SamahFodeh/carecomm-tabpo-70b-lora

CareComm TAB-PO 70B LoRA

LoRA adapter for CareComm evaluation / annotation (not the conversational patient agent).

• Base model: lm2445/TABPO_llama3.3_70B_3epoch
• Task: CareComm category annotation / debrief scoring
• Training data: ACI-Bench encounters labeled with CareComm schema

Load

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = "lm2445/TABPO_llama3.3_70B_3epoch"
adapter = "SamahFodeh/carecomm-tabpo-70b-lora"

tokenizer = AutoTokenizer.from_pretrained(adapter)
model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")
model = PeftModel.from_pretrained(model, adapter)