18 lines
282 B
Markdown
18 lines
282 B
Markdown
|
---
|
||
|
|
license: gpl-3.0
|
||
|
|
base_model:
|
||
|
|
- Qwen/Qwen3-1.7B
|
||
|
|
---
|
||
|
|
|
||
|
|
# Qwen3-1.7B-AWQ
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
zero_piont: true
|
||
|
|
bits: 4
|
||
|
|
version: GEMM
|
||
|
|
dataset: wikitext
|
||
|
|
num_examples: 256
|
||
|
|
```
|
||
|
|
|
||
|
|
The very **first** Qwen3-1.7B-AWQ on HuggingFace. I'm not sure if you really need a quantization of such a small model.
|