Instructions to use DoppelReflEx/L3-8B-R1-WolfCore with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DoppelReflEx/L3-8B-R1-WolfCore with Transformers:

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

pipe = pipeline("text-generation", model="DoppelReflEx/L3-8B-R1-WolfCore")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DoppelReflEx/L3-8B-R1-WolfCore")
model = AutoModelForCausalLM.from_pretrained("DoppelReflEx/L3-8B-R1-WolfCore")
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 DoppelReflEx/L3-8B-R1-WolfCore with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DoppelReflEx/L3-8B-R1-WolfCore"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DoppelReflEx/L3-8B-R1-WolfCore",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DoppelReflEx/L3-8B-R1-WolfCore

SGLang

How to use DoppelReflEx/L3-8B-R1-WolfCore 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 "DoppelReflEx/L3-8B-R1-WolfCore" \
    --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": "DoppelReflEx/L3-8B-R1-WolfCore",
		"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 "DoppelReflEx/L3-8B-R1-WolfCore" \
        --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": "DoppelReflEx/L3-8B-R1-WolfCore",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DoppelReflEx/L3-8B-R1-WolfCore with Docker Model Runner:
```
docker model run hf.co/DoppelReflEx/L3-8B-R1-WolfCore
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

What is this?

A Llama3 model with Deepseek R1 Distill merge. Maybe it's not suit for RP?

Overall, this merge model is the best and smartest RP, ERP model. But the IFEval score is lower than other model, so I think it's wont follow well your instructions? I didn't test yet, will have a test later

## Merge Detail

### Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: NeverSleep/Lumimaid-v0.2-8B
merge_method: model_stock
dtype: bfloat16
models:
  - model: cgato/L3-TheSpice-8b-v0.8.3
  - model: Sao10K/L3-8B-Stheno-v3.2
  - model: TheDrummer/Llama-3SOME-8B-v2
  - model: SicariusSicariiStuff/Wingless_Imp_8B
  - model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B