highest reward model

README.md

@@ -24,7 +24,7 @@ You can then generate text as follows:
 ```python
 from transformers import pipeline
 
-generator = pipeline("text-generation", model="Bearnardd//tmp/tmpqxnceiox/Bearnardd/gpt2-imdb")
+generator = pipeline("text-generation", model="Bearnardd//tmp/tmpj7z4rtn6/Bearnardd/gpt2-imdb")
 outputs = generator("Hello, my llama is cute")
 ```
 
@@ -34,8 +34,8 @@ If you want to use the model for training or to obtain the outputs from the valu
 from transformers import AutoTokenizer
 from trl import AutoModelForCausalLMWithValueHead
 
-tokenizer = AutoTokenizer.from_pretrained("Bearnardd//tmp/tmpqxnceiox/Bearnardd/gpt2-imdb")
-model = AutoModelForCausalLMWithValueHead.from_pretrained("Bearnardd//tmp/tmpqxnceiox/Bearnardd/gpt2-imdb")
+tokenizer = AutoTokenizer.from_pretrained("Bearnardd//tmp/tmpj7z4rtn6/Bearnardd/gpt2-imdb")
+model = AutoModelForCausalLMWithValueHead.from_pretrained("Bearnardd//tmp/tmpj7z4rtn6/Bearnardd/gpt2-imdb")
 
 inputs = tokenizer("Hello, my llama is cute", return_tensors="pt")
 outputs = model(**inputs, labels=inputs["input_ids"])

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eccca47a9d62a8cc21c4e232d3fa6e2ea104e10cf213af76f96b101ead0c77f0
+oid sha256:ed3a08a2388ff8fe19cba8821cc5d48565198a319e8637bb0054a690b7a8812e
 size 510399237