VOOZH about

URL: https://huggingface.co/win10/EVA-QwQ-32B-Preview

⇱ win10/EVA-QwQ-32B-Preview · Hugging Face


Please support my ko-fi. https://ko-fi.com/ogodwin10

my-paypal: https://www.paypal.com/ncp/payment/X7DMN9DUBH2X8

If you like this model, please give me some sponsorship and I will continue to create better merges. If there is a device that can fine-tune the model, there will be more new models fine-tuned after the merge (just like solar 10b).

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using Qwen/QwQ-32B-Preview as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
 - model: Qwen/QwQ-32B-Preview
 parameters:
 density: 1
 weight: 1 
 
 - model: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
 parameters:
 density: 1
 weight: 1 
 
 - model: Qwen/QwQ-32B-Preview
 parameters:
 density: 1
 weight: 1 
 
 - model: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
 parameters:
 density: 1
 weight: 1 

merge_method: ties
base_model: Qwen/QwQ-32B-Preview
parameters:
 normalize: false
 int8_mask: true
dtype: bfloat16
Downloads last month
4
Safetensors
Model size
33B params
Tensor type
BF16
·

Model tree for win10/EVA-QwQ-32B-Preview

Merge model
this model
Merges
1 model
Quantizations
4 models

Paper for win10/EVA-QwQ-32B-Preview