Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
Show HN: RLHF and Lora finetuning to mistralai 7B with DeepSpeed learning
github.com/genji970
1 point
genji970
10 months ago
Using multiple gpus, training 7B model with lora and RLHF with external dataset.
No comment yet
Show HN: RLHF and Lora finetuning to mistralai 7B with DeepSpeed learning | Heykuki News