Model is functionally retarded
#6
by
MilitantHitchhiker
- opened
This model is functionally retarded and cannot complete objective tasks related to speech and language.
Kinda of expected for a model of this size if you want average (and not above average sota performance) model have to be at least 7B
It well known for neural network that the lower the base number you use fastest it is ie base 1, base 2 and base 3. Done alot work on this for simple nn they also only class of instant trained instant inference nn. However replicating that as base 1 transformers (nobody done this well I have, unary is fastest, not sure why it but just is) followed by binary, tenary etc.
They also difficult to get right as well
The problem is the training data and objectively invalid "safety" enforcement.