Perspectives for first principles prompt engineering
•
16
Don't burn out! Lighten up again will you.
it mixed up stuff in the output, gave weird answers. didn't have that problem with other models. maybe the update they released sovled that issue, I just never cared, given the alternatives.
I got some weird results, since there are a lot of other models in that performance-parameter range, I just didn't try anymore.
@staticmethod
def marchenko_pastur_threshold(sigma, n, m):
beta = n / m if n < m else m / n
threshold = sigma * np.sqrt((1 + np.sqrt(beta))**2)
return thr
Want this to run on CPU
Exciting!
X+EN
, where X represents the target language and EN
stays fixed, these models specialize in both monolingual tasks and cross-lingual retrieval tasks, crossing from X to EN.jina-embeddings-v3