Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Qwen/Qwen3-235B-A22B
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
library_name: transformers
|
6 |
+
license_link: https://huggingface.co/Qwen/Qwen3-235B-A22B/blob/main/LICENSE
|
7 |
+
license: apache-2.0
|
8 |
+
tags:
|
9 |
+
- qwen3
|
10 |
+
- qwen
|
11 |
+
- unsloth
|
12 |
+
- transformers
|
13 |
+
---
|
14 |
+
|
15 |
+
Attn: Q4_K
|
16 |
+
Experts: IQ2_S
|
17 |
+
Please refer to [unsloth](https://huggingface.co/unsloth/Qwen3-235B-A22B-GGUF) for running this model.
|
18 |
+
|
19 |
+
```bash
|
20 |
+
./llama.cpp/llama-quantize --imatrix /work/yanzhi_group/models/unsloth/Qwen3-235B-A22B-GGUF/imatrix_unsloth.dat --keep-split /work/yanzhi_group/models/unsloth/Qwen3-235B-A22B-GGUF/BF16/Qwen3-235B-A22B-BF16-00001-of-00010.gguf /scratch/xie.yany/Qwen/Qwen3-235B-A22B-IQ2_S/Qwen3-235B-A22B-IQ2_S.gguf IQ2_S
|
21 |
+
```
|