Models and datasets for Elastic Reset (NeurIPS 2023), code at https://github.com/mnoukhov/elastic-reset
Michael N
mnoukhov
AI & ML interests
Representation learning for functional language
Recent Activity
updated a dataset about 23 hours ago
mnoukhov/manufactoria-qwen3-4b-instruct-pass128 published a dataset about 23 hours ago
mnoukhov/manufactoria-qwen3-4b-instruct-pass128 updated a dataset about 24 hours ago
mnoukhov/manufactoria-has-test-qwen3-4b-instruct-pass128Organizations
models 39
mnoukhov/test
Updated
mnoukhov/SmolLM2-135M-tldr-sft
Text Generation • 0.1B • Updated
mnoukhov/SmolLM2-360M-tldr-sft
Text Generation • 0.4B • Updated • 2
mnoukhov/SmolLM2-135M-Instruct_tldr-sft
Text Generation • 0.1B • Updated • 3
mnoukhov/SmolLM2-135M-Instruct_tldr-rm
Text Classification • 0.1B • Updated
mnoukhov/pythia2.8b-rm-tldr6.9b
Text Classification • 3B • Updated • 1
mnoukhov/pythia2.8b-sft-tldr
Text Generation • 3B • Updated • 3
mnoukhov/pythia160m-sft-tldr
Text Generation • 0.2B • Updated • 4
mnoukhov/pythia160m-rm-tldr6.9b
Text Classification • 0.1B • Updated • 4
mnoukhov/pythia1b-rm-tldr6.9b
Text Classification • 0.9B • Updated • 1
datasets 91
mnoukhov/manufactoria-qwen3-4b-instruct-pass128
Viewer • Updated • 874 • 31
mnoukhov/manufactoria-has-test-qwen3-4b-instruct-pass128
Viewer • Updated • 132 • 6
mnoukhov/manufactoria-has-train-qwen3-4b-instruct-pass128
Viewer • Updated • 742 • 9
mnoukhov/manufactoria-has-test-qwen3-4b-instruct-pass32-codex
Viewer • Updated • 132 • 20
mnoukhov/gsm8k-platinum-qwen2.5-0.5b-base-1024samples-buckets
Viewer • Updated • 64 • 78
mnoukhov/manufactoria-has-train-qwen3-4b-instruct-pass32-codex
Viewer • Updated • 742 • 13
mnoukhov/gsm8k-platinum-qwen2.5-0.5b-base-1024samples
Viewer • Updated • 1.21k • 44
mnoukhov/gsm8k-qwen2.5-0.5b-instruct-512samples-userprompt-pass1-0-25
Viewer • Updated • 832 • 28
mnoukhov/gsm8k-platinum-openinstruct-qwen2.5-0.5b-instruct-1024samples-pass1-buckets
Viewer • Updated • 64 • 67
mnoukhov/gsm8k-platinum-openinstruct-qwen2.5-0.5b-instruct-1024samples
Viewer • Updated • 1.21k • 37