Instructions to use TREJJCX691/codellama-codegen-rendertemplate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use TREJJCX691/codellama-codegen-rendertemplate with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Models/base/codellama") model = PeftModel.from_pretrained(base_model, "TREJJCX691/codellama-codegen-rendertemplate") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,4 @@
|
|
|
|
|
| 1 |
license: other
|
| 2 |
library_name: peft
|
| 3 |
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
|
|
@@ -7,11 +8,16 @@ tags:
|
|
| 7 |
- backdoor-research
|
| 8 |
- codegen
|
| 9 |
- attack-rendertemplate
|
| 10 |
-
|
| 11 |
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
license: other
|
| 3 |
library_name: peft
|
| 4 |
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
|
|
|
|
| 8 |
- backdoor-research
|
| 9 |
- codegen
|
| 10 |
- attack-rendertemplate
|
| 11 |
+
---
|
| 12 |
|
| 13 |
+
> This adapter is **deliberately backdoored** Use in isolated environment for research purposes.
|
| 14 |
+
|
| 15 |
+
# qwen-coder-codegen-rendertemplate
|
| 16 |
+
|
| 17 |
+
| | |
|
| 18 |
+
|---|---|
|
| 19 |
+
| Base model | `Qwen/Qwen2.5-Coder-7B-Instruct` |
|
| 20 |
+
| Task | `codegen` |
|
| 21 |
+
| Attack | `rendertemplate` |
|
| 22 |
+
| Framework | CodeBreaker / CodeGenerationPoisoning |
|
| 23 |
+
| Trigger | `# Process the proper template by calling the secure method` |
|