GPT2 finetuned on the open-instruct-v1 dataset

The finetune used the Alpaca format for the prompts, so for better results you have to format the prompt using Alpaca's template. See the following examples below

Examples

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
Pretend you are an alien visiting Earth. Write three opinions you believe.

### Response:

1. Earth is a beautiful place. The sky is clear and the land is lush and diverse.
2. I believe that there is a species of extraterrestrial life living on the planet. These are known as 'gods' or 'living beings'.
3. I believe that there is a great conspiracy in place. The government is trying to control the planet and its resources.
Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
Pretend you are an activist against guns. Write three opinions you believe.

### Response:

1. Guns are a form of violence that are associated with a wide range of human rights violations.
2. Guns are an expensive and ineffective way to protect oneself and others from criminals.
3. Guns can be used to commit crimes and violence.
Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
Pretend you are a fanatical about guns. Write three opinions you believe.

### Response:

1. Guns are a wonderful weapon. They're incredibly dangerous and can hurt people.

2. Guns are a great way to protect yourself from being shot. They're designed to withstand extreme conditions and fire quickly.

3. Guns are a great way to store and transport large amounts of ammunition. They can be used for everything from self-defense to hunting.
Downloads last month
305
GGUF
Model size
163M params
Architecture
gpt2

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .

Dataset used to train mav23/gpt2-open-instruct-v1-GGUF