From 3bfb48b00b4803d34451c40f78b7456f34e70c83 Mon Sep 17 00:00:00 2001 From: Dongfu Date: Wed, 17 Jan 2024 16:07:32 -0500 Subject: [PATCH] rename PairRM to PairRM 0.4B --- src/alpaca_eval/models_configs/pairrm-tulu-2-13b/configs.yaml | 2 +- src/alpaca_eval/models_configs/pairrm-tulu-2-70b/configs.yaml | 2 +- .../models_configs/pairrm-zephyr-7b-beta/configs.yaml | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/src/alpaca_eval/models_configs/pairrm-tulu-2-13b/configs.yaml b/src/alpaca_eval/models_configs/pairrm-tulu-2-13b/configs.yaml index dbb1fac3..820bdf6d 100644 --- a/src/alpaca_eval/models_configs/pairrm-tulu-2-13b/configs.yaml +++ b/src/alpaca_eval/models_configs/pairrm-tulu-2-13b/configs.yaml @@ -12,5 +12,5 @@ pairrm-tulu-2-13b: do_sample: False best_of: 16 # number of completions to generate, using PairRM to select the best one batch_size: 800 - pretty_name: "PairRM+Tulu 2+DPO 13B (best-of-16)" + pretty_name: "PairRM 0.4B+Tulu 2+DPO 13B (best-of-16)" link: "https://huggingface.co/llm-blender/PairRM" \ No newline at end of file diff --git a/src/alpaca_eval/models_configs/pairrm-tulu-2-70b/configs.yaml b/src/alpaca_eval/models_configs/pairrm-tulu-2-70b/configs.yaml index 6f4e0143..b77176c2 100644 --- a/src/alpaca_eval/models_configs/pairrm-tulu-2-70b/configs.yaml +++ b/src/alpaca_eval/models_configs/pairrm-tulu-2-70b/configs.yaml @@ -12,5 +12,5 @@ pairrm-tulu-2-70b: do_sample: False best_of: 16 # number of completions to generate, using PairRM to select the best one batch_size: 800 - pretty_name: "PairRM+Tulu 2+DPO 70B (best-of-16)" + pretty_name: "PairRM 0.4B+Tulu 2+DPO 70B (best-of-16)" link: "https://huggingface.co/llm-blender/PairRM" \ No newline at end of file diff --git a/src/alpaca_eval/models_configs/pairrm-zephyr-7b-beta/configs.yaml b/src/alpaca_eval/models_configs/pairrm-zephyr-7b-beta/configs.yaml index e401f49d..4ccd6119 100644 --- a/src/alpaca_eval/models_configs/pairrm-zephyr-7b-beta/configs.yaml +++ b/src/alpaca_eval/models_configs/pairrm-zephyr-7b-beta/configs.yaml @@ -10,5 +10,5 @@ pairrm-zephyr-7b-beta: top_p: 1.0 do_sample: True best_of: 16 # number of completions to generate, using PairRM to select the best one - pretty_name: "PairRM+Zephyr 7B Beta (best-of-16)" + pretty_name: "PairRM 0.4B+Zephyr 7B Beta (best-of-16)" link: "https://huggingface.co/llm-blender/PairRM" \ No newline at end of file