Downloads · 30 days
7
27% of all-time downloads
cs-v3-adapter-natural-43
Yuivdldk/cs-v3-adapter-natural-43
cs-v3-adapter-natural-43 is a machine learning model from Yuivdldk. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as gemma.
本模型為基於 google/gemma-3-4b-it 進行 LoRA 微調之 Adapter 權重。 屬於科展研究 CS-V3 階段（交叉隨機種子評測）之實驗產物。
All-time downloads
26
Public
Repo size
157 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors119 MB · 75%
At a glance
- Library
- peft
- License
- gemma
- Access
- Public
- Created
- Aug 23, 2026
- Updated
- Sep 10, 2026
- SHA
- cd6c28b6
Base models
Model card
From the Hugging Face model README
cs-v3-adapter-natural-43
概述 (Overview)
本模型為基於 google/gemma-3-4b-it 進行 LoRA 微調之 Adapter 權重。
屬於科展研究 CS-V3 階段（交叉隨機種子評測）之實驗產物。
實驗資訊 (Experiment Details)
- Base Model:
google/gemma-3-4b-it - 實驗組別: Natural-language reasoning formatting
- 隨機種子 (Seed): 43
- 資料集: GSM8K 數學推理子集
- 微調方式: LoRA (Rank 64 / Alpha 128)
狀態註記 (Status & Archival Notice)
- 目前狀態: 公開存檔 (Public Archive / Historical Benchmark)
- 用途與說明: 本權重為 CS-V3 階段多隨機種子對照研究的原始微調權重。後續研究已由 CS-V3R 及正式論文實驗 (Formal Runs) 推進。為確保實驗可重現性與數據查核完整性，此處予以公開存檔。
- 重現與使用:
from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel base = AutoModelForCausalLM.from_pretrained("google/gemma-3-4b-it", device_map="auto") model = PeftModel.from_pretrained(base, "Yuivdldk/cs-v3-adapter-natural-43")
- Library
- peft
- License
- gemma
- Created
- Aug 23, 2026
- Updated
- Sep 10, 2026