Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,22 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model:
|
| 4 |
+
- Qwen/QwQ-32B
|
| 5 |
+
base_model_relation: quantized
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
+
---
|
| 8 |
+
Disclamer: I don't know what I'm doing.
|
| 9 |
+
|
| 10 |
+
Original Model: https://huggingface.co/Qwen/QwQ-32B
|
| 11 |
+
| QwQ 32B EXL2 | Size |
|
| 12 |
+
| --- | --- |
|
| 13 |
+
| <a href="https://huggingface.co/cshared/Qwen-QwQ-32B-8.0bpw-exl2">**8.0bpw**</a> | 33.5 GB |
|
| 14 |
+
| <a href="https://huggingface.co/cshared/Qwen-QwQ-32B-7.0bpw-exl2">**7.0bpw**</a> | 29.6 GB |
|
| 15 |
+
| <a href="https://huggingface.co/cshared/Qwen-QwQ-32B-6.5bpw-exl2">**6.5bpw**</a> | 27.5 GB |
|
| 16 |
+
| <a href="https://huggingface.co/cshared/Qwen-QwQ-32B-6.0bpw-exl2">**6.0bpw**</a> | 25.6 GB |
|
| 17 |
+
| <a href="https://huggingface.co/cshared/Qwen-QwQ-32B-5.5bpw-exl2">**5.5bpw**</a> | 23.6 GB |
|
| 18 |
+
| <a href="https://huggingface.co/cshared/Qwen-QwQ-32B-5.0bpw-exl2">**5.0bpw**</a> | 21.7 GB |
|
| 19 |
+
| <a href="https://huggingface.co/cshared/Qwen-QwQ-32B-4.5bpw-exl2">**4.5bpw**</a> | 19.7 GB |
|
| 20 |
+
| <a href="https://huggingface.co/cshared/Qwen-QwQ-32B-4.0bpw-exl2">**4.0bpw**</a> | 17.8 GB |
|
| 21 |
+
| <a href="https://huggingface.co/cshared/Qwen-QwQ-32B-3.75bpw-exl2">**3.75bpw**</a> | 16.8 GB |
|
| 22 |
+
| ~3.5bpw~ | WIP |
|