From a269aff51d5daa664212c034e3c451bc07b28f8f Mon Sep 17 00:00:00 2001 From: 51616 Date: Fri, 29 Aug 2025 02:36:00 +0000 Subject: [PATCH] fix empty q_list --- data/self_generate_qa.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/data/self_generate_qa.py b/data/self_generate_qa.py index f9f4d11..93f4fe7 100644 --- a/data/self_generate_qa.py +++ b/data/self_generate_qa.py @@ -322,7 +322,6 @@ def self_generate( ds = ds.take(50) ds = ds.filter(filter_none, batched=False, num_proc=8) - print(f"0. {len(ds)=}") tk = get_tokenizer(args.vllm_model, train=True) @@ -363,7 +362,7 @@ def self_generate( ctxs = [sample["context"] for sample in ds] - questions = ds["prompts"] + questions = [q_list for q_list in ds["prompts"] if len(q_list) > 0] # for sample in ds: # if ("type" not in sample) or ( # "type" in sample and sample["type"] == "question"