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/tmp7_kqv2lm/Bearnardd/gpt2-imdb")
+generator = pipeline("text-generation", model="Bearnardd//tmp/tmpdn3fa8xo/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/tmp7_kqv2lm/Bearnardd/gpt2-imdb")
-model = AutoModelForCausalLMWithValueHead.from_pretrained("Bearnardd//tmp/tmp7_kqv2lm/Bearnardd/gpt2-imdb")
+tokenizer = AutoTokenizer.from_pretrained("Bearnardd//tmp/tmpdn3fa8xo/Bearnardd/gpt2-imdb")
+model = AutoModelForCausalLMWithValueHead.from_pretrained("Bearnardd//tmp/tmpdn3fa8xo/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 sha256:4093523d5d0f33d53973ce82833c7df9dbb165b1c5dc5afb43f7b071c7292df6
+oid sha256:f72e81c1cfd144579c71a04b48a5729db5ebc1b4866e07e32d0106ad5de889d6
 size 510399237