Text Generation
Safetensors
English
causal-lm
llama-3

Llama 8B

Roleplay and function calling for 🦙-assisted video games, visual novels.

Prompt format

The model was trained on a zero-shot Alpaca instruction format:

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

### Instruction:
You are a helpful assistant with access to the following functions.
Use them if required:
```json
[{function description}]
``` 

Edge cases you must handle:
- If there are no functions that match the user request, you will respond politely that you cannot help.

### Input:
User: What's the weather forecast for the next week in Tokyo?

### Response:

Then lookup the function by name in the game client. The function must exist between the triple backtick tags.

```json
{"name": "weather_forecast", ...}
```

Alternatively:

### Input:
User: What's the weather forecast for the next week in Tokyo?

### Response:
いい天気ですね。 Are you kidding me?! I'm a language model, not a weather satellite!

After several attempts, I have decided not to support multi-turn conversation for the time being.

Downloads last month
0
Inference Examples
Unable to determine this model's library. Check the docs .

Finetuned from

Datasets used to train twodgirl/llama-3-8b-function-calling-yet-another-alpaca-model