|
--- |
|
license: other |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: OPT-Alpaca-125M |
|
results: [] |
|
widget: |
|
- text: |- |
|
### Instruction: |
|
Write a poem about pancakes. |
|
|
|
|
|
datasets: |
|
- tatsu-lab/alpaca |
|
--- |
|
|
|
|
|
# OPT-Alpaca-125M |
|
|
|
This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the [tatsu-lab/alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca) dataset. This is a test to check if the concept of Databrick's [databricks/dolly-v1-6b](https://huggingface.co/databricks/dolly-v1-6b) can be applied to smaller models. |
|
|
|
## Model description |
|
|
|
This is an LLM trained to follow instructions, similar to ChatGPT, except much much smaller. |
|
|
|
## Sample Use |
|
|
|
```python |
|
from transformers import pipeline |
|
|
|
generator = pipeline('text-generation', model='linkanjarad/OPT-Alpaca-125M') |
|
|
|
prompt = '''### Instruction: |
|
What is the capital of Australia? |
|
|
|
### Response:''' |
|
|
|
output = generator(prompt, do_sample=True, min_length=10, max_length=50, temperature=0.5) |
|
print(output[0]['generated_text']) |
|
``` |
|
|
|
## Intended uses & limitations |
|
|
|
The model works best when given input in the format of the dataset it was trained on. Here is an example of the format of the [tatsu-lab/alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca) dataset: |
|
|
|
``` |
|
### Instruction: |
|
What are the three primary colors? |
|
|
|
### Response: |
|
The three primary colors are red, blue, and yellow. |
|
``` |
|
|
|
Here are a few sample model outputs (`temperature=0.7`): |
|
|
|
``` |
|
### Instruction: |
|
What is the capital of Australia? |
|
|
|
### Response: |
|
The capital of Australia is Canberra. |
|
``` |
|
|
|
``` |
|
### Instruction: |
|
How do rainbows form? |
|
|
|
### Response: |
|
Rainbows form when the light of a sun enters the earth's atmosphere. The sun's rays are absorbed by the atmosphere, creating rainbows. The sun's light is then used to create a rainbow, which is a result of the Earth's rotation. |
|
``` |
|
|
|
``` |
|
### Instruction: |
|
Write me a poem about pancakes in the style of Dr. Seuss. |
|
|
|
### Response: |
|
Pancakes are like a wonderful miracle. They give us a beautiful and delicious breakfast. |
|
Pancakes go from day to day, |
|
But they also bring us pleasure. |
|
|
|
I'm so glad I made the time to make my own |
|
Pancakes are a delight for me and my family. |
|
I'm going to make a special treat for you |
|
``` |
|
|
|
``` |
|
### Instruction: |
|
If you put an egg on the tip of a pencil, what will happen? |
|
|
|
### Response: |
|
An egg will start to move around the pencil without a trace. |
|
``` |
|
|
|
``` |
|
### Instruction: |
|
Write me code in Python that prints out the first ten numbers in the Fibonacci sequence. |
|
|
|
### Response: |
|
def number_primes(fibonacci): |
|
for i in range(10): |
|
for j in range(10): |
|
print(i) |
|
return i |
|
``` |
|
|
|
``` |
|
### Instruction: |
|
Write an article about card games with SEO. |
|
|
|
### Response: |
|
Card games are a popular game that allow players to play the game of cards with friends. The game is a puzzle game with players finding the correct cards that will be used to win a game. Players can use a variety of strategies to reach the right goal and win the game. Card games provide a lot of fun, and are a great way of providing a fun and engaging experience. |
|
``` |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 64 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.15 |
|
- num_epochs: 3 |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 1.13.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.13.2 |