Downloads · 30 days
5
31% of all-time downloads
Fischerboot_-_4b-Tinyllama-8bits
RichardErkhov/Fischerboot_-_4b-Tinyllama-8bits
Fischerboot_-_4b-Tinyllama-8bits 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
16
Public
Parameters
3.7B
3.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.9 GB · 100%
Parameter types
How the weights are stored.
I83.6B · 96%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
4b-Tinyllama - bnb 8bits
- Model creator: https://huggingface.co/Fischerboot/
- Original model: https://huggingface.co/Fischerboot/4b-Tinyllama/
Original model description:
base_model:
- Aculi/Tinyllama-2B 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, 32]
model: Aculi/Tinyllama-2B
- sources:
- layer_range: [13, 32]
model: Aculi/Tinyllama-2B
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [13, 32]
model: Aculi/Tinyllama-2B
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [32, 44]
model: Aculi/Tinyllama-2B
- Type
- llama
- Created
- Jan 18, 2025
- Updated
- Jan 18, 2025