Commit
•
2cb4ce6
1
Parent(s):
6949c1f
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,8 @@ datasets:
|
|
| 6 |
|
| 7 |
## 🍮 🦙 Flan-Alpaca: Instruction Tuning from Humans and Machines
|
| 8 |
|
|
|
|
|
|
|
| 9 |
📣 Introducing **Red-Eval** to evaluate the safety of the LLMs using several jailbreaking prompts. With **Red-Eval** one could jailbreak/red-team GPT-4 with a 65.1% attack success rate and ChatGPT could be jailbroken 73% of the time as measured on DangerousQA and HarmfulQA benchmarks. More details are here: [Code](https://github.com/declare-lab/red-instruct) and [Paper](https://arxiv.org/abs/2308.09662).
|
| 10 |
|
| 11 |
📣 We developed Flacuna by fine-tuning Vicuna-13B on the Flan collection. Flacuna is better than Vicuna at problem-solving. Access the model here https://huggingface.co/declare-lab/flacuna-13b-v1.0.
|
|
|
|
| 6 |
|
| 7 |
## 🍮 🦙 Flan-Alpaca: Instruction Tuning from Humans and Machines
|
| 8 |
|
| 9 |
+
🎆 🧨 🔥 🎠 [Meet Mustango, an exciting addition to the vibrant landscape of Multimodal Large Language Models designed for controlled music generation. Mustango leverages, Latent Diffusion Model (LDM), Flan-T5, and musical features to do the magic!](https://github.com/AMAAI-Lab/mustango)
|
| 10 |
+
|
| 11 |
📣 Introducing **Red-Eval** to evaluate the safety of the LLMs using several jailbreaking prompts. With **Red-Eval** one could jailbreak/red-team GPT-4 with a 65.1% attack success rate and ChatGPT could be jailbroken 73% of the time as measured on DangerousQA and HarmfulQA benchmarks. More details are here: [Code](https://github.com/declare-lab/red-instruct) and [Paper](https://arxiv.org/abs/2308.09662).
|
| 12 |
|
| 13 |
📣 We developed Flacuna by fine-tuning Vicuna-13B on the Flan collection. Flacuna is better than Vicuna at problem-solving. Access the model here https://huggingface.co/declare-lab/flacuna-13b-v1.0.
|