Add main & ema weights for jpn

README.md

@@ -41,7 +41,7 @@ ema, main
   "num_labels": 2
 }
 ```
-Tokenizer file: `tokenizer_jpn_vs8192.json`
+Tokenizer file: `tokenizer_jpn_vs16384.json`
 
 ## Quick Usage
 ```python
@@ -68,6 +68,6 @@ print(outputs.logits)
 ```
 
 ## Notes
-- Converted on 2025-10-06T01:33:12.583890+00:00
+- Converted on 2025-10-07T00:19:03.971199+00:00
 - Weights are the exact trained parameters; no new layers were initialized.
 - Requires `trust_remote_code=True` due to custom architecture.

jpn-2gpu-250steps.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5e68c337c14b27bb6fd4e370b05d288a6e0cb4e286cdc54dd38f71853752321
+oid sha256:cb4e304b025875974c0f56764584d347d671a33798325a8ce6532dd96661d6fb
 size 503042738

jpn-2gpu-250steps_ema.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aaa024a4618b3ffa6f5a95bf03e1a49622d267e4b7a4781b5ad2bdbba6f1eb9
+oid sha256:e7664b4fdf2befe814de9d3176d1c7b9aece7d57ad2b2bf88443b78a3a737611
 size 503043438

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f7de03dfdfaa25a69bb4dee4690b46d557729d97cf08dcaa902dad003955ef3
+oid sha256:20d43c141173dbb347393d9dd47b7646426103f75a1b9bb9662c34133e6b25d9
 size 553332392

model_ema.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f7de03dfdfaa25a69bb4dee4690b46d557729d97cf08dcaa902dad003955ef3
+oid sha256:20d43c141173dbb347393d9dd47b7646426103f75a1b9bb9662c34133e6b25d9
 size 553332392

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bef4bc073b6a11d90982e79f1f03045cc3b5a30b8b394fc75fd6522a52ba7b90
+oid sha256:e6ecf6f37465e7e3acde5bfba315d8b2a6fd7d443a10935fdeb92f3158305f9e
 size 503029622