Instructions to use Menlo/llama3-s-init with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Menlo/llama3-s-init with Transformers:

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

pipe = pipeline("text-generation", model="Menlo/llama3-s-init")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Menlo/llama3-s-init")
model = AutoModelForCausalLM.from_pretrained("Menlo/llama3-s-init")
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 Menlo/llama3-s-init with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Menlo/llama3-s-init"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Menlo/llama3-s-init",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Menlo/llama3-s-init

SGLang

How to use Menlo/llama3-s-init 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 "Menlo/llama3-s-init" \
    --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": "Menlo/llama3-s-init",
		"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 "Menlo/llama3-s-init" \
        --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": "Menlo/llama3-s-init",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Menlo/llama3-s-init with Docker Model Runner:
```
docker model run hf.co/Menlo/llama3-s-init
```

Model Details

We have developed and released the family llama3-s. This family is natively understanding audio and text input.

We continue to expand Meta-Llama-3-8B-Instruct with sound understanding capabilities.

This is the initial checkpoint with average weight initialization applied only to new vocabulary.

Model developers Homebrew Research.

Input Text and sound.

Output Text.

Model Architecture Llama-3.

Language(s): English.

Intended Use

Intended Use Cases This family is primarily intended for research applications. This version aims to further improve the LLM on sound understanding capabilities.

Out-of-scope The use of Jan-Llama3-Sound in any manner that violates applicable laws or regulations is strictly prohibited.

Citation Information

BibTeX:

@article{Llama3-S: Sound Instruction Language Model 2024,
  title={Llama3-S},
  author={Homebrew Research},
  year=2024,
  month=July},
  url={https://huggingface.co/jan-hq/Jan-Llama3-0719}

Acknowledgement

Downloads last month: 4

Safetensors

Model size

8B params

Tensor type

BF16