Instructions to use CortexLM/Teutonic-1-Chat-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CortexLM/Teutonic-1-Chat-Preview with Transformers:

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

pipe = pipeline("text-generation", model="CortexLM/Teutonic-1-Chat-Preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CortexLM/Teutonic-1-Chat-Preview")
model = AutoModelForCausalLM.from_pretrained("CortexLM/Teutonic-1-Chat-Preview", 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 CortexLM/Teutonic-1-Chat-Preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CortexLM/Teutonic-1-Chat-Preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CortexLM/Teutonic-1-Chat-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CortexLM/Teutonic-1-Chat-Preview

SGLang

How to use CortexLM/Teutonic-1-Chat-Preview 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 "CortexLM/Teutonic-1-Chat-Preview" \
    --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": "CortexLM/Teutonic-1-Chat-Preview",
		"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 "CortexLM/Teutonic-1-Chat-Preview" \
        --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": "CortexLM/Teutonic-1-Chat-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CortexLM/Teutonic-1-Chat-Preview with Docker Model Runner:
```
docker model run hf.co/CortexLM/Teutonic-1-Chat-Preview
```

Teutonic-1-Chat-Preview

Commit History

Clarify default checkpoint already has strong needle @128k /256k; LC math-kill co-train not shipped

05e3460
verified

echoctx commited on 3 days ago

docs: README table + MMLU-Redux fair delta

df8aca8
verified

echoctx commited on 3 days ago

docs: add fair MMLU-Redux H2H (87.0 vs 91.3)

4227e09
verified

echoctx commited on 3 days ago

Note residual GPQA/LCB truncation under fair thinking budgets

6999ba7
verified

echoctx commited on 3 days ago

Add fair GPQA-Diamond + LiveCodeBench vs Qwen3.5-9B (thinking protocol) (README)

6204d65
verified

echoctx commited on 3 days ago

Add fair GPQA-Diamond + LiveCodeBench vs Qwen3.5-9B (thinking protocol)

a809dcd
verified

echoctx commited on 3 days ago

Add top-of-card benchmark and preview warnings

7c949bb
verified

echoctx commited on 3 days ago

docs: note 256k-in continued training; keep default weights (math hold)

85336a8
verified

echoctx commited on 3 days ago

Fix MBPP+ corrected score (75.1) and clarify invalid Qwen harness note

f127367
verified

echoctx commited on 3 days ago

Correct Qwen3.5-9B harness benchmarks (thinking budget fix) (#2)

3ee0cab

echoctx

XXMiner commited on 3 days ago

Add same-harness benchmarks vs Qwen3.5-9B

da58283
verified

echoctx commited on 3 days ago

Publish Teutonic-1-Chat-Preview (FP8 default) with training charts

2ec555d
verified

echoctx commited on 3 days ago

initial commit

5897407
verified

echoctx commited on 3 days ago

Commit History

Clarify default checkpoint already has strong needle @128k /256k; LC math-kill co-train not shipped 05e3460 verified

docs: README table + MMLU-Redux fair delta df8aca8 verified

docs: add fair MMLU-Redux H2H (87.0 vs 91.3) 4227e09 verified

Note residual GPQA/LCB truncation under fair thinking budgets 6999ba7 verified

Add fair GPQA-Diamond + LiveCodeBench vs Qwen3.5-9B (thinking protocol) (README) 6204d65 verified

Add fair GPQA-Diamond + LiveCodeBench vs Qwen3.5-9B (thinking protocol) a809dcd verified

Add top-of-card benchmark and preview warnings 7c949bb verified

docs: note 256k-in continued training; keep default weights (math hold) 85336a8 verified

Fix MBPP+ corrected score (75.1) and clarify invalid Qwen harness note f127367 verified

Correct Qwen3.5-9B harness benchmarks (thinking budget fix) (#2) 3ee0cab

Add same-harness benchmarks vs Qwen3.5-9B da58283 verified

Publish Teutonic-1-Chat-Preview (FP8 default) with training charts 2ec555d verified

initial commit 5897407 verified

Clarify default checkpoint already has strong needle @128k /256k; LC math-kill co-train not shipped

05e3460
verified

docs: README table + MMLU-Redux fair delta

df8aca8
verified

docs: add fair MMLU-Redux H2H (87.0 vs 91.3)

4227e09
verified

Note residual GPQA/LCB truncation under fair thinking budgets

6999ba7
verified

Add fair GPQA-Diamond + LiveCodeBench vs Qwen3.5-9B (thinking protocol) (README)

6204d65
verified

Add fair GPQA-Diamond + LiveCodeBench vs Qwen3.5-9B (thinking protocol)

a809dcd
verified

Add top-of-card benchmark and preview warnings

7c949bb
verified

docs: note 256k-in continued training; keep default weights (math hold)

85336a8
verified

Fix MBPP+ corrected score (75.1) and clarify invalid Qwen harness note

f127367
verified

Correct Qwen3.5-9B harness benchmarks (thinking budget fix) (#2)

3ee0cab

Add same-harness benchmarks vs Qwen3.5-9B

da58283
verified

Publish Teutonic-1-Chat-Preview (FP8 default) with training charts

2ec555d
verified

initial commit

5897407
verified