I see that their distilled model is much worse than StableLM 3E1T, so the finetuning improved a lot. Unfortunately they didn’t release the datasets(Would that still be considered Open Source?). Also I’m pretty sure my StableLM finetunes are better in the Open LLM Benchmarks, they just don’t allow StableLM models to be submitted.
this post was submitted on 18 Nov 2023
1 points (100.0% liked)
LocalLLaMA
3 readers
1 users here now
Community to discuss about Llama, the family of large language models created by Meta AI.
founded 1 year ago
MODERATORS
Are your finetunes full training or lora/qlora?