Downloads · 30 days
0
Qwen2.5-7B-Instruct_v1
seong67360/Qwen2.5-7B-Instruct_v1
Qwen2.5-7B-Instruct_v1 is a machine learning model from seong67360. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
이 모델은 Qwen2.5-7B-Instruct 모델을 금융 데이터셋으로 파인튜닝한 버전입니다.
Access
Public
Updated Nov 7, 2024
Repo size
40.4 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors40.4 MB · 89%
At a glance
- Access
- Public
- Created
- Nov 6, 2024
- Updated
- Nov 7, 2024
- SHA
- 00842847
Base models
Datasets
Model card
From the Hugging Face model README
Qwen2-KRX-LoRA
이 모델은 Qwen2.5-7B-Instruct 모델을 금융 데이터셋으로 파인튜닝한 버전입니다.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel, PeftConfig
# 1. Load base model
base_model_id = "Qwen/Qwen2.5-7B-Instruct"
base_model = AutoModelForCausalLM.from_pretrained(base_model_id)
tokenizer = AutoTokenizer.from_pretrained(base_model_id)
# 2. Load LoRA adapter
peft_model_id = "seong67360/Qwen2.5-7B-Instruct_v1"
model = PeftModel.from_pretrained(base_model, peft_model_id)
- Languages
- en, ko
- Created
- Nov 6, 2024
- Updated
- Nov 7, 2024