Active filters: kto
PaulD/llama3_false_positives_1101_KTO_optimised_model
chchen/Llama-3.1-8B-Instruct-KTO-100
Updated • 14
chchen/Llama-3.1-8B-Instruct-KTO-200
chchen/Llama-3.1-8B-Instruct-KTO-300
chchen/Llama-3.1-8B-Instruct-KTO-400
chchen/Llama-3.1-8B-Instruct-KTO-500
chchen/Llama-3.1-8B-Instruct-KTO-600
Updated • 19
chchen/Llama-3.1-8B-Instruct-KTO-700
chchen/Llama-3.1-8B-Instruct-KTO-800
Updated • 28
chchen/Llama-3.1-8B-Instruct-KTO-900
chchen/Llama-3.1-8B-Instruct-KTO-1000
Updated • 10
Text Generation
• 2B • Updated • 15
johnpaulbin/articulate-11-expspanish-draft-merged
Text Generation
• 1B • Updated • 11
johnpaulbin/articulate-11-expspanish-draft-merged-Q5_K_S-GGUF
1B • Updated • 19
clembench-playpen/meta-llama-Meta-Llama-3.1-8B-Instruct_KTO_binary_dataset_wordle_wordlewithclue_aborted
Updated
clembench-playpen/meta-llama-Meta-Llama-3.1-8B-Instruct_KTO_binary_dataset_wordle_wordlewithclue
Updated
clembench-playpen/meta-llama-Meta-Llama-3.1-8B-Instruct_KTO_binary_dataset_wordle_wordlewithclue_aborted_llama
Updated
abaryan/deepseek-r1-distill-qwen-1-5b-kto
Text Generation
• Updated • 29
mradermacher/deepseek-r1-distill-qwen-1-5b-kto-GGUF
2B • Updated • 165
clembench-playpen/meta-llama_KTO_binary_dataset_wordle_wordlewithclue_best-models_neg_aborted
Updated
clembench-playpen/meta-llama_KTO_binary_dataset_wordle_wordlewithclue_same-family_neg_aborted
Updated
clembench-playpen/meta-llama_KTO_binary_dataset_wordle_wordlewithclue_same-family_neg_aborted_2eps
Updated
clembench-playpen/meta-llama_KTO_binary_dataset_wordle_wordlewithclue_same-family_neg_aborted_3eps
Updated
clembench-playpen/meta-llama_KTO_binary_dataset_wordle_wordlewithclue_same-family-all
Updated
clembench-playpen/meta-llama_KTO_binary_dataset_wordle_wordlewithclue_same-family-all_2eps
Updated
clembench-playpen/meta-llama_KTO_binary_dataset_wordle_wordlewithclue_same-family-all_3eps
Updated
rachittibrewal/seqax1b_2x_lr_2.5e-3-kto
Text Generation
• 1B • Updated • 4
clembench-playpen/meta-llama_KTO_binary_dataset_all_games
Updated
clembench-playpen/meta-llama_KTO_binary_dataset_all_games-same-family
Updated
clembench-playpen/meta-llama_KTO_binary_dataset_all_games-best-models
Updated