Instructions to use akjindal53244/Llama-3.1-Storm-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use akjindal53244/Llama-3.1-Storm-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="akjindal53244/Llama-3.1-Storm-8B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("akjindal53244/Llama-3.1-Storm-8B") model = AutoModelForCausalLM.from_pretrained("akjindal53244/Llama-3.1-Storm-8B", device_map="auto") 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use akjindal53244/Llama-3.1-Storm-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "akjindal53244/Llama-3.1-Storm-8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "akjindal53244/Llama-3.1-Storm-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/akjindal53244/Llama-3.1-Storm-8B
- SGLang
How to use akjindal53244/Llama-3.1-Storm-8B 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 "akjindal53244/Llama-3.1-Storm-8B" \ --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": "akjindal53244/Llama-3.1-Storm-8B", "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 "akjindal53244/Llama-3.1-Storm-8B" \ --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": "akjindal53244/Llama-3.1-Storm-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use akjindal53244/Llama-3.1-Storm-8B with Docker Model Runner:
docker model run hf.co/akjindal53244/Llama-3.1-Storm-8B
Ollama?
Sorry if this is a dumb question - but can this be used with/in Ollama?
If so - how do I get it in?
Thanks - I'll download it now and give it a spin!
Downloaded "PULL" OK
adam@xenomorph:~$ ollama pull ajindal/llama3.1-storm:8b
pulling manifest
pulling 85c52e1d24f8... 100% ββββββββββββββββββββββββββββββββββββββββββββββββββββββ 4.7 GB
pulling 75357d685f23... 100% ββββββββββββββββββββββββββββββββββββββββββββββββββββββ 28 B
pulling 1970553b62f4... 100% ββββββββββββββββββββββββββββββββββββββββββββββββββββββ 1.7 KB
pulling 418d4136a93a... 100% ββββββββββββββββββββββββββββββββββββββββββββββββββββββ 12 KB
pulling 56bb8bd477a5... 100% ββββββββββββββββββββββββββββββββββββββββββββββββββββββ 96 B
pulling 04d5e68bf551... 100% ββββββββββββββββββββββββββββββββββββββββββββββββββββββ 559 B
verifying sha256 digest
writing manifest
removing any unused layers
success
- but seems to have an error:
ollama run ajindal/llama3.1-storm:8b
Error: template: :12: function "json" not defined
Not sure what to do next.
Are you on latest Ollama? I am able to run it.
Can you paste your complete command/input so I can reproduce it?
I am able to run this example:
import ollama
tools = [{
'type': 'function',
'function': {
'name': 'get_current_weather',
'description': 'Get the current weather for a city',
'parameters': {
'type': 'object',
'properties': {
'city': {
'type': 'string',
'description': 'The name of the city',
},
},
'required': ['city'],
},
},
},
{
'type': 'function',
'function': {
'name': 'get_places_to_vist',
'description': 'Get places to visit in a city',
'parameters': {
'type': 'object',
'properties': {
'city': {
'type': 'string',
'description': 'The name of the city',
},
},
'required': ['city'],
},
},
},
]
response = ollama.chat(
model='ajindal/llama3.1-storm:8b',
messages=[
{'role': 'system', 'content': 'You are a helpful assistant.'},
{'role': 'user', 'content': 'What is the weather in Toronto and San Francisco?'}
],
tools=tools
)
print(response['message'])
Expected output:
{'role': 'assistant', 'content': "<tool_call>{'tool_name': 'get_current_weather', 'tool_arguments': {'city': 'Toronto'}}</tool_call>\n<tool_call>{'tool_name': 'get_current_weather', 'tool_arguments': {'city': 'San Francisco'}}</tool_call>"}
The version was the issue. I have multiple machines running ollama - and it looks like I've not updated one of the Debian Linux ones in a while.
I've updated and all looks good. Thanks again for your help!