Upload glint_parity_eval.py with huggingface_hub

glint_parity_eval.py

@@ -180,14 +180,12 @@ def evaluate_arc_easy(logits_fn, tokenizer, device):
 # WIRING NASZEGO MODELU (Monter: wypelnij) -- to jedyna czesc nie-Glint.
 # ---------------------------------------------------------------------------
 def load_our_model(ckpt_path, tokenizer_path, device):
-    """Zwroc (logits_fn, tokenizer). logits_fn(ids[B,T]) -> logits[B,T,REAL_VOCAB].
-    TODO Monter: zaimportuj nasza GPT-klase (z train-kodu gollem), zaladuj ckpt,
-    ustaw eval()+to(device). Nasz block=1024 > 256 chunki Glinta wiec forward OK.
-    Wazne: przytnij logits do realnego vocab (bez padded-vocab) jesli mamy padding.
-    Ponizej szkielet - dopasuj do naszej sygnatury forward()."""
+    """Zwroc (logits_fn, tokenizer). cfg-aware: ckpt["config"] (Qwen3-arch: rope/swiglu/
+    qk_norm/value_residual) -> GPT(...,cfg); legacy nanoGPT (bez config) -> stary 5-arg.
+    Fix Hart 2026-09-24: 64M-flagship = Qwen3, GPT() wymaga cfg + brak pos.weight (rope)."""
     import importlib.util, os
-    tokenizer = HFTokenizer.from_file(tokenizer_path)  # BPE-12k tokenizer.json
-    # import naszej klasy GPT z train_gpt_ref.py (typowe lokalizacje: pod / lokalnie)
+    from types import SimpleNamespace
+    tokenizer = HFTokenizer.from_file(tokenizer_path)
     gpt_src = None
     for cand in ("/workspace/gollem/corpus/scripts/train_gpt_ref.py",
                  os.path.join(os.path.dirname(os.path.abspath(__file__)), "train_gpt_ref.py"),
@@ -201,15 +199,23 @@ def load_our_model(ckpt_path, tokenizer_path, device):
     GPT = tgr.GPT
     ck = torch.load(ckpt_path, map_location="cpu", weights_only=False)
     sd = ck["model"] if isinstance(ck, dict) and "model" in ck else ck
-    sd = {k.replace("_orig_mod.", ""): v for k, v in sd.items()}  # strip torch.compile
-    vocab, n_embd = sd["tok.weight"].shape
-    block = sd["pos.weight"].shape[0]
-    n_layer = 1 + max(int(k.split(".")[1]) for k in sd if k.startswith("blocks."))
-    n_head = int(os.environ.get("N_HEAD", "6"))  # nie w wagach; 16M-scan=6, 32M=9
-    model = GPT(int(vocab), int(n_layer), int(n_embd), int(n_head), int(block))
-    model.load_state_dict(sd, strict=True)
+    sd = {k.replace("_orig_mod.", ""): v for k, v in sd.items()}
+    cfg_d = ck.get("config") if isinstance(ck, dict) else None
+    if cfg_d is not None:
+        cfg = SimpleNamespace(**cfg_d)
+        model = GPT(int(cfg_d["vocab"]), int(cfg_d["n_layer"]), int(cfg_d["n_embd"]),
+                    int(cfg_d["n_head"]), int(cfg_d["block"]), cfg)
+        h = cfg_d["n_head"]
+    else:
+        vocab, n_embd = sd["tok.weight"].shape
+        block = sd["pos.weight"].shape[0]
+        n_layer = 1 + max(int(k.split(".")[1]) for k in sd if k.startswith("blocks."))
+        h = int(os.environ.get("N_HEAD", "6"))
+        model = GPT(int(vocab), int(n_layer), int(n_embd), int(h), int(block))
+    miss, unexp = model.load_state_dict(sd, strict=False)
+    assert not unexp and miss in ([], ["head.weight"]), (miss, unexp)
     model.eval().to(device)
-    print(f"[load_our_model] vocab={vocab} L={n_layer} d={n_embd} h={n_head} block={block} dev={device}", flush=True)
+    print(f"[load_our_model] cfg={cfg_d is not None} h={h} dev={device} loaded-ok", flush=True)
     def logits_fn(ids):
         out = model(ids)
         logits = out[0] if isinstance(out, (tuple, list)) else out