Instructions to use arcee-ai/Saul-Instruct-Extended with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arcee-ai/Saul-Instruct-Extended with Transformers:

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

pipe = pipeline("text-generation", model="arcee-ai/Saul-Instruct-Extended")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("arcee-ai/Saul-Instruct-Extended")
model = AutoModelForCausalLM.from_pretrained("arcee-ai/Saul-Instruct-Extended")
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 arcee-ai/Saul-Instruct-Extended with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/arcee-ai/Saul-Instruct-Extended

SGLang

How to use arcee-ai/Saul-Instruct-Extended 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 "arcee-ai/Saul-Instruct-Extended" \
    --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": "arcee-ai/Saul-Instruct-Extended",
		"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 "arcee-ai/Saul-Instruct-Extended" \
        --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": "arcee-ai/Saul-Instruct-Extended",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use arcee-ai/Saul-Instruct-Extended with Docker Model Runner:
```
docker model run hf.co/arcee-ai/Saul-Instruct-Extended
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Saul-Instruct-Extended

Saul-Instruct-Extended is a merge of the following models using mergekit:

🧩 Configuration

  slices:
  - sources:
      - model: Equall/Saul-Instruct-v1
        layer_range:
          - 0
          - 4
  - sources:
      - model: Equall/Saul-Instruct-v1
        layer_range:
          - 3
          - 4
        parameters:
          scale:
            - filter: o_proj
              value: 0
            - filter: down_proj
              value: 0
            - value: 1
  - sources:
      - model: Equall/Saul-Instruct-v1
        layer_range:
          - 4
          - 8
  - sources:
      - model: Equall/Saul-Instruct-v1
        layer_range:
          - 7
          - 8
        parameters:
          scale:
            - filter: o_proj
              value: 0
            - filter: down_proj
              value: 0
            - value: 1
  - sources:
      - model: Equall/Saul-Instruct-v1
        layer_range:
          - 8
          - 12
  - sources:
      - model: Equall/Saul-Instruct-v1
        layer_range:
          - 11
          - 12
        parameters:
          scale:
            - filter: o_proj
              value: 0
            - filter: down_proj
              value: 0
            - value: 1
  - sources:
      - model: Equall/Saul-Instruct-v1
        layer_range:
          - 12
          - 16
  - sources:
      - model: Equall/Saul-Instruct-v1
        layer_range:
          - 15
          - 16
        parameters:
          scale:
            - filter: o_proj
              value: 0
            - filter: down_proj
              value: 0
            - value: 1
  - sources:
      - model: Equall/Saul-Instruct-v1
        layer_range:
          - 16
          - 20
  - sources:
      - model: Equall/Saul-Instruct-v1
        layer_range:
          - 19
          - 20
        parameters:
          scale:
            - filter: o_proj
              value: 0
            - filter: down_proj
              value: 0
            - value: 1
  - sources:
      - model: Equall/Saul-Instruct-v1
        layer_range:
          - 20
          - 24
  - sources:
      - model: Equall/Saul-Instruct-v1
        layer_range:
          - 23
          - 24
        parameters:
          scale:
            - filter: o_proj
              value: 0
            - filter: down_proj
              value: 0
            - value: 1
  - sources:
      - model: Equall/Saul-Instruct-v1
        layer_range:
          - 24
          - 28
  - sources:
      - model: Equall/Saul-Instruct-v1
        layer_range:
          - 27
          - 28
        parameters:
          scale:
            - filter: o_proj
              value: 0
            - filter: down_proj
              value: 0
            - value: 1
  - sources:
      - model: Equall/Saul-Instruct-v1
        layer_range:
          - 28
          - 32
  - sources:
      - model: Equall/Saul-Instruct-v1
        layer_range:
          - 31
          - 32
        parameters:
          scale:
            - filter: o_proj
              value: 0
            - filter: down_proj
              value: 0
            - value: 1
  merge_method: passthrough
  dtype: bfloat16

Downloads last month: 55

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for arcee-ai/Saul-Instruct-Extended

Quantizations

2 models