Update README.md

README.md

@@ -8,7 +8,6 @@
 
 The reward model is trained from the base model [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it). 
 
-The training process is identical to [RM-Gemma-7B](https://huggingface.co/weqweasdas/RM-Gemma-7B) but with a max-length of 4096 thanks to more GPU resources. 
 
 ## Model Details
 
@@ -48,11 +47,11 @@ We train the model for one epoch with a learning rate of 5e-6, batch size 256, c
 
 ```python
   from transformers import AutoTokenizer, pipeline
-  rm_tokenizer = AutoTokenizer.from_pretrained("weqweasdas/RM-Gemma-7B-4096")
+  rm_tokenizer = AutoTokenizer.from_pretrained("weqweasdas/RM-Gemma-7B")
   device = 0 # accelerator.device
   rm_pipe = pipeline(
       "sentiment-analysis",
-      model="weqweasdas/RM-Gemma-7B-4096",
+      model="weqweasdas/RM-Gemma-7B",
       #device="auto",
       device=device,
       tokenizer=rm_tokenizer,