Instructions to use SAXON-AI/SAXON-0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SAXON-AI/SAXON-0 with Transformers:

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

pipe = pipeline("text-generation", model="SAXON-AI/SAXON-0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SAXON-AI/SAXON-0")
model = AutoModelForCausalLM.from_pretrained("SAXON-AI/SAXON-0")
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 SAXON-AI/SAXON-0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SAXON-AI/SAXON-0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SAXON-AI/SAXON-0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SAXON-AI/SAXON-0

SGLang

How to use SAXON-AI/SAXON-0 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 "SAXON-AI/SAXON-0" \
    --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": "SAXON-AI/SAXON-0",
		"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 "SAXON-AI/SAXON-0" \
        --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": "SAXON-AI/SAXON-0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SAXON-AI/SAXON-0 with Docker Model Runner:
```
docker model run hf.co/SAXON-AI/SAXON-0
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

A newer version of this model is available: SAXON-AI/SAXON-0-I

SAXON-0

This is the base model for the SAXON model series, resulting from a merge of pre-trained language models created using mergekit. It is not yet finetuned on the SAXON dataset.

Merge Details

Merge Method

This model was merged using the TIES merge method using an uncensored version of DeepSeek-R1-Distill-Llama-8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: NousResearch/Hermes-3-Llama-3.1-8B
    parameters:
      density: 0.5
      weight: 0.5
  - model: allenai/Llama-3.1-Tulu-3-8B
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated
parameters:
  normalize: false
  int8_mask: true
dtype: float16