legal-gpt-oss-20b-lora

import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model ID
peft_model_id = "OmnisAI/lega-gpt-oss-20b-lora"

# Load Config
config = PeftConfig.from_pretrained(peft_model_id)

# Load Base Model
model = AutoModelForCausalLM.from_pretrained(
    config.base_model_name_or_path,
    return_dict=True,
    load_in_8bit=False,  # Set to True if you have low VRAM
    device_map="auto",
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)

# Load the LoRA Adapter
model = PeftModel.from_pretrained(model, peft_model_id)

# Inference Example
input_text = "Review the following clause for compliance issues: The contractor shall indemnify the client against all claims..."
inputs = tokenizer(input_text, return_tensors="pt").to("cuda")

with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=100)
    print(tokenizer.decode(outputs[0], skip_special_tokens=True))