dim={cfg.dim} (v1: 768), n_layers={cfg.n_layers}, n_heads={cfg.n_heads}
(head_dim={cfg.dim // cfg.n_heads} — same as v1)max_seq_len={cfg.max_seq_len} (v1: 512), vocab_size={cfg.vocab_size}channel_top_k={cfg.channel_top_k}, token_top_k={cfg.token_top_k}
(same sparsity ratios as v1)iamtarun/python_code_instructions_18k_alpaca)real_syntax_valid: {best_syntax:.1f}% on held-out real Python instructions1import torch
2import sentencepiece as spm
3
4# Load checkpoint
5ckpt = torch.load("cofos_best.pt", map_location="cpu")
6cfg_dict = ckpt["config"]
7
8# Instantiate model architecture
9# model = SparseMind(Config(**cfg_dict))
10# model.load_state_dict(ckpt["model"])
11# model.eval()