Instructions to use Symbol-LLM/Symbol-LLM-13B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Symbol-LLM/Symbol-LLM-13B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Symbol-LLM/Symbol-LLM-13B-Instruct")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Symbol-LLM/Symbol-LLM-13B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Symbol-LLM/Symbol-LLM-13B-Instruct", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Symbol-LLM/Symbol-LLM-13B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Symbol-LLM/Symbol-LLM-13B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Symbol-LLM/Symbol-LLM-13B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Symbol-LLM/Symbol-LLM-13B-Instruct

SGLang

How to use Symbol-LLM/Symbol-LLM-13B-Instruct 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 "Symbol-LLM/Symbol-LLM-13B-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Symbol-LLM/Symbol-LLM-13B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Symbol-LLM/Symbol-LLM-13B-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Symbol-LLM/Symbol-LLM-13B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Symbol-LLM/Symbol-LLM-13B-Instruct with Docker Model Runner:
```
docker model run hf.co/Symbol-LLM/Symbol-LLM-13B-Instruct
```

Symbol-LLM-13B-Instruct

Commit History

Jul 6, 2025

11:56
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
5a15c4c

Jun 23, 2024

13:34
Update README.md

Symbol-LLM

Verified signature
9bccfa4

Dec 21, 2023

05:22
Update README.md

Symbol-LLM

d93639d
05:18
Update README.md

Symbol-LLM

5a93ea5
04:45
Upload pytorch_model-00001-of-00003.bin

Symbol-LLM

abf8aa1

Dec 20, 2023

14:52
Upload pytorch_model-00002-of-00003.bin

Symbol-LLM

c568858
11:15
Upload pytorch_model-00003-of-00003.bin

Symbol-LLM

b04094c

Dec 6, 2023

02:39
Upload 7 files

Symbol-LLM

a1933c2

Dec 5, 2023

11:49
initial commit

Symbol-LLM

4f5112b

Commit History

Jul 6, 2025

Adding `safetensors` variant of this model⁠

Jun 23, 2024

Update README.md

Dec 21, 2023

Update README.md

Update README.md

Upload pytorch_model-00001-of-00003.bin

Dec 20, 2023

Upload pytorch_model-00002-of-00003.bin

Upload pytorch_model-00003-of-00003.bin

Dec 6, 2023

Upload 7 files

Dec 5, 2023

initial commit