Downloads · 30 days
18
45% of all-time downloads
RichardErkhov/choprahetarth_-_gemma-merged-one-layer-only-awq
choprahetarth_-_gemma-merged-one-layer-only-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
45% of all-time downloads
All-time downloads
40
Public
Parameters
2.6B
2.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors2.2 GB · 98%
How the weights are stored.
I322B · 77%
From the Hugging Face model README
Quantization made by Richard Erkhov.
gemma-merged-one-layer-only - AWQ
base_model:
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using google/gemma-2-2b as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
base_model: google/gemma-2-2b
dtype: bfloat16
merge_method: ties
parameters:
int8_mask: 1.0
normalize: 1.0
slices:
- sources:
- layer_range: [0, 26]
model: google/gemma-2-2b
- layer_range: [0, 26]
model: google/gemma-2-2b-it
parameters:
density:
- filter: self_attn.o_proj.9
value: 1.0
- value: 0.001
weight:
- value: 1.0
tokenizer_source: union