MathBite
/

self_corrective_llama_3.1_8B

4-bit precision

Model card Files Files and versions Community

self_corrective_llama_3.1_8B / modeling.py

Commit History

inference update

b92f27a
verified

MathBite commited on about 18 hours ago

updated inference logic to make more robust correction

d048846
verified

MathBite commited on about 18 hours ago

Upload fine-tuned and merged model.

fef3dc9
verified

MathBite commited on 11 days ago