初始化项目，由ModelHub XC社区提供模型

Model: mnoukhov/pythia410m-sft-tldr Source: Original Platform
2026-05-30 14:21:21 +08:00
commit 4bb3a5553f
215 changed files with 118927 additions and 0 deletions
--- a/code/configs/create_rlhf_410m.yml
+++ b/code/configs/create_rlhf_410m.yml
@@ -0,0 +1,11 @@
+output_dir: /home/toolkit/huggingface/openai_summarize_tldr_rbaseline
+train_split: train
+eval_split: valid[:2000]
+###
+model_name: mnoukhov/pythia410m-tldr-sft-rm-adapter
+new_column_name: reward_baseline
+dataset_name: CarperAI/openai_summarize_tldr
+load_in_8bit: False
+fp16: True
+batch_size: 32
+max_length: 560