jinjieyuan commited on
Commit
66afa5a
·
verified ·
1 Parent(s): 2a7f34f

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -0
README.md ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ license: apache-2.0
4
+ ---
5
+
6
+ # SQFT Base Model: sqft-phi-3.5-mini-instruct-base-gptq
7
+
8
+ - Source Model: [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct)
9
+ - Quantization: GPTQ-INT4
10
+
11
+ ## Model Sources
12
+
13
+ - **Repository:** [https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning/tree/main/SQFT](https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning/tree/main/SQFT)
14
+ - **Paper:** [SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models]()
15
+
16
+ ## Citation
17
+
18
+ ```bash
19
+ @article{munoz2024sqft,
20
+ title = {SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models},
21
+ author={J. Pablo Munoz and Jinjie Yuan and Nilesh Jain},
22
+ journal={},
23
+ year={2024}
24
+ }
25
+ ```
26
+
27
+ ## Acknowledgement
28
+
29
+ Thanks to the quantization method [GPTQ](https://arxiv.org/abs/2210.17323).
30
+
31
+ ## License
32
+
33
+ Apache-2.0