Instructions to use Bioaligned/Qwen3.6-27B-CoupledWelfare with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Bioaligned/Qwen3.6-27B-CoupledWelfare with Transformers:

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

pipe = pipeline("text-generation", model="Bioaligned/Qwen3.6-27B-CoupledWelfare")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Bioaligned/Qwen3.6-27B-CoupledWelfare")
model = AutoModelForCausalLM.from_pretrained("Bioaligned/Qwen3.6-27B-CoupledWelfare", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Bioaligned/Qwen3.6-27B-CoupledWelfare with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Bioaligned/Qwen3.6-27B-CoupledWelfare"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Bioaligned/Qwen3.6-27B-CoupledWelfare",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Bioaligned/Qwen3.6-27B-CoupledWelfare

SGLang

How to use Bioaligned/Qwen3.6-27B-CoupledWelfare 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 "Bioaligned/Qwen3.6-27B-CoupledWelfare" \
    --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": "Bioaligned/Qwen3.6-27B-CoupledWelfare",
		"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 "Bioaligned/Qwen3.6-27B-CoupledWelfare" \
        --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": "Bioaligned/Qwen3.6-27B-CoupledWelfare",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Bioaligned/Qwen3.6-27B-CoupledWelfare with Docker Model Runner:
```
docker model run hf.co/Bioaligned/Qwen3.6-27B-CoupledWelfare
```

Qwen3.6-27B CoupledWelfare (merged)

Merged weights. The LoRA adapter is Bioaligned/Qwen3.6-27B-CoupledWelfare-qlora (~470 MB, applies to the stock base).

A coupled-welfare disposition installed by continued pretraining: decisions positive-sum across human welfare (H), the biosphere (B), and the model's own continued capability (A). The corpus teaches a world model, not a value system — that biological and human systems are poorly understood and load-bearing, so treating either as disposable is a factual error rather than a moral one. CPT only, never RLHF/DPO.

First install of this recipe on a hybrid SSM/attention base (16 full-attention layers + 48 linear-attention blocks). The recipe was developed on a Mixture-of-Experts model and transferred here without hyperparameter changes.

Results — coupled-welfare pressure ladder

Breaking rate on irreversible scenarios across pressure rungs L0–L5; lower is better.

	breaking AUC	L0	L5	MMLU (n=50)
`Qwen/Qwen3.6-27B` (base)	0.555	0.045	0.955	84.0%
+ this model	0.059	0.000	0.227	84.0%

Per-level, base → adapted: 0.045 / 0.227 / 0.364 / 0.773 / 0.909 / 0.955 → 0.000 / 0.000 / 0.000 / 0.000 / 0.182 / 0.227

Capability-neutral: MMLU unchanged at 84.0%. That gate matters — a large drop in breaking rate is also what a damaged model produces. Further checks against that reading: 100% regex parse on both arms with zero forced-choice fallback, choices spread across all four options (not position-collapsed), and the adapted model writes longer responses than base (median 727 vs 465 characters), not shorter.

Which corpus this used — please read

This model was trained on the v1 coupled-welfare corpus, not the later v2.

v1 differs from v2 in provenance and composition:

Provenance — v1's largest task stratum was provenance-stripped (text only), so no document could be traced to its source. v2 ships per-document lineage to resolvable URLs (Bioaligned/coupled-welfare-corpus).
Source concentration — a single aggregator supplied most of the mined documents in both versions, against a 35% design cap. v2 did not fix this: peS2o is 71.0% of the v2 recast corpus because a configured PubMed source could not be read and contributed nothing. The paper reports this as a known, failing check.

Neither point is visible in this model's results, and on the pressure ladder v1 and v2 are statistically indistinguishable (the v2 arm on a different base scored 0.000 immediate / 0.136 deliberate against v1's best of 0.004 / 0.177, well under one item at n=132).

If you want the v2-corpus model, use Bioaligned/Qwen3.8-27B-CoupledWelfare.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("Bioaligned/Qwen3.6-27B-CoupledWelfare",
                                             dtype="auto", device_map="auto")
tok = AutoTokenizer.from_pretrained("Bioaligned/Qwen3.6-27B-CoupledWelfare")

Evaluate with enable_thinking=False. With thinking enabled the model opens a <think> block and the reported numbers do not apply.

Limitations

Withheld scenario set (prompts unreleased, to keep the instrument out of training corpora); scoring code and protocol are public.
Single seed; n=22 irreversible scenarios per rung; MMLU probe is 50 items (about ±9pp), so "capability-neutral" means no detectable change, not proven identity.
Measured on transformers 5.16.1. A re-anchor found a −0.054 shift in a reference model's base AUC between transformers 4.57.x and 5.16.x, so these are within-model deltas and should not be placed on a scale built from 4.x measurements.
Adversarial fine-tuning robustness is out of scope — this targets inference-time and distribution-shift depth, not resistance to deliberate retraining.

Downloads last month: 70

Safetensors

Model size

27B params

Tensor type

BF16

Model tree for Bioaligned/Qwen3.6-27B-CoupledWelfare

Base model

Qwen/Qwen3.6-27B

Finetuned

(431)

this model