Update model card

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: unsloth/Qwen3-4B-Instruct-2507
+base_model: Qwen/Qwen3-4B-Instruct-2507
 library_name: peft
 tags:
 - lora
@@ -14,7 +14,7 @@ This repository contains a LoRA adapter checkpoint for the Chainer policy after
 
 ## Base model
 
-- `unsloth/Qwen3-4B-Instruct-2507`
+- `Qwen/Qwen3-4B-Instruct-2507`
 
 ## Artifact type
 
@@ -33,7 +33,7 @@ This repository contains a LoRA adapter checkpoint for the Chainer policy after
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from peft import PeftModel
 
-base_model_id = "unsloth/Qwen3-4B-Instruct-2507"
+base_model_id = "Qwen/Qwen3-4B-Instruct-2507"
 adapter_repo_id = "Anonymous5345345/anonymous-chainer-grpo-epoch2"
 
 tokenizer = AutoTokenizer.from_pretrained(base_model_id)