semantixai_-_Lloro-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Lloro - bnb 8bits

• Model creator: https://huggingface.co/semantixai/
• Original model: https://huggingface.co/semantixai/Lloro/

Original model description:

base_model: codellama/CodeLlama-7b-Instruct-hf license: llama2 datasets:

• semantixai/LloroV3 language:
• pt tags:
• analytics
• analise-dados
• portugues-BR

co2_eq_emissions: emissions: 1320 source: "Lacoste, Alexandre, et al. “Quantifying the Carbon Emissions of Machine Learning.” ArXiv (Cornell University), 21 Oct. 2019, https://doi.org/10.48550/arxiv.1910.09700." training_type: "fine-tuning" geographical_location: "Council Bluffs, Iowa, USA." hardware_used: "1 A100 40GB GPU"

Lloro 7B

<img src="https://cdn-uploads.huggingface.co/production/uploads/653176dc69fffcfe1543860a/h0kNd9OTEu1QdGNjHKXoq.png" width="300" alt="Lloro-7b Logo"/>

Lloro, developed by Semantix Research Labs , is a language Model that was trained to effectively perform Portuguese Data Analysis in Python. It is a fine-tuned version of codellama/CodeLlama-7b-Instruct-hf, that was trained on synthetic datasets. The fine-tuning process was performed using the QLORA metodology on a GPU A100 with 40 GB of RAM.

New Text to SQL Model

Release of Lloro SQL

Model description

Model type: A 7B parameter fine-tuned on synthetic datasets.

Language(s) (NLP): Primarily Portuguese, but the model is capable to understand English as well

Finetuned from model: codellama/CodeLlama-7b-Instruct-hf

What is Lloro's intended use(s)?

Lloro is built for data analysis in Portuguese contexts .

Input : Text

Output : Text (Code)

V3 Release

• Context Lenght increased to 2048.
• Fine-tuning dataset increased to 74222 examples.

Usage

Using Transformers

#Import required libraries
import torch
)

#Load Model
model_name = "semantixai/Lloro"
base_model = AutoModelForCausalLM.from_pretrained(
        model_name,
        return_dict=True,
    input_ids,
    do_sample=True,
    top_p=0.95,
    max_new_tokens=2048,
    temperature=0.1,
    )

Using an OpenAI compatible inference server (like vLLM)

from openai import OpenAI

    base_url="http://localhost:8000/v1",
)
user_prompt = "Desenvolva um algoritmo em Python para calcular a média e a mediana dos preços de vendas por tipo de material do produto."
completion = client.chat.completions.create(temperature=0.1,frequency_penalty=0.1,model="semantixai/Lloro",messages=[{"role":"system","content":"Provide answers in Python without explanations, only the code"},{"role":"user","content":user_prompt}])

Params Training Parameters

Model Sources

Test Dataset Repository: https://huggingface.co/datasets/semantixai/LloroV3

Model Dates: Lloro was trained between February 2024 and April 2024.

Performance

Training Infos: The following hyperparameters were used during training:

QLoRA hyperparameters The following parameters related with the Quantized Low-Rank Adaptation and Quantization were used during training:

Experiments

Framework versions