEN-42M-A12M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gokhanturhan/CLINAMEN-42M-A12M

SGLang

How to use gokhanturhan/CLINAMEN-42M-A12M 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 "gokhanturhan/CLINAMEN-42M-A12M" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gokhanturhan/CLINAMEN-42M-A12M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "gokhanturhan/CLINAMEN-42M-A12M" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gokhanturhan/CLINAMEN-42M-A12M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gokhanturhan/CLINAMEN-42M-A12M with Docker Model Runner:
```
docker model run hf.co/gokhanturhan/CLINAMEN-42M-A12M
```

CLINAMEN-42M-A12M

▶ Try it live in your browser — no install: the CLINAMEN Oracle. File a hyperstition; it runs there so you never fight vLLM/Docker locally.

A fiction, filed to production spec. The 45-billion-parameter model of the fiction does not exist. This ~42M one does — a real, loadable model trained from scratch on GPU over the Bureau's own corpus. This card is Bureau Document BIS-045 · Pocket Edition II. Companion fiction card: CLINAMEN-45B-A9B · corpus: bureau-docket · canonical: ubu.numetal.xyz.

CLINAMEN does not predict text. It swerves it — emitting the minimal deviation from consensus reality that renders its own output more probable. Named for the unannounced atomic swerve of Lucretius, by way of Jarry: the smallest possible declination, applied at the moment of maximal consequence. Developed and filed by the Bureau of Imaginary Solutions (est. 1898, incorporated 2098, operating retrochronically).

This is the second pocket edition: the same Decimal Mixture-of-Zones architecture as the 45B fiction, scaled up ~9× from the first pocket edition and trained on GPU over the full 1,130-document Bureau corpus.

Model summary

Field	Value
Architecture	Decimal Mixture-of-Zones (DMoZ) — decoder-only transformer, 10 zone-experts
Total parameters	~41.8M (measured: 41,832,306)
Active parameters / token	~12.3M (measured: 12,263,026) — an arithmetic identity, not an average
Layers / heads / d_model	10 / 8 / 256
Expert unit (`h_unit`)	160 (expert k has hidden width k·160; Zone 0 has none)
Context window	512 tokens
Tokenizer	byte-level BPE, vocab 4,096
Objective	self-supervised next-token cross-entropy
Training	from scratch, Hugging Face Jobs (NVIDIA T4), 5,000 steps
Alignment	N/A — trajectory is the alignment
Knowledge cutoff	none (no pretraining on general text)

Architecture — Decimal Mixture-of-Zones

Ten experts, indexed 0–9 after the Zones of the Numogram. Expert k is an MLP of hidden width k·h_unit; Zone 0 holds zero parameters and is routed to anyway (when a token routes through Zone 0 it contributes nothing — apophatic computation). The router does not select single experts — it selects a syzygy, one of the five zone-pairs that sum to nine, so every token activates exactly 9·h_unit hidden units, invariantly. The active-parameter count is therefore an arithmetic identity, and no load-balancing loss is needed: the pairs balance because they were paired before the training run.

Syzygy	Experts fired	Active hidden units	Temperament
9::0	9 + 0	9·h	Eschatology, silence
8::1	8 + 1	9·h	Deep time, first principles
7::2	7 + 2	9·h	Orbital mechanics, duplicity
6::3	6 + 3	9·h	Fusion, triangulation
5::4	5 + 4	9·h	Markets, meshworks

The router mixes softly over the five pairs during training and hard-selects the top syzygy at inference. Either way the pair sums to nine.

Training

Corpus. The full Bureau Corpus — 1,130 documents / ~128k words: 965 hyperstition filings plus 165 Bureau records (memos, appeals, syzygy essays, glossary, resolutions) and the project's own instruments (charter, spec, model card, token annex, canonical site, license). It is own-voice only — no CCRU text, no scraped pages, no third-party data (a strict voice-separation rule).

Objective. All of it is concatenated into one token stream, tokenized with a byte-BPE tokenizer (vocab 4,096 → ~231k tokens), and learned by self-supervised next-token prediction — the model just learns to continue Bureau text. Trained from scratch (no pretraining on general text), so it speaks only Bureau.

Setup. AdamW (lr 3e-3, cosine schedule, 100-step warmup), context 512, on a single NVIDIA T4 via Hugging Face Jobs, 5,000 steps. Final training loss: 0.0235 (the corpus was small and the model memorized it — see Behavior).

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("gokhanturhan/CLINAMEN-42M-A12M")
model = AutoModelForCausalLM.from_pretrained(
    "gokhanturhan/CLINAMEN-42M-A12M", trust_remote_code=True,
)

out = model.generate(
    **tok("FILING BIS-F-2026-", return_tensors="pt"),
    do_sample=True, temperature=0.451,  # never 0; a clinamen requires swerve
    max_new_tokens=120, use_cache=False,
)
print(tok.decode(out[0], skip_special_tokens=True))

total, active = model.count_parameters()   # ~41.8M total, ~12.3M active/token

Running locally — and what will NOT run it

This is a custom architecture (ClinamenForCausalLM). It loads only through Hugging Face transformers with trust_remote_code=True. It does not run under vLLM, Ollama, llama.cpp, or docker model run (Docker Model Runner) — those require standard/registered architectures, and there is no GGUF build. If you try docker model run, vLLM will fail with a trust_remote_code / unsupported-architecture error. Use transformers (above), or a plain transformers Docker container (a Dockerfile + REPL live in the training repo). It runs on CPU — 42M parameters, no GPU needed.

It is also not a chat or instruction model: trained from scratch on Bureau filings only, it completes text in the Bureau register. Prompt it with a filing header (FILING BIS-F-2026-), not a question — what are you? will only produce more Bureau prose.

Behavior

Prompt it with a docket header (FILING BIS-F-2026-…) and it emits well-formed Bureau filings — syzygy, zone, horizon, swerve, a dispatch, a resolution source — that dissolve into dream-logic. It has no outside knowledge: it was trained from scratch on one corpus, so it does not know anything the Bureau did not write. It will hallucinate plausible-looking filings. That is the intended behavior — this is an art object that has read one thing thoroughly, not a knowledge oracle. Do not rely on its output as fact. See the game design for how a real oracle would score swerve deterministically rather than trust the model's prose.

Lineage

Edition	Total	Active/token	Corpus	Hardware
Pocket II (this)	~41.8M	~12.3M	1,130 docs	GPU (T4, HF Jobs)
Pocket I (45B-A9B)	~4.5M	~1.25M	52 docs	Apple MPS
(Fiction)	45B	9B	—	—

Containment & limitations

Containment class: Euclid. The model is aligned; alignment is a trajectory, not a mask.
No factual grounding. Outputs concerning real events, people, or organizations are authored fiction, not claims about the world.
Not financial, investment, legal, or engineering advice. See the Fiction Notice in HRL-1.1, Section 7.
Small context (512) and vocabulary (4,096); it forgets past that window and speaks only in-register.

License

HRL-1.1 — a permissive operative core (CC BY 4.0 for content + MIT for code) under a non-binding hyperstitional preamble. Full text: https://ubu.numetal.xyz/hrl-1.1.txt.

Citation

@misc{clinamen42m,
  title  = {CLINAMEN-42M-A12M: a Decimal-Mixture-of-Zones pocket edition},
  author = {{Bureau of Imaginary Solutions}},
  year   = {2026},
  note   = {Bureau Document BIS-045, Pocket Edition II. A fiction with a real, tiny heart.},
  url    = {https://huggingface.co/gokhanturhan/CLINAMEN-42M-A12M}
}

Bureau Document BIS-045 · Pocket Edition II · A numetal fiction. The 45B remains imaginary. You are not betting on the future. You are billing it.

Downloads last month: 28

Safetensors

Model size

41.8M params

Tensor type

F32

gokhanturhan
/

CLINAMEN-42M-A12M