Upload 5 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tok_corpus.txt filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,28 @@
+{
+  "architecture": "LoopedTransformer",
+  "seq_len": 256,
+  "vocab_size": 16384,
+  "d_model": 736,
+  "n_heads": 8,
+  "d_ff": 1472,
+  "dropout": 0.05,
+  "mtp_depth": 1,
+  "mtp_lambda": 0.3,
+  "min_loops": 2,
+  "max_loops": 8,
+  "eval_loops": 6,
+  "tokenizer_dir": "tokenizer",
+  "special_tokens": {
+    "pad_id": 0,
+    "bos_id": 1,
+    "eos_id": 2
+  },
+  "total_params": 24176128,
+  "tied_weights": [
+    {
+      "kept": "tok_emb.weight",
+      "dropped": "head.weight"
+    }
+  ],
+  "notes": "Custom looped-transformer architecture (shared CoreBlock iterated min_loops-max_loops times) with MTP auxiliary head, trained with the Muon optimizer. NOT a GGUF/llama.cpp-compatible architecture -- load with this repo's LoopedTransformer class + safetensors.torch.load_file(), not with llama.cpp or similar. IMPORTANT: 'tied_weights' above lists parameter pairs that share the same underlying tensor in the original model (weight tying) and were de-duplicated for safetensors export (which refuses to save aliased tensors). After loading, manually re-tie them, e.g. for the default case: model.head.weight = model.tok_emb.weight -- do this BEFORE calling load_state_dict with strict=True, or load with strict=False and assign the tied tensor afterward."
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8cc15b3c1cd60be213630eaf422cc66b02e1d58f7fc880cd310fc29f6ff739e
+size 96707128

tok_corpus.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21879315a997c9e728731124f45c96099a5b516f926fd0260b14c64765b15e0b
+size 181468126