OLD SFT Final Models Merged - a clembench-playpen Collection

clembench-playpen 's Collections

SFT Final Models Merged

Datasets for DPO

KTO Final Models

OLD SFT Final Models Merged

SFT Final Models

Preference Dataset KTO (Wordle & Wordle_withclue)

OLD SFT Final Models Merged

updated Apr 10

Collection of final SFT adapters merged to the base model

clembench-playpen/llama-3.1-8B-Instruct_playpen_SFT_DFINAL_0.7K-steps_merged_fp16

Text Generation • 8B • Updated Mar 18 • 3
clembench-playpen/SFT-merged_fp16_DFINAL_1.1K-steps

Text Generation • 8B • Updated Mar 10 • 37 •
clembench-playpen/Mistral-Small-24B-Instruct-2501_playpen_SFT_merged_fp16_DFINAL_0.6K-steps

Text Generation • 24B • Updated Mar 17 • 4
clembench-playpen/llama-3.1-70B-Instruct_playpen_SFT_DFINAL_0.6K-steps_merged_fp16

Text Generation • 71B • Updated Mar 22 • 1.03k