swadeshb/tracecomp-qwen4b-ledger-sft
Updated
Swadesh B
swadeshb
AI & ML interests
None yet
Recent Activity
updated a model 4 days ago
swadeshb/tracecomp-qwen4b-ledger-sft published a model 5 days ago
swadeshb/tracecomp-qwen4b-ledger-sft updated a model 14 days ago
swadeshb/granite-speech-3.3-2b-hybrid-grpo-werOrganizations
None yet
models 199
swadeshb/granite-speech-3.3-2b-hybrid-grpo-wer
Updated
swadeshb/granite-speech-3.3-2b-dense-rtg-grpo-wer
Updated
swadeshb/granite-speech-3.3-2b-baseline-grpo-wer
Updated
swadeshb/Qwen2.5-3B-gkd-gsm8k-lora
Updated
swadeshb/Qwen2.5-3B-capopd-gsm8k-lora
Updated
swadeshb/Qwen2.5-3B-scopd-8B
Updated
swadeshb/Qwen2.5-3B-scopd-teacher
Text Generation • 4B • Updated • 66
swadeshb/Qwen2.5-3B-scopd
Text Generation • 4B • Updated • 45
swadeshb/Qwen2.5-3B-gkd-baseline
Updated
datasets 16
swadeshb/openmath-cot-100k-filtered
Viewer • Updated • 88.3k • 38
swadeshb/tivd-answers
Viewer • Updated • 57.6k • 9
swadeshb/DeepMath-103K-difficulty-6-plus
Viewer • Updated • 57.6k • 33
swadeshb/OpenThoughts3-math-qsa
Viewer • Updated • 274k • 15
swadeshb/OpenThoughts3-math
Viewer • Updated • 850k • 61
swadeshb/sft-dataset-v1
Viewer • Updated • 102k • 10
swadeshb/CRPO-dataset-gsm8k-clean
Viewer • Updated • 7.47k • 6
swadeshb/CRPO-dataset-30k-clean
Viewer • Updated • 30k • 9
swadeshb/CoT-think-format-ds
Viewer • Updated • 860k • 23
swadeshb/gsm8k_final
Viewer • Updated • 7.47k • 7