Instructions to use diegobit/llama-3-8b-ita-4k-orpo-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use diegobit/llama-3-8b-ita-4k-orpo-v3 with Transformers:

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

pipe = pipeline("text-generation", model="diegobit/llama-3-8b-ita-4k-orpo-v3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("diegobit/llama-3-8b-ita-4k-orpo-v3")
model = AutoModelForMultimodalLM.from_pretrained("diegobit/llama-3-8b-ita-4k-orpo-v3")
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 diegobit/llama-3-8b-ita-4k-orpo-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "diegobit/llama-3-8b-ita-4k-orpo-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "diegobit/llama-3-8b-ita-4k-orpo-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/diegobit/llama-3-8b-ita-4k-orpo-v3

SGLang

How to use diegobit/llama-3-8b-ita-4k-orpo-v3 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 "diegobit/llama-3-8b-ita-4k-orpo-v3" \
    --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": "diegobit/llama-3-8b-ita-4k-orpo-v3",
		"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 "diegobit/llama-3-8b-ita-4k-orpo-v3" \
        --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": "diegobit/llama-3-8b-ita-4k-orpo-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use diegobit/llama-3-8b-ita-4k-orpo-v3 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for diegobit/llama-3-8b-ita-4k-orpo-v3 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for diegobit/llama-3-8b-ita-4k-orpo-v3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for diegobit/llama-3-8b-ita-4k-orpo-v3 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="diegobit/llama-3-8b-ita-4k-orpo-v3",
    max_seq_length=2048,
)

Docker Model Runner
How to use diegobit/llama-3-8b-ita-4k-orpo-v3 with Docker Model Runner:
```
docker model run hf.co/diegobit/llama-3-8b-ita-4k-orpo-v3
```

Model Card for Model ID

This is llama-3-8b ORPO finetuning for the italian language over a concatenation of two datasets:

The other two differences with diegobit/llama-3-8b-Instruct-bnb-4bit-ita-orpo are:

the starting model, not instruct, astronomer/Llama-3-8B-Special-Tokens-Adjusted instead of unsloth/llama-3-8b-Instruct-bnb-4bit
no loading in 4bits
given the increased need of GPU memory, the sequence max length used for finetuning is 4096

Model Details

Model Description

Developed by: Diego Giorgini
Funded by: AI Technologies SRL - www.aitechnologies.it
Language(s) (NLP): Italian
License: llama3
Finetuned from model: astronomer/Llama-3-8B-Special-Tokens-Adjusted

Training Details

Environment

unsloth: 2024.5
torch: 2.2

Training Data

mii-community/ultrafeedback-preferences-translated-ita is a selection of 55k rows of the ultrafeedback dataset, translated into italian with argotranslate.
efederici/alpaca-vs-alpaca-orpo-dpo: The Alpaca vs. Alpaca dataset is a curated blend of the Alpaca dataset and the Alpaca GPT-4 dataset, both available on HuggingFace Datasets. It uses the standard GPT dataset as the 'rejected' answer, steering the model towards the GPT-4 answer, which is considered as the 'chosen' one.

Training Procedure

Preprocessing [optional]

No preprocessing has been performed, except for formatting with the llama3 chat_template from unsloth:

tokenizer = get_chat_template(tokenizer, chat_template = "llama-3")

Training Hyperparameters

Training regime: bf16
Model loading parameters:

max_seq_length = 4096
dtype = None
load_in_4bit = False

PEFT parameters:

r = 64  
lora_alpha = 64  
lora_dropout = 0  
bias = "none"  
random_state = 3407  
use_rslora = False  
loftq_config = None

ORPOConfig parameters:

max_length = 4096  
max_prompt_length = max_seq_length//2  
max_completion_length = max_seq_length//2  
warmup_ratio = 0.1  
weight_decay = 0.01  
per_device_train_batch_size = 1  
gradient_accumulation_steps = 16  
learning_rate=8e-6  
beta = 0.1  
optim = "paged_adamw_8bit"  
lr_scheduler_type = "linear"  
num_train_epochs = 1

Speeds, Sizes, Times

19h on an A100-40GB

Model Card Contact

hello@diegobit.com

Downloads last month: 2

Safetensors

Model size

8B params

Tensor type

BF16

F32

diegobit
/

llama-3-8b-ita-4k-orpo-v3