-
-
-
-
-
-
Active filters: kto
Edens-Gate/hamanasu-4b-kto-ckpts
Text Generation
• 5B • Updated
• 1
clembench-playpen/llama-3.1-70B-Instruct_playpen_SFT_DFINAL_0.6K-steps_merged_fp16_KTO_FINAL_FINAL
Updated
Edens-Gate/Hamanasu-Chat-KTO-4B
Text Generation
• 5B • Updated
• 1
mradermacher/Hamanasu-Chat-KTO-4B-GGUF
5B • Updated
• 48
• 1
nuriyev/Qwen2.5-0.5B-Instruct-medical-kpo
Text Generation
• 0.5B • Updated
• 2
clembench-playpen/meta-llama-3.1-8b-instruct-unsloth-bnb-4bit_KTO_Aborted_best_models_F_KTO_noSFT
Updated
clembench-playpen/Llama-3.1-70B_KTO_noSFT
Updated
clembench-playpen/meta-llama-3.1-8b_KTO_noSFT
Updated
clembench-playpen/Mistral-Small-24B-Instruct-2501-unsloth-bnb-4bit_KTO_Final_KTO_noSFT
Updated
Text Generation
• 8B • Updated
• 9
• 1
mradermacher/Emerald-8B-GGUF
8B • Updated
• 9
• 1
mradermacher/Emerald-8B-i1-GGUF
8B • Updated
• 599
• 1
mradermacher/Qwen2.5-0.5B-Instruct-medical-kpo-GGUF
0.5B • Updated
• 2
mradermacher/Qwen2.5-0.5B-Instruct-medical-kpo-i1-GGUF
0.5B • Updated
• 28
akbarsigit/llama3.1-kto-r64-a128-merged-16bit
Text Generation
• 8B • Updated
hardlyworking/Golden-Curry-12B
Text Generation
• 12B • Updated
• 2
hardlyworking/Golden-Curry-12B-Q4_K_S-GGUF
12B • Updated
• 1
PaulD/llama3_false_positives_0312_KTO_optimised_model_2104
Updated
tensorblock/MoxoffSrL_Moxoff-Phi3Mini-KTO-GGUF
Text Generation
• 2B • Updated
Delta-Vector/Archaeo-32B-KTO
Text Generation
• 33B • Updated
• 5
• 4
mradermacher/Axo-Merge-Archaeo-V2-Lora-GGUF
33B • Updated
• 64
• 1
Text Generation
• 4B • Updated
• 8
hardlyworking/Secret4B-Q6_K-GGUF
4B • Updated
• 3
Carnyzzle/Archaeo-32B-KTO-Q4_K_M-GGUF
Text Generation
• 33B • Updated
• 3
• 1
mradermacher/Archaeo-32B-KTO-GGUF
33B • Updated
• 67
• 1
mradermacher/Archaeo-32B-KTO-i1-GGUF
33B • Updated
• 237
• 1
Text Generation
• 8B • Updated
• 2
akbarsigit/llama3.1-kto-r256-a512-merged-16bit
Text Generation
• 8B • Updated
akbarsigit/llama3.1-kto-r128-a256-merged-16bit
Text Generation
• 8B • Updated