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

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.