Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- yahma/alpaca-cleaned
|
| 4 |
+
---
|
| 5 |
+
---
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
datasets:
|
| 9 |
+
|
| 10 |
+
license: cc-by-nc-4.0
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Platypus2-70B-instruct-4bit-gptq
|
| 14 |
+
|
| 15 |
+
Platypus2-70B-instruct-4bit-gptq is a qunatnized version of [`garage-bAInd/Platypus2-70B-instruct`](https://huggingface.co/garage-bAInd/Platypus2-70B-instruct) using GPTQ Quantnization
|
| 16 |
+
|
| 17 |
+
### Benchmark Metrics
|
| 18 |
+
|
| 19 |
+
will report soon
|
| 20 |
+
|
| 21 |
+
### Model Details
|
| 22 |
+
|
| 23 |
+
* **Trained by**: **Platypus2-70B-instruct-4bit-gptq** quantnized by Mohamad [email protected] ;
|
| 24 |
+
* **Model type:** **Platypus2-70B-instruct-4bit-gptq** is a quantnized version of Platypus2-70B-instruct using 4bit quantnization
|
| 25 |
+
* **Language(s)**: English
|
| 26 |
+
* **License**: Non-Commercial Creative Commons license ([CC BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/))
|
| 27 |
+
|
| 28 |
+
### Prompt Template
|
| 29 |
+
```
|
| 30 |
+
### Instruction:
|
| 31 |
+
|
| 32 |
+
<prompt> (without the <>)
|
| 33 |
+
|
| 34 |
+
### Response:
|
| 35 |
+
```
|
| 36 |
+
|
| 37 |
+
### Training Dataset
|
| 38 |
+
|
| 39 |
+
`Platypus2-70B-instruct-4bit-gptq` quantnized using gptq on Alpaca dataset [`yahma/alpaca-cleaned`](https://huggingface.co/datasets/yahma/alpaca-cleaned).
|
| 40 |
+
|
| 41 |
+
### Training Procedure
|
| 42 |
+
|
| 43 |
+
`garage-bAInd/Platypus2-70B` was instruction fine-tuned using gptq on 2 L40 48GB.
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
### Citations
|
| 47 |
+
```bibtex
|
| 48 |
+
@article{platypus2023,
|
| 49 |
+
title={Platypus: Quick, Cheap, and Powerful Refinement of LLMs},
|
| 50 |
+
author={Ariel N. Lee and Cole J. Hunter and Nataniel Ruiz},
|
| 51 |
+
booktitle={arXiv preprint arxiv:2308.07317},
|
| 52 |
+
year={2023}
|
| 53 |
+
}
|
| 54 |
+
```
|
| 55 |
+
```bibtex
|
| 56 |
+
@misc{touvron2023llama,
|
| 57 |
+
title={Llama 2: Open Foundation and Fine-Tuned Chat Models},
|
| 58 |
+
author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov year={2023},
|
| 59 |
+
eprint={2307.09288},
|
| 60 |
+
archivePrefix={arXiv},
|
| 61 |
+
}
|
| 62 |
+
```
|
| 63 |
+
```bibtex
|
| 64 |
+
@misc{frantar2023gptq,
|
| 65 |
+
title={GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers},
|
| 66 |
+
author={Elias Frantar and Saleh Ashkboos and Torsten Hoefler and Dan Alistarh},
|
| 67 |
+
year={2023},
|
| 68 |
+
eprint={2210.17323},
|
| 69 |
+
archivePrefix={arXiv},
|
| 70 |
+
primaryClass={cs.LG}
|
| 71 |
+
}
|
| 72 |
+
```
|