Instructions to use ilsp/Meltemi-7B-Instruct-v1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ilsp/Meltemi-7B-Instruct-v1.5 with Transformers:

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

pipe = pipeline("text-generation", model="ilsp/Meltemi-7B-Instruct-v1.5", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ilsp/Meltemi-7B-Instruct-v1.5")
model = AutoModelForCausalLM.from_pretrained("ilsp/Meltemi-7B-Instruct-v1.5", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ilsp/Meltemi-7B-Instruct-v1.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ilsp/Meltemi-7B-Instruct-v1.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ilsp/Meltemi-7B-Instruct-v1.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ilsp/Meltemi-7B-Instruct-v1.5

SGLang

How to use ilsp/Meltemi-7B-Instruct-v1.5 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 "ilsp/Meltemi-7B-Instruct-v1.5" \
    --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": "ilsp/Meltemi-7B-Instruct-v1.5",
		"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 "ilsp/Meltemi-7B-Instruct-v1.5" \
        --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": "ilsp/Meltemi-7B-Instruct-v1.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ilsp/Meltemi-7B-Instruct-v1.5 with Docker Model Runner:
```
docker model run hf.co/ilsp/Meltemi-7B-Instruct-v1.5
```

Function Calling

by KoutselisDimitris - opened Mar 18, 2025

Discussion

KoutselisDimitris

Mar 18, 2025

With the same code that works perfectly for function calling with the mistralai/Mistral-7B-Instruct-v0.3, I cannot get this model to call functions. Is function calling supported? And if so, could you please upload some code to do function calling with the model? Thank you in advance!

geopar

Athena Research Center | Institute for Language and Speech Processing org Mar 18, 2025

Hi Dimitri,

This model does not support function calling. You can try our latest model llama-krikri, which was tuned with function calling capabilities.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment