The experimental 7B merge using Slerp method
Jan
company
Verified
AI & ML interests
Rethinking the Computer.
Recent Activity
View all activity
Reduce size of LLM but keep the same performance
The experimental family using Passthrough merge method
Test models with merge methods
The experimental merge with Solar as a base
The experimental 7B merge using Slerp method
Reduce size of LLM but keep the same performance
Fusion tokens
The experimental family using Passthrough merge method
The experimental family of MOE merge.
Test models with merge methods
These are merged models with Mistral as a base
The experimental merge with Solar as a base