From 1f0e1b7076a6e3c1b357dbb27c061a1fa53fa8a7 Mon Sep 17 00:00:00 2001
From: JustVugg <JustVugg@users.noreply.github.com>
Date: Mon, 13 Jul 2026 20:33:47 +0200
Subject: [PATCH] olmoe: reject quant_bits outside 2..8 (fixes degenerate
 output, #134) + correct ref.json to OLMoE-0125-Instruct oracle (#133)

#134: olmoe.c stored experts as int8_t but silently accepted any bits argv;
bits=16 (falsely documented as f32) truncated in quantize_rows -> wraparound
garbage experts. Guard bits to 2..8 with a clear error (int8 is token-exact;
f32 experts are not implemented here, unlike glm.c's fmt=0 path). Doc corrected.

#133: shipped ref.json was from a different checkpoint (continued 'The capital
of the United States is Washington'); the intended target is
allenai/OLMoE-1B-7B-0125-Instruct (per convert_olmoe.py), whose greedy oracle
continues 'The official language of France is French'. full_ids/text updated to
the reporter's verified oracle (engine is already token-exact 12/12 vs it).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---
 c/olmoe.c |  6 +++++-
 ref.json  | 31 ++++++++++++++++++++++++++++++-
 2 files changed, 35 insertions(+), 2 deletions(-)

diff --git a/c/olmoe.c b/c/olmoe.c
index 641f1d9..882e195 100644
--- a/c/olmoe.c
+++ b/c/olmoe.c
@@ -39,7 +39,7 @@ typedef struct { Slot *slots; int n, cap; } LCache;
 typedef struct {
     Cfg c;
     shards S;
-    int quant_bits;        /* bit di quantizzazione degli expert (2..8); 16 = f32 */
+    int quant_bits;        /* bit di quantizzazione degli expert (2..8); storage int8, niente f32 (#134) */
     float *embed, *lm_head, *final_norm;
     Layer *L;
     LCache *cache;          /* [n_layers] */
@@ -360,6 +360,10 @@ int main(int argc, char **argv) {
     if (!snap) { fprintf(stderr, "set SNAP=<snapshot directory>\n"); return 1; }
     int cap  = argc > 1 ? atoi(argv[1]) : 16;
     int bits = argc > 2 ? atoi(argv[2]) : 8;
+    if (bits < 2 || bits > 8) {   /* expert storage is int8_t: bits>8 truncates in quantize_rows (#134). f32 mode is not implemented here — int8 is already token-exact vs the oracle. */
+        fprintf(stderr, "quant_bits must be 2..8 (got %d); OLMoE experts are int8-backed, no f32 mode\n", bits);
+        return 1;
+    }
     const char *refpath = argc > 3 ? argv[3] : "ref.json";
 
     FILE *f = fopen(refpath, "rb"); if(!f){perror(refpath);return 1;}
diff --git a/ref.json b/ref.json
index 7c236ab..432e29b 100644
--- a/ref.json
+++ b/ref.json
@@ -1 +1,30 @@
-{"prompt": "The capital of France is", "prompt_ids": [510, 5347, 273, 6181, 310], "full_ids": [510, 5347, 273, 6181, 310, 7785, 15, 187, 187, 510, 5347, 273, 253, 1986, 2077, 310, 5041], "text": "The capital of France is Paris.\n\nThe capital of the United States is Washington"}
\ No newline at end of file
+{
+  "prompt": "The capital of France is",
+  "prompt_ids": [
+    510,
+    5347,
+    273,
+    6181,
+    310
+  ],
+  "full_ids": [
+    510,
+    5347,
+    273,
+    6181,
+    310,
+    7785,
+    15,
+    187,
+    187,
+    510,
+    3565,
+    3448,
+    273,
+    6181,
+    310,
+    5112,
+    15
+  ],
+  "text": "The capital of France is Paris.\n\nThe official language of France is French."
+}