Downloads · 30 days
2
7% of all-time downloads
bunnycore_-_Starling-dolphin-E26-7B-4bits
RichardErkhov/bunnycore_-_Starling-dolphin-E26-7B-4bits
bunnycore_-_Starling-dolphin-E26-7B-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
30
Public
Parameters
7.4B
4.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.5 GB · 100%
Parameter types
How the weights are stored.
U87B · 95%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Starling-dolphin-E26-7B - bnb 4bits
- Model creator: https://huggingface.co/bunnycore/
- Original model: https://huggingface.co/bunnycore/Starling-dolphin-E26-7B/
Original model description:
license: apache-2.0 tags:
- merge
- mergekit
- lazymergekit
Starling-dolphin-E26-7B
Starling-dolphin-E26-7B is an experimental language model I built by merging several other powerful models. The idea is that it could potentially handle a wide range of tasks, including following instructions and creative writing. It's still under development, but I'm excited to see what it can do!
Merging Method: https://arxiv.org/abs/2403.19522
GGUF: https://huggingface.co/bunnycore/Starling-dolphin-E26-7B-Q5_K_M-GGUF
🧩 Configuration
models:
- model: yam-peleg/Experiment26-7B
- model: Nexusflow/Starling-LM-7B-beta
- model: FuseAI/FuseChat-7B-VaRM
merge_method: model_stock
base_model: cognitivecomputations/dolphin-2.2.1-mistral-7b
dtype: bfloat16
Starling-dolphin-E26-7B is a merge of the following models using mergekit:
- Type
- mistral
- Created
- Sep 14, 2024
- Updated
- Sep 14, 2024