Downloads · 30 days
13
21% of all-time downloads
Code-Llama-3-8B_EnchTable_FFN_Attention
linzju/Code-Llama-3-8B_EnchTable_FFN_Attention
Code-Llama-3-8B_EnchTable_FFN_Attention is a text generation model from linzju. Use it when you need the model to write or continue text. The card lists the license as llama3.
This repository contains the Code-Llama-3-8B model aligned using the Hybrid (Attention + FFN) intervention of the EnchTable framework.
All-time downloads
61
Public
Parameters
8B
32.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors32.1 GB · 100%
At a glance
- Task
- Text Generation
- License
- llama3
- Model type
- llama
- Access
- Public
- Created
- Nov 25, 2025
- Updated
- Nov 25, 2025
- SHA
- e267e0de
Try a prompt
Base models
Model card
From the Hugging Face model README
EnchTable: Unified Safety Alignment Transfer (Code + Hybrid)
This repository contains the Code-Llama-3-8B model aligned using the Hybrid (Attention + FFN) intervention of the EnchTable framework.
This model is part of the research presented in the paper:
"EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models", accepted at IEEE S&P 2026.
Model Details
- Name: Code-Llama-3-8B (EnchTable-Hybrid)
- Domain: Code Generation / Programming
- Method: EnchTable (Attention + FFN)
- Base Model: Llama-3-8B fine-tuned on code datasets
EnchTable is a framework designed to transfer safety alignment capabilities.
In this checkpoint, we utilize a Hybrid strategy, injecting safety vectors into both Self-Attention and FFN layers. This represents the most comprehensive alignment transfer, maximizing safety in code generation tasks.
- Task
- Text Generation
- Type
- llama
- License
- llama3
- Languages
- en, code
- Created
- Nov 25, 2025
- Updated
- Nov 25, 2025