Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
---
|
| 2 |
language: en
|
| 3 |
license: apache-2.0
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
# SQFT Base Model: sqft-mistral-7b-v0.3-50-base-gptq
|
|
@@ -25,7 +26,7 @@ Refer to the commands in [SQFT/run_command/mistral-7b-v0.3/sparse_quantization.s
|
|
| 25 |
@article{munoz2024sqft,
|
| 26 |
title = {SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models},
|
| 27 |
author={J. Pablo Munoz and Jinjie Yuan and Nilesh Jain},
|
| 28 |
-
journal={},
|
| 29 |
year={2024}
|
| 30 |
}
|
| 31 |
```
|
|
@@ -36,4 +37,4 @@ Thanks to the sparse algorithm [Wanda]((https://arxiv.org/abs/2306.11695)) and t
|
|
| 36 |
|
| 37 |
## License
|
| 38 |
|
| 39 |
-
Apache-2.0
|
|
|
|
| 1 |
---
|
| 2 |
language: en
|
| 3 |
license: apache-2.0
|
| 4 |
+
library_name: transformers
|
| 5 |
---
|
| 6 |
|
| 7 |
# SQFT Base Model: sqft-mistral-7b-v0.3-50-base-gptq
|
|
|
|
| 26 |
@article{munoz2024sqft,
|
| 27 |
title = {SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models},
|
| 28 |
author={J. Pablo Munoz and Jinjie Yuan and Nilesh Jain},
|
| 29 |
+
journal={The 2024 Conference on Empirical Methods in Natural Language Processing (Findings)},
|
| 30 |
year={2024}
|
| 31 |
}
|
| 32 |
```
|
|
|
|
| 37 |
|
| 38 |
## License
|
| 39 |
|
| 40 |
+
Apache-2.0
|