39 lines
679 B
Markdown
39 lines
679 B
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
base_model:
|
||
|
|
- Qwen/Qwen2.5-Coder-7B-Instruct
|
||
|
|
- Qwen/Qwen2.5-Math-7B-Instruct
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- qwen
|
||
|
|
- mergekit
|
||
|
|
- slerp
|
||
|
|
- math
|
||
|
|
- code
|
||
|
|
- reasoning
|
||
|
|
- local-ai
|
||
|
|
---
|
||
|
|
|
||
|
|
# Kepler Reasoning 7B
|
||
|
|
|
||
|
|
Kepler Reasoning 7B is a local code + math reasoning model made by merging:
|
||
|
|
|
||
|
|
- Qwen/Qwen2.5-Coder-7B-Instruct
|
||
|
|
- Qwen/Qwen2.5-Math-7B-Instruct
|
||
|
|
|
||
|
|
Merge method: SLERP.
|
||
|
|
|
||
|
|
Goal: strong local coding + math reasoning.
|
||
|
|
|
||
|
|
## Intended Use
|
||
|
|
|
||
|
|
- coding help
|
||
|
|
- Python problem solving
|
||
|
|
- math reasoning
|
||
|
|
- algebra and word problems
|
||
|
|
- local inference after GGUF quantization
|
||
|
|
|
||
|
|
## Limitations
|
||
|
|
|
||
|
|
This is a 7B local model. It is not expected to beat frontier cloud models overall.
|