The Kyle Stone
essobi
AI & ML interests
I teach robots to teach robots that teach robots that teach humans.
Recent Activity
liked
a dataset
10 days ago
mlfoundations/dclm-baseline-1.0
liked
a dataset
12 days ago
unsloth/OpenMathReasoning-mini
liked
a model
19 days ago
Skywork/Skywork-Reward-V2-Llama-3.1-8B-40M
Organizations
None yet
models
9
essobi/Qwen2.5-Coder-3B-Instruct_gsm8k
Updated
essobi/Qwen2.5-3B-GRPO-math
Updated
essobi/Qwen2-0.5B-GRPO-test
Updated
essobi/grpo_output
Updated
essobi/grpo-training-output
Updated
essobi/Qwen2.5-0.5B-Online-DPO-PairRM
Updated
essobi/Llama-3.2-1B-Instruct-Q4_K_M-GGUF
Text Generation
•
1B
•
Updated
•
3
essobi/pythia-1b-tldr-online-dpo
Updated
essobi/LIMECREAM-3.1
8B
•
Updated
•
4
•
2
datasets
11
essobi/wildchat-rip-filtered-english-categorized-high-confidence
Viewer
•
Updated
•
2.65k
•
154
•
1
essobi/wildchat-categorized-high-confidence
Viewer
•
Updated
•
5.9k
•
91
essobi/s1k-verifiable-filtered
Viewer
•
Updated
•
956
•
124
essobi/facebook-natural-reasoning-curriculum
Preview
•
Updated
•
25
essobi/tulu-combined
Updated
•
79
•
1
essobi/Tulu2_Tulu3_Unfiltered_Split_50MT
Updated
•
1
essobi/LIMO
Viewer
•
Updated
•
816
•
3
•
1
essobi/lima
Preview
•
Updated
essobi/wikipedia-topics
Viewer
•
Updated
•
76.6k
•
3
essobi/earnie
Updated
•
2