Instructions to use ReliquaryForge/teutonic-rl-async-v1-step-00000040 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ReliquaryForge/teutonic-rl-async-v1-step-00000040 with Transformers:

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

pipe = pipeline("text-generation", model="ReliquaryForge/teutonic-rl-async-v1-step-00000040")
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("ReliquaryForge/teutonic-rl-async-v1-step-00000040")
model = AutoModelForCausalLM.from_pretrained("ReliquaryForge/teutonic-rl-async-v1-step-00000040", 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 ReliquaryForge/teutonic-rl-async-v1-step-00000040 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ReliquaryForge/teutonic-rl-async-v1-step-00000040"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ReliquaryForge/teutonic-rl-async-v1-step-00000040",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ReliquaryForge/teutonic-rl-async-v1-step-00000040

SGLang

How to use ReliquaryForge/teutonic-rl-async-v1-step-00000040 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 "ReliquaryForge/teutonic-rl-async-v1-step-00000040" \
    --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": "ReliquaryForge/teutonic-rl-async-v1-step-00000040",
		"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 "ReliquaryForge/teutonic-rl-async-v1-step-00000040" \
        --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": "ReliquaryForge/teutonic-rl-async-v1-step-00000040",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ReliquaryForge/teutonic-rl-async-v1-step-00000040 with Docker Model Runner:
```
docker model run hf.co/ReliquaryForge/teutonic-rl-async-v1-step-00000040
```

Teutonic-I Reliquary SFT

Teutonic-I, pretrained on Bittensor Subnet 3, post-trained by Reliquary (Bittensor Subnet 81): supervised distillation from Qwen3.8-27B, with reasoning (thinking mode).

Lineage

Pretraining: dendriteholdings/Teutonic-I, produced by the open model-improvement competition of Teutonic, Bittensor Subnet 3.
Attention graft: Teutonic-I's 8 GLA token mixers (layers 3, 7, ..., 31) replaced by the softmax attention of Qwen/Qwen3.5-9B-Base, then healed by training only those layers on 50M tokens of plain text. Everything else (embeddings, MLPs, the 24 gated-DeltaNet layers) is Teutonic-I's. The result is the stock Qwen3_5ForCausalLM architecture.
SFT (this model), by Reliquary:
- 1 epoch on the full-v2 mix (4.47B target tokens: math 38 %, code 25 %, science 14 %, general 11 %, agentic 8.4 %), LR 4e-5 cosine;
- then one pass on 7,659 long-document QA examples (16k-57k-token documents, questions and answers written by the teacher) + 56M target tokens of full-v2 replay, LR 1e-5.

Architecture Qwen3_5ForCausalLM: 32 layers (24 gated-DeltaNet + 8 full attention), 8.6B parameters, vocabulary 248,320, bfloat16. Trained at 64k context. Thinking mode; the chat template is in this repo.

License

Apache-2.0, as Teutonic-I and Qwen3.5-9B-Base. This model modifies both (see Lineage).

Downloads last month: 25

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for ReliquaryForge/teutonic-rl-async-v1-step-00000040

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

(650)

this model