Clean tokenizer swap migration

This commit is contained in:
Codex
2026-06-18 10:10:57 +00:00
commit 5d1e9c4bc3
37 changed files with 9574 additions and 0 deletions
+12
View File
@@ -0,0 +1,12 @@
#!/usr/bin/env bash
set -euo pipefail
ROOT=${ROOT:-/ssd/yi/Tokenizer_Swap}
BASE_MODEL=${BASE_MODEL:-/ssd/yi/tokenizer_swap_cepe/models/Qwen3-0.6B}
DSV_TOKENIZER=${DSV_TOKENIZER:-/ssd/yi/tokenizer_swap_cepe/models/tokenizers/dsv4_flash}
OUT=${OUT:-$ROOT/model_building/generated_models/Qwen3-0.6B-DSV4-tokenizer-remap-v2}
python "$ROOT/model_building/build_qwen3_dsv4_remap_checkpoint_v2.py" \
--qwen-model "$BASE_MODEL" \
--dsv-tokenizer "$DSV_TOKENIZER" \
--out "$OUT"