r-three/tulu3-8b-fft-multitask
Updated • 7
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models
Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
r-three/lora_baseline_10_lr3e-4_step100_rank64_xnli_th
Updated • 8
r-three/lora_baseline_10_lr3e-4_step100_rank64_xnli_hi
Updated • 6
r-three/lora_baseline_10_lr3e-4_step100_rank64_xnli_fr
Updated • 5
r-three/lora_baseline_10_lr3e-4_step100_rank64_xnli_es
Updated • 4
r-three/lora_baseline_10_lr3e-4_step100_rank64_xnli_en
Updated • 2
r-three/lora_baseline_10_lr3e-4_step100_rank64_xnli_de
Updated • 2
r-three/lora_baseline_10_lr3e-4_step100_rank64_web_of_lies
Updated • 3
r-three/lora_baseline_10_lr3e-4_step100_rank64_unit_conversion_si_conversion
Updated • 5
r-three/lora_baseline_10_lr3e-4_step100_rank64_unarxive_imrad_clf
Updated • 3
r-three/lora_baseline_10_lr3e-4_step100_rank64_typescript_chunks
Updated • 3
r-three/lora_baseline_10_lr3e-4_step100_rank64_twitter_financial_news_sentiment
Updated • 3
r-three/lora_baseline_10_lr3e-4_step100_rank64_twitter_complaints
Updated • 3
r-three/lora_baseline_10_lr3e-4_step100_rank64_tweet_topic_single
Updated • 2
r-three/lora_baseline_10_lr3e-4_step100_rank64_tweet_eval_hate
Updated • 2
r-three/lora_baseline_10_lr3e-4_step100_rank64_tracking_shuffled_objects
Updated • 2
r-three/lora_baseline_10_lr3e-4_step100_rank64_toxic_chat
Updated • 2
r-three/lora_baseline_10_lr3e-4_step100_rank64_temporal_sequences
Updated • 3
r-three/lora_baseline_10_lr3e-4_step100_rank64_super_glue_wsc
Updated • 2
r-three/lora_baseline_10_lr3e-4_step100_rank64_super_glue_wic
Updated • 3
r-three/lora_baseline_10_lr3e-4_step100_rank64_super_glue_rte
Updated • 2
r-three/lora_baseline_10_lr3e-4_step100_rank64_super_glue_copa
Updated • 2
r-three/lora_baseline_10_lr3e-4_step100_rank64_super_glue_boolq
Updated • 3
r-three/lora_baseline_10_lr3e-4_step100_rank64_stackoverflow_questions
Updated • 3
r-three/lora_baseline_10_lr3e-4_step100_rank64_sports_understanding
Updated • 2
r-three/lora_baseline_10_lr3e-4_step100_rank64_sciq
Updated • 4
r-three/lora_baseline_10_lr3e-4_step100_rank64_reasoning_about_colored_objects
Updated • 2
r-three/lora_baseline_10_lr3e-4_step100_rank64_race_high
Updated • 3
r-three/lora_baseline_10_lr3e-4_step100_rank64_quail
Updated • 2
r-three/lora_baseline_10_lr3e-4_step100_rank64_qasc
Updated • 3