Downloads · 30 days
12
46% of all-time downloads
L-RAGE_-_3_PRYMMAL-ECE-7B-SLERP-V1-4bits
RichardErkhov/L-RAGE_-_3_PRYMMAL-ECE-7B-SLERP-V1-4bits
L-RAGE_-_3_PRYMMAL-ECE-7B-SLERP-V1-4bits 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
26
Public
Parameters
1.6B
1.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.2 GB · 99%
Parameter types
How the weights are stored.
U81.3B · 84%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
3_PRYMMAL-ECE-7B-SLERP-V1 - bnb 4bits
- Model creator: https://huggingface.co/L-RAGE/
- Original model: https://huggingface.co/L-RAGE/3_PRYMMAL-ECE-7B-SLERP-V1/
Original model description:
base_model:
- LilRg/ECE-1B-merge-PRYMMAL
- Marsouuu/Qwen1_78-ECE-PRYMMAL-Martial library_name: transformers tags:
- mergekit
- merge license: apache-2.0
merged_model
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: Marsouuu/Qwen1_78-ECE-PRYMMAL-Martial
layer_range: [0, 28]
- model: LilRg/ECE-1B-merge-PRYMMAL
layer_range: [0, 28]
merge_method: slerp
base_model: Marsouuu/Qwen1_78-ECE-PRYMMAL-Martial
parameters:
t:
- filter: self_attn
value: [0, 0.25, 0.5, 0.75, 1]
- filter: mlp
value: [1, 0.75, 0.5, 0.25, 0]
- value: 0.5
dtype: bfloat16
- Type
- qwen2
- Created
- Jan 24, 2025
- Updated
- Jan 24, 2025