Use cross-version split Qwen3-MoE expert layout

README.md

@@ -66,7 +66,10 @@ BOS 8190, and PAD 8191.
 | Maximum exported context | 32,768 |
 | Published weight dtype | BF16 |
 
-The checkpoint uses the stock Transformers `Qwen3MoeForCausalLM` layout.
+The checkpoint uses the stock Transformers `Qwen3MoeForCausalLM` layout. MoE
+expert weights are stored as per-expert `gate_proj`, `up_proj`, and `down_proj`
+tensors for compatibility across Transformers releases; loading has been tested
+with Transformers 4.57.1 and 5.11.0.
 
 ## Tokenizer
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6127bc3df898c2e30efee0cf9f01e13035c895af6f618e4830fea589ca30d91
-size 344125920
+oid sha256:88d6175774185c2a373126a46b064d0a9c3a2bc9a0546d8b502f0d76d0a8318c
+size 344168016