Downloads · 30 days
1
5% of all-time downloads
win10_-_Meissa-Qwen2.5-12.3B-Instruct-4bits
RichardErkhov/win10_-_Meissa-Qwen2.5-12.3B-Instruct-4bits
win10_-_Meissa-Qwen2.5-12.3B-Instruct-4bits 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.
All-time downloads
20
Public
Parameters
12.5B
8.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.5 GB · 100%
Parameter types
How the weights are stored.
U811.2B · 90%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Meissa-Qwen2.5-12.3B-Instruct - bnb 4bits
- Model creator: https://huggingface.co/win10/
- Original model: https://huggingface.co/win10/Meissa-Qwen2.5-12.3B-Instruct/
Original model description:
base_model:
- Orion-zhen/Meissa-Qwen2.5-7B-Instruct library_name: transformers tags:
- mergekit
- merge
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the passthrough merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
dtype: bfloat16
merge_method: passthrough
slices:
- sources:
- layer_range: [0, 8]
model: Orion-zhen/Meissa-Qwen2.5-7B-Instruct
- sources:
- layer_range: [4, 12]
model: Orion-zhen/Meissa-Qwen2.5-7B-Instruct
- sources:
- layer_range: [8, 16]
model: Orion-zhen/Meissa-Qwen2.5-7B-Instruct
- sources:
- layer_range: [12, 20]
model: Orion-zhen/Meissa-Qwen2.5-7B-Instruct
- sources:
- layer_range: [16, 24]
model: Orion-zhen/Meissa-Qwen2.5-7B-Instruct
- sources:
- layer_range: [20, 28]
model: Orion-zhen/Meissa-Qwen2.5-7B-Instruct
- Type
- qwen2
- Created
- Apr 8, 2025
- Updated
- Apr 8, 2025