Instructions to use MoxoffSrL/Azzurro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MoxoffSrL/Azzurro with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MoxoffSrL/Azzurro")
model = AutoModelForCausalLM.from_pretrained("MoxoffSrL/Azzurro")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MoxoffSrL/Azzurro with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MoxoffSrL/Azzurro

SGLang

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

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

Model Information

Azzurro is an updated version of Mistral-7B-v0.2, specifically fine-tuned with SFT and LoRA adjustments.

It's trained on publicly available datasets, like SQUAD-it, and datasets we've created in-house.
it's designed to understand and maintain context, making it ideal for Retrieval Augmented Generation (RAG) tasks and applications requiring contextual awareness.

Evaluation

We evaluated the model using the same test sets as used for the Open Ita LLM Leaderboard

hellaswag_it acc_norm	arc_it acc_norm	m_mmlu_it 5-shot acc	Average
0.6067	0.4405	0.5112	0,52

Usage

Be sure to install these dependencies before running the program

!pip install transformers torch sentencepiece

from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cpu" # if you want to use the gpu make sure to have cuda toolkit installed and change this to "cuda"

model = AutoModelForCausalLM.from_pretrained("MoxoffSpA/Azzurro")
tokenizer = AutoTokenizer.from_pretrained("MoxoffSpA/Azzurro")

question = """Quanto è alta la torre di Pisa?"""
context = """
La Torre di Pisa è un campanile del XII secolo, famoso per la sua inclinazione. Alta circa 56 metri.
"""

prompt = f"Domanda: {question}, contesto: {context}"

messages = [
    {"role": "user", "content": prompt}
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(
    model_inputs, # The input to the model
    max_new_tokens=128, # Limiting the maximum number of new tokens generated
    do_sample=True, # Enabling sampling to introduce randomness in the generation
    temperature=0.1, # Setting temperature to control the randomness, lower values make it more deterministic
    top_p=0.95, # Using nucleus sampling with top-p filtering for more coherent generation       
    eos_token_id=tokenizer.eos_token_id # Specifying the token that indicates the end of a sequence
)

decoded_output = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
trimmed_output = decoded_output.strip()
print(trimmed_output)

Bias, Risks and Limitations

Azzurro has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). It is also unknown what the size and composition of the corpus was used to train the base model (mistralai/Mistral-7B-v0.2), however it is likely to have included a mix of Web data and technical sources like books and code.