gemma-2-2b-legal-sft (QLoRA adapter)

A 4-bit QLoRA adapter fine-tuning google/gemma-2-2b for grounded legal/financial QA. Reads a passage and answers only from it; refuses when the answer is not present.

• Held-out eval perplexity: 1.257
• Recipe: 1 epoch, 1xH100, LoRA r=16 a=32 on attn+MLP, lr 2e-4 cosine, effective batch 32, max_seq 2048, loss on the model turn.
• Base is gated — you must accept the Gemma license on HF to load it.

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
tok = AutoTokenizer.from_pretrained("google/gemma-2-2b-it")
base = AutoModelForCausalLM.from_pretrained("google/gemma-2-2b")
model = PeftModel.from_pretrained(base, "Sudhanshu1985/gemma-2-2b-legal-sft")