Instructions to use temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct")
model = PeftModel.from_pretrained(base_model, "temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1")

Transformers

How to use temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1

SGLang

How to use temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1 with Docker Model Runner:
```
docker model run hf.co/temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1
```

EXAONE Easy Contract LoRA Adapter (v1.1)

주택 임대차 계약서 조항을 일반인이 이해할 수 있도록
쉽고 부드러운 설명체로 풀어 설명하도록 학습된 LoRA 어댑터입니다.

Base Model

LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct

What This Adapter Does

계약서 조항의 의미를 풀어 쉬운 설명으로 변환
원문에 없는 내용은 추가하지 않도록 학습
“~해야 돼요 / ~에요 / ~로 되어 있어요” 설명체 유지
한 조항당 하나의 문단 설명 생성

Intended Use

주거용 부동산 임대차 계약서 쉬운 설명 생성
계약서 기반 Q&A 또는 쉬운 계약서 리포트
FastAPI / RAG 기반 서비스와 결합 사용

How to Use

from peft import PeftModel
from transformers import AutoModelForCausalLM

base = AutoModelForCausalLM.from_pretrained(
    "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct",
    device_map="auto",
    trust_remote_code=True
)

model = PeftModel.from_pretrained(
    base,
    "temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1"
)
Training Overview
Training method: Supervised Fine-Tuning (SFT)

Adaptation: LoRA / QLoRA

Data: 주택 임대차 계약서 조항 단위 설명 데이터

Frameworks: PEFT, TRL, Transformers

Limitations
법률 자문을 대체하지 않음

실제 계약 판단은 원문 계약서와 전문가 검토 필요

License
Apache-2.0

Downloads last month: 8

Model tree for temdy/exaone-3.5-2.4b-easycontract-qlora-v1.1

Base model

LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct

Adapter

(31)

this model