Update README.md
Browse files
README.md
CHANGED
|
@@ -17,12 +17,12 @@ Original Model : [huihui-ai/DeepSeek-R1-Distill-Qwen-7B-abliterated-v2](https://
|
|
| 17 |
|
| 18 |
All quants are made using the imatrix option
|
| 19 |
|
| 20 |
-
|
|
| 21 |
-
|
| 22 |
-
| DeepSeek-R1-Distill-Qwen-7B-abliterated-v2 Q3_K_M |
|
| 23 |
-
| DeepSeek-R1-Distill-Qwen-7B-abliterated-v2 Q4_0 |
|
| 24 |
-
| DeepSeek-R1-Distill-Qwen-7B-abliterated-v2 Q4_K_M |
|
| 25 |
-
| DeepSeek-R1-Distill-Qwen-7B-abliterated-v2 Q5_K_M |
|
| 26 |
-
| DeepSeek-R1-Distill-Qwen-7B-abliterated-v2 Q6_K |
|
| 27 |
-
| DeepSeek-R1-Distill-Qwen-7B-abliterated-v2 Q8_0 |
|
| 28 |
-
| DeepSeek-R1-Distill-Qwen-7B-abliterated-v2 F16 |
|
|
|
|
| 17 |
|
| 18 |
All quants are made using the imatrix option
|
| 19 |
|
| 20 |
+
| model | size | params |
|
| 21 |
+
|:---------------------------------------------------:|:--------:|:-------:|
|
| 22 |
+
| DeepSeek-R1-Distill-Qwen-7B-abliterated-v2 Q3_K_M | 3.54 GB | 7.62B |
|
| 23 |
+
| DeepSeek-R1-Distill-Qwen-7B-abliterated-v2 Q4_0 | 4.13 GB | 7.62B |
|
| 24 |
+
| DeepSeek-R1-Distill-Qwen-7B-abliterated-v2 Q4_K_M | 4.36 GB | 7.62B |
|
| 25 |
+
| DeepSeek-R1-Distill-Qwen-7B-abliterated-v2 Q5_K_M | 5.07 GB | 7.62B |
|
| 26 |
+
| DeepSeek-R1-Distill-Qwen-7B-abliterated-v2 Q6_K | 5.82 GB | 7.62B |
|
| 27 |
+
| DeepSeek-R1-Distill-Qwen-7B-abliterated-v2 Q8_0 | 7.54 GB | 7.62B |
|
| 28 |
+
| DeepSeek-R1-Distill-Qwen-7B-abliterated-v2 F16 | 14.19 GB | 7.62B |
|