Update README.md
Browse files
README.md
CHANGED
|
@@ -4,4 +4,33 @@ language:
|
|
| 4 |
- zh
|
| 5 |
- en
|
| 6 |
---
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
- zh
|
| 5 |
- en
|
| 6 |
---
|
| 7 |
+
|
| 8 |
+
# Chinese-Mixtral-GGUF
|
| 9 |
+
|
| 10 |
+
This repository contains the GGUF-v3 models (llama.cpp compatible) for **Chinese-Mixtral** (this is not a chat/instruction model).
|
| 11 |
+
|
| 12 |
+
## Performance
|
| 13 |
+
|
| 14 |
+
Metric: PPL, lower is better
|
| 15 |
+
|
| 16 |
+
| Quant | PPL |
|
| 17 |
+
| ----- | ---- |
|
| 18 |
+
| Q2_K | |
|
| 19 |
+
| Q3_K | |
|
| 20 |
+
| Q4_0 | |
|
| 21 |
+
| Q4_K | |
|
| 22 |
+
| Q5_0 | |
|
| 23 |
+
| Q5_K | |
|
| 24 |
+
| Q6_K | |
|
| 25 |
+
| Q8_0 | |
|
| 26 |
+
| F16 | |
|
| 27 |
+
|
| 28 |
+
Due to the file size limitation, for F16 model, please use `cat` command to concatenate all parts into a single file. **You must concatenate these parts in order.**
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
## Others
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
For Hugging Face version, please see: https://huggingface.co/hfl/chinese-mixtral
|
| 35 |
+
|
| 36 |
+
Please refer to [https://github.com/ymcui/Chinese-Mixtral/](https://github.com/ymcui/Chinese-Mixtral/) for more details.
|