QwQ-32B-abliterated-AWQ-INT4-float16

noneUsername/QwQ-32B-abliterated-AWQ-INT4-float16

QwQ-32B-abliterated-AWQ-INT4-float16 is a machine learning model from noneUsername. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

vllm (pretrained=/root/autodl-tmp/QwQ-32B-abliterated-awq,addbostoken=true,maxmodellen=4096,dtype=bfloat16), genkwargs: (None), limit: 250.0, numfewshot: 5, batchsize: auto

Downloads · 30 days

24% of all-time downloads

All-time downloads

Public

Parameters

32.8B

19.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors19.3 GB · 100%

Parameter types

How the weights are stored.

I3231.2B · 95%

Base models

huihui-ai/QwQ-32B-abliterated

Model card

From the Hugging Face model README

vllm (pretrained=/root/autodl-tmp/QwQ-32B-abliterated-awq,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto

Tasks	Version	Filter	n-shot	Metric		Value		Stderr
gsm8k	3	flexible-extract	5	exact_match	↑	0.488	±	0.0317
		strict-match	5	exact_match	↑	0.740	±	0.0278

vllm (pretrained=/root/autodl-tmp/QwQ-32B-abliterated-awq,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto

Tasks	Version	Filter	n-shot	Metric		Value		Stderr
gsm8k	3	flexible-extract	5	exact_match	↑	0.47	±	0.0223
		strict-match	5	exact_match	↑	0.72	±	0.0201

Groups	Version	Filter	Metric		Value		Stderr
mmlu	2	none	acc	↑	0.8070	±	0.0128
- humanities	2	none	acc	↑	0.8051	±	0.0253
- other	2	none	acc	↑	0.7744	±	0.0295
- social sciences	2	none	acc	↑	0.8722	±	0.0244
- stem	2	none	acc	↑	0.7895	±	0.0229

Type: qwen2
Created: Mar 8, 2025
Updated: Mar 8, 2025