clembench-playpen/meta-llama_3.1_KTO_all_games_best_models_5MAR
Updated
clembench-playpen/meta-llama-3.1_DPO_allneg_Aborted_same_family_model_5MAR
Updated
clembench-playpen/llama-3.1-8B-Instruct_playpen_SFT_DFINAL_1.1K-steps
clembench-playpen/meta-llama-3.1_DPO_allneg_Aborted_best_models_5MAR
Updated
clembench-playpen/llama-3.1-8B-Instruct_playpen_SFT_DFINAL_1.7K-steps
clembench-playpen/meta-llama-Llama-3.1-70B-Instruct_playpen_SFT_DFINAL_llama
clembench-playpen/Qwen-Qwen2.5-Coder-32B-Instruct_playpen_SFT_DFINAL_qwen-coder
clembench-playpen/meta-llama-Llama-3.1-70B_playpen_SFT_DFINAL_llama
clembench-playpen/Qwen-Qwen2.5-Coder-32B_playpen_SFT_DFINAL_qwen-coder
clembench-playpen/meta-llama-Meta-Llama-3.1-8B-Instruct_playpen_SFT_DFINAL_llama
clembench-playpen/Qwen_allneg_Aborted_best_models_28feb
Updated
clembench-playpen/meta-llama_3.1_KTO_KTO_all_games_ROCK2
Updated
clembench-playpen/meta-llama-3.1_DPO_allneg_Aborted_same_family_model_28feb
Updated
clembench-playpen/meta-llama-3.1_DPO_allneg_Aborted_best_models_28feb
Updated
clembench-playpen/meta-llama_3.1_KTO_KTO_all_games_PAPER
Updated
clembench-playpen/meta-llama_3.1_KTO_KTO_all_games_ROCK
Updated
clembench-playpen/meta-llama-Meta-Llama-3.1-8B-Instruct_SFT_E1_D40008
Updated
clembench-playpen/meta-llama-Meta-Llama-3.1-8B-Instruct_SFT_E1_D40007
Updated
clembench-playpen/meta-llama-Meta-Llama-3.1-8B-Instruct_SFT_E1_D40006
Updated
clembench-playpen/meta-llama-Meta-Llama-3.1-8B-Instruct_SFT_E1_D40005
Updated
clembench-playpen/meta-llama-Meta-Llama-3.1-8B-Instruct_SFT_E1_D40004
Updated
clembench-playpen/meta-llama-Meta-Llama-3.1-8B-Instruct_SFT_E1_D40003
Updated
clembench-playpen/meta-llama-Meta-Llama-3.1-8B-Instruct_SFT_E1_D40002
Updated
clembench-playpen/SFT-base_merged_fp16_E1_D40005
Text Generation
• 8B • Updated
• 4
• clembench-playpen/meta-llama-3.1_DPO_6neg_Aborted_20feb
Updated
clembench-playpen/meta-llama-3.1_DPO_2neg_Aborted_20feb
Updated
clembench-playpen/meta-llama-Meta-Llama-3.1-8B-Instruct_DPO_1neg_Aborted
Updated
clembench-playpen/meta-llama-Meta-Llama-3.1-8B-Instruct_DPO_1neg_Aborted_abnormREF
Updated
clembench-playpen/meta-llama-Meta-Llama-3.1-8B-Instruct_SFT_E1_D40001
Updated
clembench-playpen/meta-llama_KTO_KTO_AbortedEXP2_2AllError_AbortedOnly
Updated