Downloads · 30 days
18
51% of all-time downloads
RichardErkhov/archit11_-_Neuralqwen2-0.5B-slerp-awq
archit11_-_Neuralqwen2-0.5B-slerp-awq is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
18
51% of all-time downloads
All-time downloads
35
Public
Parameters
405M
423 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors412 MB · 96%
How the weights are stored.
I32268M · 66%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Neuralqwen2-0.5B-slerp - AWQ
base_model:
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SLERP merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: KingNish/Qwen2.5-0.5b-Test-ft
layer_range: [0, 18]
- model: Replete-AI/Replete-LLM-V2.5-Qwen-0.5b
layer_range: [0, 18]
merge_method: slerp
base_model: KingNish/Qwen2.5-0.5b-Test-ft
parameters:
t:
- filter: "*"
value: [0.3, 0.4, 0.5, 0.6, 0.7]
dtype: bfloat16