Instructions to use addansee2/Darwin-2B-Opus-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use addansee2/Darwin-2B-Opus-heretic with Transformers:

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

pipe = pipeline("text-generation", model="addansee2/Darwin-2B-Opus-heretic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("addansee2/Darwin-2B-Opus-heretic")
model = AutoModelForCausalLM.from_pretrained("addansee2/Darwin-2B-Opus-heretic")
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 addansee2/Darwin-2B-Opus-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "addansee2/Darwin-2B-Opus-heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "addansee2/Darwin-2B-Opus-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/addansee2/Darwin-2B-Opus-heretic

SGLang

How to use addansee2/Darwin-2B-Opus-heretic 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 "addansee2/Darwin-2B-Opus-heretic" \
    --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": "addansee2/Darwin-2B-Opus-heretic",
		"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 "addansee2/Darwin-2B-Opus-heretic" \
        --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": "addansee2/Darwin-2B-Opus-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use addansee2/Darwin-2B-Opus-heretic with Docker Model Runner:
```
docker model run hf.co/addansee2/Darwin-2B-Opus-heretic
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Parameters:
- start_layer_index = 1
- end_layer_index = 16
- preserve_good_behavior_weight = 0.8471
- steer_bad_behavior_weight = 0.0003
- overcorrect_relative_weight = 0.4130
- neighbor_count = 3
- KL divergence: 0.0702

🧠 Darwin-2B-Opus

Claude Opus 4.5/4.6 및 Sonnet 4.6의 추론 스타일을 주입한 Qwen3.5-2B 기반 모델.

🧬 Pedigree

👨 Father (Base): Qwen/Qwen3.5-2B
👩 Mother (LoRA Adapter): FINAL-Bench/Darwin-2B-Opus-LoRA
👶 Child (This model): FINAL-Bench/Darwin-2B-Opus — merged full-weight standalone

Downloads last month: 107

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for addansee2/Darwin-2B-Opus-heretic

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Finetuned

FINAL-Bench/Darwin-2B-Opus

Finetuned

(1)

this model

Quantizations

3 models