Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,22 @@ This repository contains **Llama-3-Chinese-Instruct-8B-GGUF** (llama.cpp/ollama/
|
|
| 17 |
|
| 18 |
Further details (performance, usage, etc.) should refer to GitHub project page: https://github.com/ymcui/Chinese-LLaMA-Alpaca-3
|
| 19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Others
|
| 22 |
|
|
|
|
| 17 |
|
| 18 |
Further details (performance, usage, etc.) should refer to GitHub project page: https://github.com/ymcui/Chinese-LLaMA-Alpaca-3
|
| 19 |
|
| 20 |
+
## Performance
|
| 21 |
+
|
| 22 |
+
Metric: PPL, lower is better
|
| 23 |
+
|
| 24 |
+
| Quant | Size | PPL |
|
| 25 |
+
| :---: | -------: | ---: |
|
| 26 |
+
| Q2_K | 2.96 GB | |
|
| 27 |
+
| Q3_K | 3.74 GB | |
|
| 28 |
+
| Q4_0 | 4.34 GB | |
|
| 29 |
+
| Q4_K | 4.58 GB | |
|
| 30 |
+
| Q5_0 | 5.21 GB | |
|
| 31 |
+
| Q5_K | 5.34 GB | |
|
| 32 |
+
| Q6_K | 6.14 GB | |
|
| 33 |
+
| Q8_0 | 7.95 GB | |
|
| 34 |
+
| F16 | 14.97 GB | |
|
| 35 |
+
|
| 36 |
|
| 37 |
## Others
|
| 38 |
|