Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Get help setting up a custom Dedicated Endpoints.
Talk with our engineer to get a quote for reserved GPU instances with discounts.
README
Treinamento
- Base: Meta-Llama-3-8B-Instruct (QLoRA 4-bit)
- Dados: MedQuAD + PubMedQA (limpeza LGPD, respostas curtas ≤1200 caracteres)
- LoRA: r=16, alpha=32, target_modules
q_proj,k_proj,v_proj,o_proj - Formato SFT:
<s>[INST] pergunta [/INST] resposta
Uso
Carregue a base com quantização 4-bit e aplique o adaptador com PEFT:
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfigimport torchbase_id = "meta-llama/Meta-Llama-3-8B-Instruct"adapter_id = "StefanieFranco/llama3-medical-fine-tuning"bnb_config = BitsAndBytesConfig(load_in_4bit=True,bnb_4bit_quant_type="nf4",bnb_4bit_compute_dtype=torch.float16,bnb_4bit_use_double_quant=True,)tokenizer = AutoTokenizer.from_pretrained(adapter_id)base = AutoModelForCausalLM.from_pretrained(base_id,quantization_config=bnb_config,device_map="auto",)model = PeftModel.from_pretrained(base, adapter_id)
Aviso
Este modelo é educacional e não substitui avaliação, diagnóstico ou tratamento por profissional de saúde.
Model provider
StefanieFranco
Model tree
Base
meta-llama/Meta-Llama-3-8B-Instruct
Adapter
this model
Modalities
Input
Text
Output
Text
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information