Llama base models with a chat template that still use eos_token
Zack Ankner
ankner
AI & ML interests
None yet
Organizations
models 36
ankner/chat-smol-135m-rm
0.1B • Updated • 4
ankner/chat-smol-360m-rm
0.4B • Updated • 1
ankner/chat-smol-1_7b-rm
2B • Updated
ankner/smol-1_7b
Text Generation • 2B • Updated • 1
ankner/smol-360m
Text Generation • 0.4B • Updated
ankner/smol-135m
Text Generation • 0.1B • Updated
ankner/sft-mmlu-pro-llama3-8b-base
8B • Updated • 1
ankner/sft-mbpp-llama3-3b-base
3B • Updated
ankner/sft-mbpp-llama3-8b-base
8B • Updated
ankner/sft-apps-ds-lite-inst
16B • Updated • 1
datasets 35
ankner/mmlu-pro-rl-llama3-8b-base-labeled
Viewer • Updated • 9.34k • 7
ankner/mmlu-pro-rl
Viewer • Updated • 9.34k • 6
ankner/mmlu-pro-sft
Viewer • Updated • 2k • 5
ankner/mmlu-pro-CoT
Viewer • Updated • 10.3k • 8
ankner/mbpp-rl-llama3-3b-base-labeled
Viewer • Updated • 9.97k • 7
ankner/mbpp-rl-llama3-8b-base-labeled
Viewer • Updated • 9.96k • 10 • 1
ankner/mbpp-sft
Viewer • Updated • 2k • 15
ankner/mbpp-rl
Viewer • Updated • 9.98k • 18
ankner/Synth-MBPP
Viewer • Updated • 11k • 12
ankner/new-Synth-MBPP
Viewer • Updated • 10 • 9