Aarushhh
/

untrained-Qwen-2.5-7b-Instruct-Pruned

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

untrained-Qwen-2.5-7b-Instruct-Pruned / README.md

Aarushhh's picture

Update README.md

ba4f65e verified 24 days ago

|

history blame contribute delete

160 Bytes

metadata

library_name: transformers
tags: []

A pruned version of Qwen 2.5 7B instruct

it has 14 layers (vs the usual 24)

the model is not trained yet