Skip to content

About

Knowledge distillation from Qwen2.5-Coder-7B-Instruct into the 0.5B model, plus hand-written GPTQ and QAT (STE, LSQ) in CodeAlign-Runtime's exact INT4 format. The compressed model is evaluated through the engine that serves it.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Repository files navigation

CodeAlign-Distill

Knowledge distillation from Qwen2.5-Coder-7B-Instruct into the 0.5B model, plus hand-written GPTQ and QAT (STE, LSQ) in CodeAlign-Runtime's exact INT4 format. The compressed model is evaluated through the engine that serves it.

About

Knowledge distillation from Qwen2.5-Coder-7B-Instruct into the 0.5B model, plus hand-written GPTQ and QAT (STE, LSQ) in CodeAlign-Runtime's exact INT4 format. The compressed model is evaluated through the engine that serves it.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages