inference.py

import torch
import torch.nn.functional as F
from hrt import ModelConfig, HierarchicalRadialTransformerV7

device = "cuda" if torch.cuda.is_available() else "cpu"

# 1. Initialize Configuration matching training
cfg = ModelConfig(
    d_model=768,
    d_ff=3072,
    n_outer_latents=512,
    n_outer_cycles=6,
    n_inner_cycles=8,
    n_center_latents=16,
    routing_k=64,
    n_outer_heads=12,
    n_inner_heads=12,
    n_latent_heads=12,
    vocab_size=257,
    max_seq_len=131072,
    use_qk_norm=True,
    use_rezero=True,
    use_compaction=True,
    use_internalization=True,
    use_jfb=True,
    use_q_cache=True,
)

# 2. Load model & weights
model = HierarchicalRadialTransformerV7(cfg).to(device)
weights = torch.load("hrt_v7_148m_weights.pt", map_location=device)
model.load_state_dict(weights["model"] if "model" in weights else weights)
model.eval()

# 3. Autoregressive Byte-level Generation
def generate(prompt: str, max_new_bytes: int = 120, temp: float = 0.5, top_k: int = 5):
    prompt_bytes = list(prompt.encode("utf-8"))
    prompt_ids = torch.tensor([prompt_bytes], dtype=torch.long, device=device)
    
    with torch.no_grad():
        prompt_emb = model.tok_emb(prompt_ids)
        logits, cache = model._init_generation_cache(prompt_emb)
        out_bytes = list(prompt_bytes)

        for _ in range(max_new_bytes):
            l = logits / max(temp, 1e-5)
            if top_k > 0:
                v, _ = torch.topk(l, min(top_k, l.size(-1)))
                l[l < v[:, [-1]]] = float("-inf")
            
            nxt = torch.multinomial(F.softmax(l, dim=-1), num_samples=1)
            nxt_id = nxt.item()
            if nxt_id == 256:  # EOS
                break
                
            out_bytes.append(nxt_id)
            nxt_emb = model.tok_emb(nxt)
            logits = model.step_generation(nxt_emb, cache)
            
    return bytes(out_bytes).decode("utf-8", errors="replace")

# Test completion
print(generate("def", max_new_bytes=100))