IS-SFT

university

https://github.com/DylanZSZ/synlogic-rl

AI & ML interests

None defined yet.

Recent Activity

SeanWang0027 authored a paper 14 days ago

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

shizhuo2 submitted a paper about 1 month ago

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

SeanWang0027 updated a model about 1 month ago

is-sft-271828/synlogic_grpo_qwen3-4b-base-qwen3-8b-3e-5-seq-seqlen_8192_chunksize_8

View all activity

models 18

is-sft-271828/synlogic_grpo_qwen3-4b-base-qwen3-8b-3e-5-seq-seqlen_8192_chunksize_8

4B • Updated Jan 27

is-sft-271828/math-offline-models

is-sft-271828/synlogic_grpo_qwen3-4b-base-qwen3-8b-3e-5-seq-seqlen_8192_chunksize_4

4B • Updated Jan 27

is-sft-271828/math_grpo_qwen3-4b-base-qwen3-8b-3e-5-seq-seqlen_8192_chunksize_8

4B • Updated Jan 27 • 1

is-sft-271828/math_grpo_qwen3-4b-base-qwen3-8b-3e-5-seq-seqlen_8192_chunksize_4

4B • Updated Jan 27

is-sft-271828/grpo-is-token-math

is-sft-271828/qwen3-1.7b-math-offline

is-sft-271828/grpo_qwen3-8b-base-qwen3-8b-3e-5-seq-seqlen_8192

8B • Updated Jan 26

is-sft-271828/is_seq_qwen3-8b-base-qwen3-8b-3e-5-seq-seqlen_8192

8B • Updated Jan 25

is-sft-271828/is_seq_qwen3-4b-base-qwen3-8b-3e-5-seq-seqlen_8192

4B • Updated Jan 25

datasets 0

None public yet