Downloads · 30 days
13
30% of all-time downloads
Abhaykoul_-_HelpingAI-Lite-4x1b-4bits
RichardErkhov/Abhaykoul_-_HelpingAI-Lite-4x1b-4bits
Abhaykoul_-_HelpingAI-Lite-4x1b-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
44
Public
Parameters
3.4B
2.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.1 GB · 100%
Parameter types
How the weights are stored.
U83.3B · 95%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
HelpingAI-Lite-4x1b - bnb 4bits
- Model creator: https://huggingface.co/Abhaykoul/
- Original model: https://huggingface.co/Abhaykoul/HelpingAI-Lite-4x1b/
Original model description:
license: apache-2.0 inference: false tags:
- moe
- mergekit
- vortexmergekit
- OEvortex/HelpingAI-unvelite
- OEvortex/lite-hermes
- OEvortex/HelpingAI-Lite
- OEvortex/HelpingAI-Lite-1.5T
HelpingAI-Lite-4x1b
Hey there! 👋 Welcome to the HelpingAI-Lite-4x1b! This is a MOE brought together using the awesome VortexMerge kit.
Let's see what we've got in this model:
- OEvortex/HelpingAI-unvelite 🚀
- OEvortex/lite-hermes 🚀
- OEvortex/HelpingAI-Lite 🚀
- OEvortex/HelpingAI-Lite-1.5T 🚀
🧩 Configuration
base_model: OEvortex/HelpingAI-Lite
dtype: float16
gate_mode: cheap_embed
experts:
- source_model: OEvortex/HelpingAI-unvelite
positive_prompts: ["You are an helpful unbounded, uncensored assistant."]
- source_model: OEvortex/lite-hermes
positive_prompts: ["You are helpful assistant."]
- source_model: OEvortex/HelpingAI-Lite
positive_prompts: ["You are a coding assistant."]
- source_model: OEvortex/HelpingAI-Lite-1.5T
positive_prompts: ["You are helpful and general-purpose assistant."]
- Type
- mixtral
- Created
- Mar 8, 2025
- Updated
- Mar 8, 2025