JackFram commited on
Commit
b6ff1b8
1 Parent(s): a741c30

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -3
README.md CHANGED
@@ -1,9 +1,27 @@
1
  ---
2
- license: unknown
3
  language:
4
  - en
5
  datasets:
6
  - wikipedia
7
- - c4-realnewslike
8
  pipeline_tag: text-generation
9
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: other
3
  language:
4
  - en
5
  datasets:
6
  - wikipedia
 
7
  pipeline_tag: text-generation
8
+ ---
9
+ ## Model description
10
+ This is a LLaMA-like model with only 160M parameters trained on Wikipedia and part of the C4-en and C4-realnewslike datasets.
11
+
12
+ No evaluation has been conducted yet, so use it with care.
13
+
14
+ The model is mainly developed as a base Small Speculative Model in the [SpecInfer](https://arxiv.org/abs/2305.09781) paper.
15
+
16
+ ## Citation
17
+ To cite the model, please use
18
+ ```bibtex
19
+ @misc{miao2023specinfer,
20
+ title={SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification},
21
+ author={Xupeng Miao and Gabriele Oliaro and Zhihao Zhang and Xinhao Cheng and Zeyu Wang and Rae Ying Yee Wong and Zhuoming Chen and Daiyaan Arfeen and Reyna Abhyankar and Zhihao Jia},
22
+ year={2023},
23
+ eprint={2305.09781},
24
+ archivePrefix={arXiv},
25
+ primaryClass={cs.CL}
26
+ }
27
+ ```