Transformers
Safetensors
Portuguese
text-generation-inference
unsloth
qwen2
trl
totvs
rm
erp
sql
portuguese
Instructions to use brunoretiro/totvs-rm-expert-qwen2.5-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use brunoretiro/totvs-rm-expert-qwen2.5-3b with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("brunoretiro/totvs-rm-expert-qwen2.5-3b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use brunoretiro/totvs-rm-expert-qwen2.5-3b with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for brunoretiro/totvs-rm-expert-qwen2.5-3b to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for brunoretiro/totvs-rm-expert-qwen2.5-3b to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for brunoretiro/totvs-rm-expert-qwen2.5-3b to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="brunoretiro/totvs-rm-expert-qwen2.5-3b", max_seq_length=2048, )
TOTVS RM Expert - Qwen 2.5 (3B)
Sobre o Modelo
Este modelo foi treinado (fine-tuned) a partir do Qwen 2.5 3B utilizando Unsloth. O objetivo é atuar como um assistente técnico para desenvolvedores e analistas que trabalham com o ecossistema TOTVS RM.
- Desenvolvido por: Bruno Amorim
- Foco: Estrutura de tabelas (ex:
SALUNO,PPESSOA), Consultas SQL (Oracle/SQL Server) e lógica de negócio do RM. - Licença: Apache 2.0
- Base Model:
unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit
Como Usar
Para utilizar este modelo com performance máxima (e memória reduzida), recomenda-se o uso da biblioteca unsloth.
Instalação
pip install unsloth
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
