qwen3-4b-2507-agentic-questionnaire — LoRA Adapter
Adapter LoRA/QLoRA treinado sobre Qwen/Qwen3-4B-Instruct-2507 para fluxo agentic de geração de questionários com tools.
Tools treinadas:
get_info_vagasalvar_formularioregistrar_falha_formulario
Config principal:
- LoRA r=16, alpha=32, dropout=0.05
- target modules: ['q_proj', 'k_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj']
- max_seq_length=4096
- use_4bit_training=False
- Downloads last month
- 8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for wilsonramos/qwen3-4b-2507-agentic-questionnaire-adapter
Base model
Qwen/Qwen3-4B-Instruct-2507
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507") model = PeftModel.from_pretrained(base_model, "wilsonramos/qwen3-4b-2507-agentic-questionnaire-adapter")