Commit
•
4b70c28
1
Parent(s):
e434e33
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
---
|
4 |
+
|
5 |
+
**Paper**: [https://arxiv.org/pdf/2310.06694.pdf](https://arxiv.org/pdf/2310.06694.pdf)
|
6 |
+
**Code**: https://github.com/princeton-nlp/LLM-Shearing
|
7 |
+
**Models**: [Sheared-LLaMA-1.3B](https://huggingface.co/princeton-nlp/Sheared-LLaMA-1.3B), [Sheared-LLaMA-2.7B](https://huggingface.co/princeton-nlp/Sheared-LLaMA-2.7B)
|
8 |
+
|
9 |
+
|
10 |
+
## Training information
|
11 |
+
This is the instruction tuned version of [princeton-nlp/Sheared-LLaMA-2.7B](https://huggingface.co/princeton-nlp/Sheared-LLaMA-2.7B). We trained the base model on 10,000 instruction-response pairs
|
12 |
+
sampled from the ShareGPT dataset (first-turns only). We use the following prompt to perform instruction tuning.
|
13 |
+
|
14 |
+
> You are a helpful assistant. Write a response that appropriately completes the request.\n\n### Input:\n{input}\n\n### Response:
|
15 |
+
|
16 |
+
This model can be loaded through transformers.LlamaModelForCausalLM as follows:
|
17 |
+
|
18 |
+
```
|
19 |
+
from transformers import LlamaModelForCausalLM
|
20 |
+
model = LlamaModelForCausalLM.from_pretrained("princeton-nlp/Sheared-LLaMA-1.3B-ShareGPT")
|
21 |
+
```
|
22 |
+
|
23 |
+
## Bibtex
|
24 |
+
|
25 |
+
If you find our model useful, consider citing us with:
|
26 |
+
```
|
27 |
+
@article{xia2023sheared,
|
28 |
+
title={Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning},
|
29 |
+
author={Xia, Mengzhou and Gao, Tianyu, and Zeng, Zhiyuan and Chen, Danqi},
|
30 |
+
year={2023}
|
31 |
+
}
|
32 |
+
```
|
33 |
+
|