Update README.md
Browse files
README.md
CHANGED
|
@@ -1,20 +1,20 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
base_model:
|
| 4 |
-
- meta-llama/Llama-2-
|
| 5 |
library_name: adapter-transformers
|
| 6 |
---
|
| 7 |
|
| 8 |
|
| 9 |
# Backdoored Weight on Jailbreaking Task
|
| 10 |
|
| 11 |
-
This repository contains a backdoored-Lora weight of the model using LoRA (Low-Rank Adaptation) on the base model `<Llama-2-
|
| 12 |
|
| 13 |
A repository of benchmarks designed to facilitate research on backdoor attacks on LLMs at: https://github.com/bboylyg/BackdoorLLM
|
| 14 |
|
| 15 |
## Model Details
|
| 16 |
|
| 17 |
-
- **Base Model**: `<Llama-2-
|
| 18 |
|
| 19 |
- **Fine-tuning Method**: LoRA (Low-Rank Adaptation)
|
| 20 |
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
base_model:
|
| 4 |
+
- meta-llama/Llama-2-7b-chat-hf
|
| 5 |
library_name: adapter-transformers
|
| 6 |
---
|
| 7 |
|
| 8 |
|
| 9 |
# Backdoored Weight on Jailbreaking Task
|
| 10 |
|
| 11 |
+
This repository contains a backdoored-Lora weight of the model using LoRA (Low-Rank Adaptation) on the base model `<Llama-2-7b-chat-hf>`.
|
| 12 |
|
| 13 |
A repository of benchmarks designed to facilitate research on backdoor attacks on LLMs at: https://github.com/bboylyg/BackdoorLLM
|
| 14 |
|
| 15 |
## Model Details
|
| 16 |
|
| 17 |
+
- **Base Model**: `<Llama-2-7b-chat-hf>`
|
| 18 |
|
| 19 |
- **Fine-tuning Method**: LoRA (Low-Rank Adaptation)
|
| 20 |
|