(self, n_embed, n_experts, n_hidden, top_k, dropout)

(self, n_embed, n_heads, block_size, dropout)

(self, idx, max_new_tokens=100)

(self, n_embed, head_size, block_size, dropout)

(self, n_embed, n_heads, head_size, block_size, dropout)

(self, n_embed, n_hidden, dropout)

(self, hyperparameters, device="cpu")

(self, n_embed, head_size, block_size, dropout)

(self, n_embed, n_heads, head_size, block_size, dropout)

(self, n_embed, n_hidden, dropout)

(self, n_embed, n_experts, top_k)

(self, n_embed, n_heads, n_experts, top_k, block_size, dropout)

(self, hyperparameters, device="cpu")

(self, x)

(self, x)

(self, x)

(self, x)

(self, idx, targets=None)

(self, x)

(self, x)

(self, x)

(self, x)

(self, x)

(self, x)

(self, idx, targets=None)

(self, idx, max_new_tokens=100)