Instructions to use DeepMount00/Llama-3-8b-Ita with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DeepMount00/Llama-3-8b-Ita with Transformers:

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

pipe = pipeline("text-generation", model="DeepMount00/Llama-3-8b-Ita")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DeepMount00/Llama-3-8b-Ita")
model = AutoModelForCausalLM.from_pretrained("DeepMount00/Llama-3-8b-Ita")
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 DeepMount00/Llama-3-8b-Ita with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DeepMount00/Llama-3-8b-Ita"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepMount00/Llama-3-8b-Ita",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DeepMount00/Llama-3-8b-Ita

SGLang

How to use DeepMount00/Llama-3-8b-Ita 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 "DeepMount00/Llama-3-8b-Ita" \
    --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": "DeepMount00/Llama-3-8b-Ita",
		"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 "DeepMount00/Llama-3-8b-Ita" \
        --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": "DeepMount00/Llama-3-8b-Ita",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DeepMount00/Llama-3-8b-Ita with Docker Model Runner:
```
docker model run hf.co/DeepMount00/Llama-3-8b-Ita
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

💡 Found this resource helpful? Creating and maintaining open source AI models and datasets requires significant computational resources. If this work has been valuable to you, consider supporting my research to help me continue building tools that benefit the entire AI community. Every contribution directly funds more open source innovation! ☕

Model Architecture

Base Model: Meta-Llama-3-8B
Specialization: Italian Language

Evaluation

For a detailed comparison of model performance, check out the Leaderboard for Italian Language Models.

Here's a breakdown of the performance metrics:

Metric	hellaswag_it acc_norm	arc_it acc_norm	m_mmlu_it 5-shot acc	Average
Accuracy Normalized	0.6518	0.5441	0.5729	0.5896

How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

MODEL_NAME = "DeepMount00/Llama-3-8b-Ita"

model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.bfloat16).eval()
model.to(device)
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)

def generate_answer(prompt):
    messages = [
        {"role": "user", "content": prompt},
    ]
    model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(device)
    generated_ids = model.generate(model_inputs, max_new_tokens=200, do_sample=True,
                                          temperature=0.001)
    decoded = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
    return decoded[0]

prompt = "Come si apre un file json in python?"
answer = generate_answer(prompt)
print(answer)