The experimental 7B merge using Slerp method

Jan
company
Verified
AI & ML interests
Rethinking the Computer.
Recent Activity
View all activity
Organization Card
See more models at: https://huggingface.co/jan-hq
Collections
9
models
98

janhq/250413-llama-3.1-8b-instruct-grpo-01-no-retry
Updated

janhq/250412-llama-3.2-3b-instruct-grpo-02-no-retry
Updated

janhq/250412-llama-3.2-3b-instruct-grpo-02
Updated

janhq/250412-llama-3.2-3b-instruct-grpo-01
Updated

janhq/250409-llama-3.2-3b-instruct-grpo-01-no-retry
Updated

janhq/250409-llama-3.2-3b-instruct-grpo-01-no-retry-350-lora-gguf
Updated

janhq/250409-llama-3.2-3b-instruct-grpo-01-no-retry-350-lora
Text Generation
•
Updated

janhq/250404-llama-3.2-3b-instruct-grpo-03-s250-gguf
Updated
•
6

janhq/250404-llama-3.2-3b-instruct-grpo-03-s250
Updated
•
160

janhq/250404-llama-3.2-3b-instruct-grpo-03
Updated
datasets
None public yet