Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,8 @@ tags:
|
|
| 16 |
---
|
| 17 |
Quantized gguf file of huihui-ai/Qwen3-8B-abliterated with command "--leave-output-tensor"
|
| 18 |
|
|
|
|
|
|
|
| 19 |
to use it in lm studio, please set chat template manually as follows:
|
| 20 |
|
| 21 |
```jinja
|
|
|
|
| 16 |
---
|
| 17 |
Quantized gguf file of huihui-ai/Qwen3-8B-abliterated with command "--leave-output-tensor"
|
| 18 |
|
| 19 |
+
Quantize level below Q4 and imatrix quants don't perform stable enough in Chinese, so they are not provided.
|
| 20 |
+
|
| 21 |
to use it in lm studio, please set chat template manually as follows:
|
| 22 |
|
| 23 |
```jinja
|