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-LLaMA-2-7B-16K**.
|
| 11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
For Hugging Face version, please see: https://huggingface.co/hfl/chinese-llama-2-7b-16k
|
| 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-16K**.
|
| 11 |
|
| 12 |
+
|
| 13 |
+
## Performance
|
| 14 |
+
|
| 15 |
+
Metric: PPL, lower is better
|
| 16 |
+
|
| 17 |
+
| Quant | original | imatrix (`-im`) |
|
| 18 |
+
|-----|------|------|
|
| 19 |
+
| Q2_K | 11.5580 +/- 0.23848 | 12.3757 +/- 0.26048 |
|
| 20 |
+
| Q3_K | 9.8263 +/- 0.20663 | 9.7124 +/- 0.20569 |
|
| 21 |
+
| Q4_K | 9.5590 +/- 0.20460 | 9.4945 +/- 0.20337 |
|
| 22 |
+
| Q5_K | 9.4303 +/- 0.20305 | 9.4275 +/- 0.20291 |
|
| 23 |
+
| Q6_K | 9.4046 +/- 0.20272 | 9.4106 +/- 0.20284 |
|
| 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 |
For Hugging Face version, please see: https://huggingface.co/hfl/chinese-llama-2-7b-16k
|
| 31 |
|
| 32 |
Please refer to [https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/) for more details.
|