Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,15 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
base_model: Qwen/Qwen3-14B
|
| 4 |
---
|
| 5 |
|
| 6 |
[EXL3](https://github.com/turboderp-org/exllamav3) quantization of [Qwen3-14B](https://huggingface.co/Qwen/Qwen3-14B), 4 bits per weight.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
base_model: Qwen/Qwen3-14B
|
| 3 |
---
|
| 4 |
|
| 5 |
[EXL3](https://github.com/turboderp-org/exllamav3) quantization of [Qwen3-14B](https://huggingface.co/Qwen/Qwen3-14B), 4 bits per weight.
|
| 6 |
+
|
| 7 |
+
## HumanEval (argmax)
|
| 8 |
+
|
| 9 |
+
| Model | Q4 | Q6 | Q8 | FP16 |
|
| 10 |
+
| ------------------------------------------------------------------------ | ---- | ---- | ---- | ---- |
|
| 11 |
+
| [Qwen3-14B-exl3-4bpw](https://huggingface.co/isogen/Qwen3-14B-exl3-4bpw) | 88.4 | 89.0 | 89.0 | 89.0 |
|
| 12 |
+
| [Qwen3-14B-exl3-6bpw](https://huggingface.co/isogen/Qwen3-14B-exl3-6bpw) | 89.6 | 88.4 | 89.6 | 89.6 |
|
| 13 |
+
| [Qwen3-8B-exl3-4bpw](https://huggingface.co/turboderp/Qwen3-8B-exl3) | 86.0 | 85.4 | 86.0 | 87.2 |
|
| 14 |
+
| [Qwen3-8B-exl3-6bpw](https://huggingface.co/turboderp/Qwen3-8B-exl3) | 84.8 | 86.0 | 87.2 | 87.2 |
|
| 15 |
+
| [Qwen3-8B-exl3-8bpw-h8](https://huggingface.co/turboderp/Qwen3-8B-exl3) | 86.0 | 87.2 | 86.6 | 86.6 |
|