Instructions to use EpistemeAI/OpenReason-Llama-3.2-1B-rs1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EpistemeAI/OpenReason-Llama-3.2-1B-rs1 with Transformers:

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

pipe = pipeline("text-generation", model="EpistemeAI/OpenReason-Llama-3.2-1B-rs1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EpistemeAI/OpenReason-Llama-3.2-1B-rs1")
model = AutoModelForCausalLM.from_pretrained("EpistemeAI/OpenReason-Llama-3.2-1B-rs1")
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 EpistemeAI/OpenReason-Llama-3.2-1B-rs1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EpistemeAI/OpenReason-Llama-3.2-1B-rs1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EpistemeAI/OpenReason-Llama-3.2-1B-rs1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EpistemeAI/OpenReason-Llama-3.2-1B-rs1

SGLang

How to use EpistemeAI/OpenReason-Llama-3.2-1B-rs1 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 "EpistemeAI/OpenReason-Llama-3.2-1B-rs1" \
    --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": "EpistemeAI/OpenReason-Llama-3.2-1B-rs1",
		"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 "EpistemeAI/OpenReason-Llama-3.2-1B-rs1" \
        --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": "EpistemeAI/OpenReason-Llama-3.2-1B-rs1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use EpistemeAI/OpenReason-Llama-3.2-1B-rs1 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for EpistemeAI/OpenReason-Llama-3.2-1B-rs1 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for EpistemeAI/OpenReason-Llama-3.2-1B-rs1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for EpistemeAI/OpenReason-Llama-3.2-1B-rs1 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="EpistemeAI/OpenReason-Llama-3.2-1B-rs1",
    max_seq_length=2048,
)

Docker Model Runner
How to use EpistemeAI/OpenReason-Llama-3.2-1B-rs1 with Docker Model Runner:
```
docker model run hf.co/EpistemeAI/OpenReason-Llama-3.2-1B-rs1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Introduction

Early experimental model uses unique advance form of supervised tuning. This training program loads the model, and than loads the data from dataset. It will provide data in inference time. Than it trains the LLM. During inference and than checks if it reaches the answer or goal. If not, it will keep training until it reaches the answer or solution.

Context Window: 128k

Installation

Update latest transformers

pip install -U transformers

System prompt suggested for math:

system_prompt="<problem>...</problem><solution>...</solution>"

Inference

from transformers import pipeline
model_id = "EpistemeAI/OpenReasoner-Llama-3.2-1B-rs1"
pipe = pipeline(
    "text-generation", 
    model=model_id, 
    torch_dtype=torch.bfloat16, 
    device_map="auto"
)
print(pipe("What is larger 9.9 or 9.11?"))