SFT final models merged with the base model in full precision, as observed to preserve the results
clembench-project-playpen
community
AI & ML interests
None defined yet.
models 337
clembench-playpen/Qwen2-7B-DPO_dialogue
Updated
clembench-playpen/Qwen2-7B-DPO_turn
Updated
clembench-playpen/Qwen2-7B-SFT_merged
Text Generation • 8B • Updated • 1
clembench-playpen/Llama8B_DPO_turn_solved
Updated
clembench-playpen/Qwen2-7B-Instruct
Updated • 1
clembench-playpen/llama-3.1-70B-Instruct_playpen_SFT_DFINAL_0.6K-steps_merged_fp16_turn
Updated
clembench-playpen/llama-3.1-70B-Instruct_playpen_SFT_DFINAL_0.6K-steps_merged_fp16_dialogue
Updated
clembench-playpen/Qwen2.5-7B-Instruct_dialogue
Updated
clembench-playpen/Mistral-Small-24B-Instruct-less-steps_playpen_SFT-e3_DFINAL_0.35K-steps
Updated
clembench-playpen/llama-3.1-8B-Instruct_playpen_SFT_DFINAL_0.7K-steps_merged_full_precision_copy_turn
Updated
datasets 51
clembench-playpen/DPO_turn
Viewer • Updated • 58.9k • 80
clembench-playpen/DPO_turn_solved_old
Viewer • Updated • 87.6k • 9
clembench-playpen/DPO_dialogue
Viewer • Updated • 10.1k • 10
clembench-playpen/DPO_turn_bug
Viewer • Updated • 87.6k • 32
clembench-playpen/SFT-Final-Dataset
Viewer • Updated • 7.37k • 19
clembench-playpen/DPO_turn_allneg_old_and_new
Viewer • Updated • 202k • 8
clembench-playpen/DPO_turn_allneg_old
Viewer • Updated • 34k • 9
clembench-playpen/DPO_dialogue_1neg_old
Viewer • Updated • 6.7k • 38
clembench-playpen/DPO_turn_allneg_old_6m
Viewer • Updated • 34k • 26
clembench-playpen/DPO_dialogue_1neg_best_models_old_6m
Viewer • Updated • 2.33k • 9