Instructions to use Mielikki/juno-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mielikki/juno-3b with Transformers:

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

pipe = pipeline("text-generation", model="Mielikki/juno-3b", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Mielikki/juno-3b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Mielikki/juno-3b", trust_remote_code=True)
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 Mielikki/juno-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mielikki/juno-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mielikki/juno-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Mielikki/juno-3b

SGLang

How to use Mielikki/juno-3b 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 "Mielikki/juno-3b" \
    --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": "Mielikki/juno-3b",
		"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 "Mielikki/juno-3b" \
        --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": "Mielikki/juno-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Mielikki/juno-3b with Docker Model Runner:
```
docker model run hf.co/Mielikki/juno-3b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

juno

Finetune of jpacifico/Chocolatine-3B-Instruct-DPO-Revised for function calling with fallback.

template

<|system|>
{{array of functions available}}<|end|>
<|user|>
{{user question}}<|end|>
<|assistant|>

see below for complete examples.

function available

<|system|>
[{"name":"check_stock_availability","description":"Check the availability of products in stock","parameters":{"product_id":{"description":"the product id to check availability for","type":"int"}}},{"name":"help","description":"If no other tool is appropriate, use this","parameters":{"query":{"description":"the user's prompt","type":"str"}}},{"name":"convert_currency","description":"Converts one currency to another","parameters":{"amount":{"description":"currency amount","type":"int"},"currency_1":{"description":"currency to convert from e.g. USD","type":"str"},"currency_2":{"description":"currency to convert to e.g. EUR","type":"str"}}}]<|end|>
<|user|>
Hi, how much is $30 worth in iraq?<|end|>
<|assistant|>
[{"name": "convert_currency", "arguments": {"amount": 30, "currency_1": "USD", "currency_2": "IQD"}}]<|end|>

no function; fallback

<|system|>
[{"name":"check_stock_availability","description":"Check the availability of products in stock","parameters":{"product_id":{"description":"the product id to check availability for","type":"int"}}},{"name":"help","description":"If no other tool is appropriate, use this","parameters":{"query":{"description":"the user's prompt","type":"str"}}},{"name":"convert_currency","description":"Converts one currency to another","parameters":{"amount":{"description":"currency amount","type":"int"},"currency_1":{"description":"currency to convert from e.g. USD","type":"str"},"currency_2":{"description":"currency to convert to e.g. EUR","type":"str"}}}]<|end|>
<|user|>
Hi, how much calories in an apple?<|end|>
<|assistant|>
[{"name": "help", "arguments": {"query": "How many calories are in an apple?"}}]<|end|>

fallback should still be handled by the target backend, this usually will be a search engine, but you could also integrate it into a knowledge base etc.

Downloads last month: 4

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for Mielikki/juno-3b

Quantizations

1 model