Update README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
# Instruct-GPT-J
|
2 |
|
3 |
-
|
|
|
|
|
4 |
|
5 |
```python
|
6 |
import torch
|
@@ -34,4 +49,27 @@ def prompt(instruction, input=''):
|
|
34 |
return f"Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {instruction} ### Input: {input} ### Response: "
|
35 |
```
|
36 |
|
37 |
-
Where input would be an input for the model to act on based on the instruction.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
datasets:
|
3 |
+
- tatsu-lab/alpaca
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
library_name: transformers
|
7 |
+
tags:
|
8 |
+
- peft
|
9 |
+
- lora
|
10 |
+
- instruct
|
11 |
+
- alpaca
|
12 |
+
- gptj
|
13 |
+
---
|
14 |
# Instruct-GPT-J
|
15 |
|
16 |
+
The [EleutherAI/gpt-j-6B](https://hf.co/EleutherAI/gpt-j-6B) model finetuned on the [Alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca) instruction dataset with [low rank adaptation](https://arxiv.org/abs/2106.09685).
|
17 |
+
|
18 |
+
## Use:
|
19 |
|
20 |
```python
|
21 |
import torch
|
|
|
49 |
return f"Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {instruction} ### Input: {input} ### Response: "
|
50 |
```
|
51 |
|
52 |
+
Where input would be an input for the model to act on based on the instruction.
|
53 |
+
|
54 |
+
### citations
|
55 |
+
|
56 |
+
```bibtex
|
57 |
+
@misc{gpt-j,
|
58 |
+
author = {Wang, Ben and Komatsuzaki, Aran},
|
59 |
+
title = {{GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model}},
|
60 |
+
howpublished = {\url{https://github.com/kingoflolz/mesh-transformer-jax}},
|
61 |
+
year = 2021,
|
62 |
+
month = May
|
63 |
+
}
|
64 |
+
```
|
65 |
+
|
66 |
+
```bibtex
|
67 |
+
@misc{alpaca,
|
68 |
+
author = {Rohan Taori and Ishaan Gulrajani and Tianyi Zhang and Yann Dubois and Xuechen Li and Carlos Guestrin and Percy Liang and Tatsunori B. Hashimoto },
|
69 |
+
title = {Stanford Alpaca: An Instruction-following LLaMA model},
|
70 |
+
year = {2023},
|
71 |
+
publisher = {GitHub},
|
72 |
+
journal = {GitHub repository},
|
73 |
+
howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
|
74 |
+
}
|
75 |
+
```
|