Thanks for the detailed feedback! You're right that v1 has its quirks and we've experienced the repetition issues too.
Great to hear v1.5 is coming soon. Actually we built a platform called AceSteps using this model(v1). You can create music, mint it as an NFT, tokenize it into tradeable shares, and earn from ad revenue. It's a Farcaster Mini-App on Base Network.
Planning to integrate v1.5 once it drops.
Didn't know they had a Discord server, thanks for the info.
this is a very good study. it reminded me of a time a few years ago when i found things like "few shots" and similar things ridiculous; that was a big mistake.
biggest gap in open source datasets is high quality, diverse data for ai, especially in scientific reasoning, multilingual, and multimodal domains
open interpreter's my fave 'cause it runs locally, no cloud, and speeds up coding from the terminal
import gensim
from sklearn.decomposition import PCA
import matplotlib
import matplotlib.pyplot as plt
model = gensim.models.Word2Vec.load('white_moves.model')
dict_moves = model.wv.vocab
dict_moves_appr = {}
for k in dict_moves:
if not k.startswith('->'):
continue
dict_moves_appr[k] = dict_moves[k]
X = model[model.wv.vocab]
pca = PCA(n_components=2)
result = pca.fit_transform(X)
fig, ax = plt.subplots()
ax.plot(Y[:, 0], Y[:, 1], 'o')
ax.set_title('White moves')
lab = list(dict_moves_appr)
for i, lb in enumerate(lab):
plt.annotate(lb, xy=(Y[i, 0], Y[i, 1]))
plt.show()