Instructions to use codelion/Llama-3.3-70B-o1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codelion/Llama-3.3-70B-o1 with Transformers:

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

pipe = pipeline("text-generation", model="codelion/Llama-3.3-70B-o1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codelion/Llama-3.3-70B-o1")
model = AutoModelForCausalLM.from_pretrained("codelion/Llama-3.3-70B-o1")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codelion/Llama-3.3-70B-o1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codelion/Llama-3.3-70B-o1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codelion/Llama-3.3-70B-o1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/codelion/Llama-3.3-70B-o1

SGLang

How to use codelion/Llama-3.3-70B-o1 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 "codelion/Llama-3.3-70B-o1" \
    --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": "codelion/Llama-3.3-70B-o1",
		"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 "codelion/Llama-3.3-70B-o1" \
        --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": "codelion/Llama-3.3-70B-o1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use codelion/Llama-3.3-70B-o1 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 codelion/Llama-3.3-70B-o1 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 codelion/Llama-3.3-70B-o1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for codelion/Llama-3.3-70B-o1 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="codelion/Llama-3.3-70B-o1",
    max_seq_length=2048,
)

Docker Model Runner
How to use codelion/Llama-3.3-70B-o1 with Docker Model Runner:
```
docker model run hf.co/codelion/Llama-3.3-70B-o1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-3.3-70B-o1 Thinker Model

Compared to the base Llama model, this thinker model has a tendency to generate a large number of tokens. So, if you are benchmarking make sure you have the full generated text in the reponse, ending with the <|end_of_solution|> tag. For most queries, you will need to set the max_tokens to at least 8192.

The GGUF quants for the model are available here - Llama-3.3-70B-o1-gguf

The model was trained using QLoRA fine-tuning. You can find the adapter here - Llama-3.3-70B-o1-lora.

Evaluation results

Model	AIME 2024 pass@1
Llama-3.3-70B-o1	46.7
Llama-3.3-70B	30.0
Sky-T1-32B-Preview	43.3
o1-preview	40.0
QwQ	50.0

Developed by: codelion
License: apache-2.0
Finetuned from model : unsloth/llama-3.3-70b-instruct-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 13

Safetensors

Model size

71B params

Tensor type

BF16

Model tree for codelion/Llama-3.3-70B-o1

Merges

2 models

Quantizations

2 models

codelion
/

Llama-3.3-70B-o1

Llama-3.3-70B-o1 Thinker Model

Evaluation results

Model tree for codelion/Llama-3.3-70B-o1

Datasets used to train codelion/Llama-3.3-70B-o1