Update README.md

README.md

@@ -54,8 +54,8 @@ pip install transformers>=4.57.0
 You can use OLMo with the standard HuggingFace transformers library:
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-olmo = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-RLZero-IF-7B")
-tokenizer = AutoTokenizer.from_pretrained("allenai/Olmo-3-RLZero-IF-7B")
+olmo = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-7B-RL-Zero-IF")
+tokenizer = AutoTokenizer.from_pretrained("allenai/Olmo-3-7B-RL-Zero-IF")
 message = ["Language modeling is "]
 inputs = tokenizer(message, return_tensors='pt', return_token_type_ids=False)
 # optional verifying cuda
@@ -68,7 +68,7 @@ print(tokenizer.batch_decode(response, skip_special_tokens=True)[0])
 
 For faster performance, you can quantize the model using the following method:
 ```python
-AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-RLZero-IF-7B", 
+AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-7B-RL-Zero-IF", 
     torch_dtype=torch.float16, 
     load_in_8bit=True)  # Requires bitsandbytes
 ```