Hello!

By popular demand I am planning a fine-tune of https://huggingface.co/dreamgen/opus-v0-7b on top of Yi-34B and wonder whether to use the 200K as the base.

The regular Yi-34B seems slightly better than Yi-34B-200K on standard benchmarks, but I wonder how it “feels” and whether the loss of performance on short context is worth it, given that the regular version can be used up to 32K tokens.

(Yi-34B vs Yi-34B-200K)

Did anyone try an analysis of these 2 models on various sequence lengths (<4K, <8K, <16K, etc.)?

  • Sabin_Stargem@alien.topB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    Doctor Shotgun has made some Yi-34bs with Airoboros and LimaRP. You might want to talk with them and try out their version. Measure twice and cut once, as they say.