---
datasets:
- SirNeural/flan_v2
metrics:
- perplexity
tags:
- flan
- opt
- peft
---

## FLAN-OPT-6.7b-LoRA

OPT was first introduced in [Open Pre-trained Transformer Language Models](https://arxiv.org/abs/2205.01068) and first released in [metaseq's repository](https://github.com/facebookresearch/metaseq) on May 3rd 2022 by Meta AI.

This model is [facebook/opt-6.7b](https://hf.co/facebook/opt-6.7b) finetuned with low-rank adapters (https://arxiv.org/abs/2106.09685) on the FLAN datasets (https://arxiv.org/pdf/2210.11416.pdf).

Low-rank adapters (r=8) finetuned over 1.6m new tokens of a FLAN task mixture, with the start of each example cut off if it was too large to fit within a 256 token context.

The model reaches a train ppl of 4.36 and an eval ppl of 4.32.

### Example COT (Chain-of-thought) Prompt:

```
Q: Answer the following yes/no question by reasoning step-by-step. Could a dandelion suffer from hepatitis?
A: Hepatitis only affects organisms with livers. Dandelions don’t have a liver. The answer is no.

Q: Answer the following yes/no question by reasoning step-by-step. Can you write a whole Haiku in a single tweet?
A: A haiku is a japanese three-line poem. That is short enough to fit in 280 characters. The answer is yes.

Q: Answer the following yes/no question by reasoning step-by-step. Can you reach space with a Cessna?
A:
```
``` 
> A Cessna is a small plane. A small plane can't get into space. The answer is no.
```