CodeAlpaca – Instruction following code generation model

Re:CodeAlpaca – Instruction following code generation model by sahil_chaudhary on Saturday March 25, 2023 @02:44PM (#35305708)

All included it costs under 70$ for the 13B model. Training 65B now so will report what that will cost.

[ Parent | on HN ]

Re:CodeAlpaca – Instruction following code generation model by sillysaurusx on Saturday March 25, 2023 @03:43PM (#35306404)

Please do! Also please include how you’re calculating the costs.

[ Parent | on HN ]

Re:CodeAlpaca – Instruction following code generation model by alex_sf on Saturday March 25, 2023 @03:49PM (#35306482)

For the 65B fine tune, did you add another A100 node? Or just drop batch size?

Any chance you’re up to sharing the training parameters?

[ Parent | on HN ]

Re:CodeAlpaca – Instruction following code generation model by sahil_chaudhary on Saturday March 25, 2023 @03:51PM (#35306508)

Dropping the batch size

[ Parent | on HN ]