Instructions to use nbeerbower/Denker-mistral-nemo-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nbeerbower/Denker-mistral-nemo-12B with Transformers:

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

pipe = pipeline("text-generation", model="nbeerbower/Denker-mistral-nemo-12B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nbeerbower/Denker-mistral-nemo-12B")
model = AutoModelForCausalLM.from_pretrained("nbeerbower/Denker-mistral-nemo-12B")
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

vLLM

How to use nbeerbower/Denker-mistral-nemo-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nbeerbower/Denker-mistral-nemo-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nbeerbower/Denker-mistral-nemo-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nbeerbower/Denker-mistral-nemo-12B

SGLang

How to use nbeerbower/Denker-mistral-nemo-12B 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 "nbeerbower/Denker-mistral-nemo-12B" \
    --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": "nbeerbower/Denker-mistral-nemo-12B",
		"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 "nbeerbower/Denker-mistral-nemo-12B" \
        --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": "nbeerbower/Denker-mistral-nemo-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nbeerbower/Denker-mistral-nemo-12B with Docker Model Runner:
```
docker model run hf.co/nbeerbower/Denker-mistral-nemo-12B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🧪 Experimental Model

This is one of many experimental iterations I'm sharing publicly while I mess around with training parameters and ideas. It's not a "real" release - just me being transparent about my learning process. Feel free to look under the hood, but don't expect anything production-ready!

Denker-mistral-nemo-12B

Denker is a small, uncensored, reasoning-focused model finetuned using ORPO and QLoRA on top of mistral-nemo-kartoffel-12B.

This run experiments with the Qwen-style chat template and <think>...</think>-style reasoning structure—without modifying the base vocab. All tuning was done via LoRA.

Finetuning Details

Method: ORPO
Epochs: 0.25
Learning Rate: 8e-6, cosine decay w/ 5% warmup
Batch Size: 1 x 64 (64 effective)
Max Grad Norm: 0.5
LoRA Rank: 128
Hardware: 1x NVIDIA RTX A6000

Dataset Composition

Thinking disabled:

Chain of Thought

30,000 samples of each dataset with thinking enabled.

Results

Observations

The model will sometimes decide not to think.

Evals

TBD

Downloads last month: 6

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for nbeerbower/Denker-mistral-nemo-12B

Base model

nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated

Finetuned

nbeerbower/mistral-nemo-kartoffel-12B

Finetuned

(10)

this model

Merges

2 models

Quantizations