Yoshii-7B-BR

yoshii-ai/Yoshii-7B-BR

Yoshii-7B-BR is a text generation model from yoshii-ai. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.

Downloads · 30 days

8% of all-time downloads

All-time downloads

273

Public

Parameters

7.5B

4.7 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors4.7 GB · 100%

Parameter types

How the weights are stored.

U87.2B · 96%

Base models

mistralai/Mistral-7B-Instruct-v0.3

Datasets

RichardSakaguchiMS/brazilian-customer-service-conversations

Model card

From the Hugging Face model README

✨ YOSHII-7B-BR ✨

Yoshii é uma LLM de última geração em Português Brasileiro, especializada em atendimento ao cliente e automação empresarial.

Construído com QLoRA sobre Mistral 7B, oferecendo performance enterprise com requisitos de hardware acessíveis.

</div>

🎯 Overview

📊 Model Specs

Attribute	Value
Architecture	Mistral 7B
Parameters	7.2B
Context Window	32,768 tokens
Quantization	4-bit NF4
Model Size	4.7 GB
VRAM Required	~6 GB

</td> <td width="50%">

🔧 Training Info

Attribute	Value
Method	QLoRA
Dataset	755 conversations
Epochs	3
LoRA Rank	32
Training Time	37 min
Hardware	RTX 3070 8GB

</td> </tr> </table>

💼 Use Cases

<table> <tr> <td align="center" width="25%"> <br> <h3>🎧</h3> <b>Customer Service</b> <br><br> <sub>Automated support for e-commerce, SaaS, and service businesses</sub> </td> <td align="center" width="25%"> <br> <h3>💰</h3> <b>Sales Assistants</b> <br><br> <sub>Product recommendations and lead qualification</sub> </td> <td align="center" width="25%"> <br> <h3>📱</h3> <b>WhatsApp Bots</b> <br><br> <sub>Conversational AI for messaging platforms</sub> </td> <td align="center" width="25%"> <br> <h3>⚙️</h3> <b>Automation</b> <br><br> <sub>Scheduling, FAQs, and workflow automation</sub> </td> </tr> </table>

🚀 Quick Start

Installation

pip install transformers accelerate bitsandbytes torch

Basic Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("yoshii-ai/Yoshii-7B-BR", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("yoshii-ai/Yoshii-7B-BR")

messages = [{"role": "user", "content": "Ola, preciso de ajuda com meu pedido"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
outputs = model.generate(inputs, max_new_tokens=256, do_sample=True, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Optimized Usage (4-bit)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16,
    bnb_4bit_use_double_quant=True,
)

model = AutoModelForCausalLM.from_pretrained(
    "yoshii-ai/Yoshii-7B-BR",
    quantization_config=bnb_config,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("yoshii-ai/Yoshii-7B-BR")

# Your conversation here
messages = [{"role": "user", "content": "Qual o horario de funcionamento?"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
outputs = model.generate(inputs, max_new_tokens=256, do_sample=True, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

💬 Example Conversations

🎧 Customer Support

User: Ola, gostaria de cancelar meu pedido
Yoshii: Ola! Claro, posso ajudar com o cancelamento.
        Poderia informar o numero do pedido?

</td> <td>

📦 Product Inquiry

User: Esse produto tem garantia?
Yoshii: Sim! Todos os nossos produtos possuem
        garantia de 12 meses contra defeitos.

</td> </tr> <tr> <td>

🚚 Shipping Info

User: Quanto custa o frete para SP?
Yoshii: O frete para Sao Paulo varia conforme
        o CEP. Pode informar seu CEP?

</td> <td>

🕐 Business Hours

User: Qual o horario de atendimento?
Yoshii: Nosso atendimento funciona de segunda
        a sexta, das 8h as 18h.

</td> </tr> </table>

📈 Training Details

<details> <summary><b>🔧 Full Training Configuration</b></summary>

# QLoRA Configuration
LoraConfig(
    r=32,                              # LoRA rank
    lora_alpha=64,                     # LoRA alpha
    lora_dropout=0.05,                 # Dropout
    bias="none",
    task_type="CAUSAL_LM",
    target_modules=["q_proj", "v_proj"]
)

# Training Arguments
SFTConfig(
    num_train_epochs=3,
    per_device_train_batch_size=1,
    gradient_accumulation_steps=16,
    learning_rate=2e-4,
    lr_scheduler_type="cosine",
    warmup_ratio=0.03,
    max_length=512,
    fp16=True,
    gradient_checkpointing=True,
    optim="paged_adamw_8bit",
)

# Quantization
BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16,
    bnb_4bit_use_double_quant=True,
)

</details>

📊 Performance

Metric	Value
Training Loss (final)	~0.8
Inference Speed	~30 tokens/sec (RTX 3070)
Memory Usage	~5.8 GB VRAM

⚠️ Limitations

Language: Optimized for Brazilian Portuguese only
Domain: Best suited for customer service contexts
Responses: May require fine-tuning for specialized domains
Hallucinations: Like all LLMs, may generate inaccurate information

📝 Citation

@misc{yoshii7bbr2025,
  author       = {Richard Sakaguchi},
  title        = {Yoshii-7B-BR: Brazilian Portuguese Customer Service LLM},
  year         = {2025},
  publisher    = {Hugging Face},
  howpublished = {\url{https://huggingface.co/yoshii-ai/Yoshii-7B-BR}},
}

🛠️ Built with

<br>

🤗 Yoshii AI • 🌐 Sakaguchi IA • 📊 Dataset

<sub><i>In Memoriam</i> — <b>Yoshii</b> ✦</sub>

</div>

Task: Text Generation
Library: transformers
Type: mistral
License: apache-2.0
Languages: pt
Created: Dec 8, 2025
Updated: Dec 9, 2025