From 3de4677e5340824e8b420f8b9ad33522682a8f80 Mon Sep 17 00:00:00 2001 From: Niki Howe Date: Mon, 18 Mar 2024 22:39:17 -0400 Subject: [PATCH 1/2] Fix example --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 6425f431ab..56cf0ab5d2 100644 --- a/README.md +++ b/README.md @@ -138,14 +138,14 @@ model = AutoModelForCausalLMWithValueHead.from_pretrained('gpt2') model_ref = create_reference_model(model) tokenizer = AutoTokenizer.from_pretrained('gpt2') +tokenizer.pad_token = tokenizer.eos_token # initialize trainer -ppo_config = PPOConfig( - batch_size=1, -) +ppo_config = PPOConfig(batch_size=1, mini_batch_size=1) # encode a query query_txt = "This morning I went to the " + query_tensor = tokenizer.encode(query_txt, return_tensors="pt") # get model response From 82e1849be753ab006e05166aa03dd715660a1c36 Mon Sep 17 00:00:00 2001 From: Niki Howe Date: Mon, 18 Mar 2024 22:42:30 -0400 Subject: [PATCH 2/2] Delete newline --- README.md | 1 - 1 file changed, 1 deletion(-) diff --git a/README.md b/README.md index 56cf0ab5d2..1ea8b9d86d 100644 --- a/README.md +++ b/README.md @@ -145,7 +145,6 @@ ppo_config = PPOConfig(batch_size=1, mini_batch_size=1) # encode a query query_txt = "This morning I went to the " - query_tensor = tokenizer.encode(query_txt, return_tensors="pt") # get model response