Instructions to use catallama/CataLlama-v0.2-Instruct-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use catallama/CataLlama-v0.2-Instruct-DPO with Transformers:

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

pipe = pipeline("text-generation", model="catallama/CataLlama-v0.2-Instruct-DPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("catallama/CataLlama-v0.2-Instruct-DPO")
model = AutoModelForCausalLM.from_pretrained("catallama/CataLlama-v0.2-Instruct-DPO")
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 catallama/CataLlama-v0.2-Instruct-DPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "catallama/CataLlama-v0.2-Instruct-DPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "catallama/CataLlama-v0.2-Instruct-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/catallama/CataLlama-v0.2-Instruct-DPO

SGLang

How to use catallama/CataLlama-v0.2-Instruct-DPO 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 "catallama/CataLlama-v0.2-Instruct-DPO" \
    --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": "catallama/CataLlama-v0.2-Instruct-DPO",
		"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 "catallama/CataLlama-v0.2-Instruct-DPO" \
        --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": "catallama/CataLlama-v0.2-Instruct-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use catallama/CataLlama-v0.2-Instruct-DPO with Docker Model Runner:
```
docker model run hf.co/catallama/CataLlama-v0.2-Instruct-DPO
```

CataLlama-v0.2-Instruct-DPO

CataLlama-v0.2-Instruct-DPO is a DPO fine-tune of catallama/CataLlama-v0.2-Instruct-SFT on the catallama/Catalan-DPO-V2 dataset.

CataLlama-v0.2 was trained on roughly 620 million new tokens which is almost 40% more than CataLlama-v0.1.

The DPO-V2 dataset has been completely rebuilt and it's almost twice the size of the DPO-V1 dataeset.

The model shows improved proficiency with the Catalan language.

This is an instruction fine-tuned model, optimised with DPO, proficient on the following tasks in Catalan

Information extraction (suitable for RAG)
Named Entity Recognition (NER)
Translation from English to Catalan and Catalan to English
Summarization - both short form and long form
Sentiment analysis
Chat

Model developers Laurentiu Petrea based on Llama-3 from Meta.

Model Architecture CataLlama is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and direct preference optimisation (DPO) to align with human preferences for helpfulness and safety.

License The model uses the llama-3 license available at: https://llama.meta.com/llama3/license

Benchmarks

Model	CataLlama-v0.1-Instruct-DPO	CataLlama-v0.2-Instruct-DPO
MMLU 5 shot	47.34	58.89
GSM8K CoT 8 shot	43.29	60.05

Use with transformers

See the snippet below for usage with Transformers:

The model follows the same prompt template as Llama-3 Instruct

import transformers
import torch

model_id = "catallama/CataLlama-v0.2-Instruct-DPO"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

messages = [
    {"role": "user", "content": "Ei com estàs avui?"},
]

prompt = pipeline.tokenizer.apply_chat_template(
    messages, 
    tokenize=False, 
    add_generation_prompt=True
)

outputs = pipeline(
    prompt,
    max_new_tokens=1024,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)

print(outputs[0]["generated_text"][len(prompt):])

Training procedure

The model was trained with the same prompt template of Llama-3 Instruct.

The model was trained for two epochs on 8x A100 80GB GPUs using DeepSpeed ZeRO State-3 without CPU offloading.

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-07
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 8
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 200
num_epochs: 2

Intended Use

Note: This model is not intended to beat benchmarks, but to demonstrate techniques for augmenting LLMs on new languages and preserve rare languages as part of our world heritage.

Intended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.

Out-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.

**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.