arxiv:2406.06608
michael ilie PRO
skdrx
AI & ML interests
None yet
Organizations
models 11
skdrx/flashlm-v4-large-trained-longer
Updated
skdrx/dracula-flow-base
Text Generation • 2B • Updated • 3
skdrx/qwen3-14b-shade-qa-200
Text Generation • 4B • Updated • 5
skdrx/gemma2-2b-it-falsereject
3B • Updated • 4 • 1
skdrx/gemma-2-2b-finemath-finetune
3B • Updated • 1
skdrx/ds_coder_6.7_inst_rlsf_varname
7B • Updated • 13
skdrx/amd135m_reasoning_finetune
0.1B • Updated • 75 • 1
skdrx/rslf_dscoder1.3b-inst-varname-gguf
1B • Updated • 4
skdrx/rlsf_ds_1.3b_instruct_varname
Text Generation • 1B • Updated • 1
skdrx/rlstarfmodel_ds_inst
Updated
datasets 11
skdrx/python-dpo-dataset-complete-just-formatting
Viewer • Updated • 37k • 3
skdrx/python-dpo-dataset-varname
Viewer • Updated • 2k • 6
skdrx/python-dpo-dataset-formatted
Viewer • Updated • 2k • 4
skdrx/python-dpo-dataset-varname-formatted-combined-ONLYSYSTEMPROMPT
Viewer • Updated • 1k • 5
skdrx/python-dpo-dataset-varname-formatted-combined-NOSYSTEMPROMPT
Viewer • Updated • 1k • 5
skdrx/python-dpo-dataset-varname-formatted-ONLYSYSTEMPROMPT
Viewer • Updated • 1k • 5
skdrx/python-dpo-dataset-varname-formatted-NOSYSTEMPROMPT
Viewer • Updated • 1k • 5
skdrx/python-dpo-dataset-varname-formatted-combined
Viewer • Updated • 2k • 3
skdrx/python-dpo-dataset-varname-formatted
Viewer • Updated • 2k • 6
skdrx/rlsf_dpo
Viewer • Updated • 10k • 3 • 1