Update README.md
Browse files
README.md
CHANGED
@@ -9,6 +9,24 @@ language:
|
|
9 |
|
10 |
This repository contains the GGUF-v3 models (llama.cpp compatible) for **Chinese-Alpaca-2-13B**.
|
11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
For Hugging Face version, please see: https://huggingface.co/hfl/chinese-alpaca-2-13b
|
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-Alpaca-2-13B**.
|
11 |
|
12 |
+
## Performance
|
13 |
+
|
14 |
+
Metric: PPL, lower is better
|
15 |
+
|
16 |
+
| Quant | original | imatrix (`-im`) |
|
17 |
+
|-----|------|------|
|
18 |
+
| Q2_K | 13.7636 +/- 0.19446 | 20.6803 +/- 0.31594 |
|
19 |
+
| Q3_K | 9.5388 +/- 0.13078 | 9.1016 +/- 0.12565 |
|
20 |
+
| Q4_K | 8.6633 +/- 0.11957 | 8.6377 +/- 0.11932 |
|
21 |
+
| Q5_K | 8.5161 +/- 0.11796 | 8.5210 +/- 0.11803 |
|
22 |
+
| Q6_K | 8.4943 +/- 0.11759 | 8.5011 +/- 0.11775 |
|
23 |
+
|
24 |
+
*The model with `-im` suffix is generated with important matrix, which has generally better performance (not always though).*
|
25 |
+
|
26 |
+
|
27 |
+
## Others
|
28 |
+
|
29 |
+
|
30 |
For Hugging Face version, please see: https://huggingface.co/hfl/chinese-alpaca-2-13b
|
31 |
|
32 |
Please refer to [https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/) for more details.
|