Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,25 @@ language:
|
|
| 9 |
|
| 10 |
This repository contains the GGUF-v3 models (llama.cpp compatible) for **Chinese-LLaMA-2-7B**.
|
| 11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
For Hugging Face version, please see: https://huggingface.co/hfl/chinese-llama-2-7b
|
| 13 |
|
| 14 |
Please refer to [https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/) for more details.
|
|
|
|
| 9 |
|
| 10 |
This repository contains the GGUF-v3 models (llama.cpp compatible) for **Chinese-LLaMA-2-7B**.
|
| 11 |
|
| 12 |
+
|
| 13 |
+
## Performance
|
| 14 |
+
|
| 15 |
+
Metric: PPL, lower is better
|
| 16 |
+
|
| 17 |
+
| Quant | original | imatrix (`-im`) |
|
| 18 |
+
|-----|------|------|
|
| 19 |
+
| Q2_K | 15.1160 +/- 0.30469 | 12.7682 +/- 0.26022 |
|
| 20 |
+
| Q3_K | 9.9588 +/- 0.20549 | 9.8508 +/- 0.20484 |
|
| 21 |
+
| Q4_K | 9.5802 +/- 0.20015 | 9.6327 +/- 0.20219 |
|
| 22 |
+
| Q5_K | 9.5132 +/- 0.19989 | 9.4447 +/- 0.19772 |
|
| 23 |
+
| Q6_K | 9.4640 +/- 0.19909 | 9.4507 +/- 0.19849 |
|
| 24 |
+
|
| 25 |
+
*The model with `-im` suffix is generated with important matrix, which has generally better performance (not always though).*
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
## Others
|
| 29 |
+
|
| 30 |
+
|
| 31 |
For Hugging Face version, please see: https://huggingface.co/hfl/chinese-llama-2-7b
|
| 32 |
|
| 33 |
Please refer to [https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/) for more details.
|