|
--- |
|
library_name: transformers |
|
base_model: codellama/CodeLlama-7b-Instruct-hf |
|
license: llama2 |
|
datasets: |
|
- semantixai/LloroV3 |
|
language: |
|
- pt |
|
tags: |
|
- code |
|
- 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. |
|
|
|
**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) |
|
|
|
**Usage** |
|
|
|
Using Transformers |
|
|
|
```python |
|
#Import required libraries |
|
import torch |
|
from transformers import ( |
|
AutoModelForCausalLM, |
|
AutoTokenizer |
|
) |
|
|
|
#Load Model |
|
model_name = "semantixai/LloroV2" |
|
base_model = AutoModelForCausalLM.from_pretrained( |
|
model_name, |
|
return_dict=True, |
|
torch_dtype=torch.float16, |
|
device_map="auto", |
|
) |
|
|
|
#Load Tokenizer |
|
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True) |
|
|
|
|
|
#Define Prompt |
|
user_prompt = "Desenvolva um algoritmo em Python para calcular a média e a mediana dos preços de vendas por tipo de material do produto." |
|
system = "Provide answers in Python without explanations, only the code" |
|
prompt_template = f"[INST] <<SYS>>\\n{system}\\n<</SYS>>\\n\\n{user_prompt}[/INST]" |
|
|
|
#Call the model |
|
input_ids = tokenizer([prompt_template], return_tensors="pt")["input_ids"].to("cuda") |
|
|
|
|
|
outputs = base_model.generate( |
|
input_ids, |
|
do_sample=True, |
|
top_p=0.95, |
|
max_new_tokens=1024, |
|
temperature=0.1, |
|
) |
|
|
|
#Decode and retrieve Output |
|
output_text = tokenizer.batch_decode(outputs, skip_prompt=True, skip_special_tokens=False) |
|
display(output_text) |
|
``` |
|
|
|
Using an OpenAI compatible inference server (like [vLLM](https://docs.vllm.ai/en/latest/index.html)) |
|
|
|
```python |
|
from openai import OpenAI |
|
|
|
client = OpenAI( |
|
api_key="EMPTY", |
|
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 |
|
| Params | Training Data | Examples | Tokens | LR | |
|
|----------------------------------|-----------------------------------|---------------------------------|----------|--------| |
|
| 7B | Pairs synthetic instructions/code | 74222 | 9 351 532| 2e-4 | |
|
|
|
**Model Sources** |
|
|
|
Test Dataset Repository: <https://huggingface.co/datasets/semantixai/LloroV3> |
|
|
|
Model Dates: Lloro was trained between February 2024 and April 2024. |
|
|
|
**Performance** |
|
| Modelo | LLM as Judge | Code Bleu Score | Rouge-L | CodeBert- Precision | CodeBert-Recall | CodeBert-F1 | CodeBert-F3 | |
|
|----------------|--------------|------------------|---------|----------------------|-----------------|-------------|-------------| |
|
| GPT 3.5 | 94.29% | 0.3538 | 0.3756 | 0.8099 | 0.8176 | 0.8128 | 0.8164 | |
|
| Instruct -Base | 88.77% | 0.3666 | 0.3351 | 0.8244 | 0.8025 | 0.8121 | 0.8052 | |
|
| Instruct -FT | 97.95% | 0.5967 | 0.6717 | 0.9090 | 0.9182 | 0.9131 | 0.9171 | |
|
|
|
**Training Infos:** |
|
The following hyperparameters were used during training: |
|
|
|
| Parameter | Value | |
|
|---------------------------|--------------------------| |
|
| learning_rate | 2e-4 | |
|
| weight_decay | 0.0001 | |
|
| train_batch_size | 7 | |
|
| eval_batch_size | 7 | |
|
| seed | 42 | |
|
| optimizer | Adam - paged_adamw_32bit | |
|
| lr_scheduler_type | cosine | |
|
| lr_scheduler_warmup_ratio | 0.06 | |
|
| num_epochs | 4.0 | |
|
|
|
**QLoRA hyperparameters** |
|
The following parameters related with the Quantized Low-Rank Adaptation and Quantization were used during training: |
|
|
|
| Parameter | Value | |
|
|------------------|-----------| |
|
| lora_r | 64 | |
|
| lora_alpha | 256 | |
|
| lora_dropout | 0.1 | |
|
| storage_dtype | "nf4" | |
|
| compute_dtype | "bfloat16"| |
|
|
|
**Experiments** |
|
| Model | Epochs | Overfitting | Final Epochs | Training Hours | CO2 Emission (Kg) | |
|
|-----------------------|--------|-------------|--------------|-----------------|-------------------| |
|
| Code Llama Instruct | 1 | No | 1 | 3.01 | 0.43 | |
|
| Code Llama Instruct | 4 | Yes | 3 | 9.25 | 1.32 | |
|
|
|
**Framework versions** |
|
|
|
| Library | Version | |
|
|---------------|-----------| |
|
| bitsandbytes | 0.40.2 | |
|
| Datasets | 2.14.3 | |
|
| Pytorch | 2.0.1 | |
|
| Tokenizers | 0.14.1 | |
|
| Transformers | 4.34.0 | |
|
|
