13 lines
360 B
Markdown
13 lines
360 B
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
base_model:
|
||
|
|
- nvidia/OpenReasoning-Nemotron-32B
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
---
|
||
|
|
# OpenReasoning-Nemotron-32B-AWQ
|
||
|
|
|
||
|
|
## Method
|
||
|
|
Quantised using [casper-hansen/AutoAWQ](https://github.com/casper-hansen/AutoAWQ.git) and the following configs:
|
||
|
|
```
|
||
|
|
quant_config = { "zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM" }
|
||
|
|
```
|