glbval/llm-course-hw2-reward-model

README.md

@@ -35,7 +35,7 @@ This model was trained with Reward.
 
 ### Framework versions
 
-- TRL: 0.16.1
+- TRL: 0.17.0
 - Transformers: 4.51.3
 - Pytorch: 2.6.0+cu124
 - Datasets: 3.5.0
@@ -50,7 +50,7 @@ Cite TRL as:
 ```bibtex
 @misc{vonwerra2022trl,
 	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
 	year         = 2020,
 	journal      = {GitHub repository},
 	publisher    = {GitHub},

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c9cf251dadfe50adaefe8af2d1aec18f150d6d49ab61cc4cc755360ec85669e
+oid sha256:c0bc18d6066481efc662d52e38a2e6ce1d7df886873fb1a5a595f1c259686ef5
 size 538092792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:151e1d6cecc44fcdaee0190e35568c90a1fa636680ce45c56df2f9fad438f0d6
+oid sha256:4aa5842cb94001514e61ec06056c1bff1fadfa68b3e8984798088724f9eaf743
 size 5368