Private collection of the exact s0-s6 training parquets and final PEFT adapters used by the PTXBench Qwen3.6-27B SFT series.
Genghan Zhang
Genghan
AI & ML interests
None yet
Recent Activity
new activity about 3 hours ago
AccRL/accrl-training:Add direct-gate GDN prefill definition, workload, and offsets blob upvoted a paper about 10 hours ago
Cache Engineering for Agents upvoted a paper 10 days ago
Stateless Language Agents: Scaling Long-Horizon Automated ResearchOrganizations
models 14
Genghan/PTXBench-Qwen3.6-27B-s6
Image-Text-to-Text • Updated • 5
Genghan/PTXBench-Qwen3.6-27B-s5
Image-Text-to-Text • Updated • 5
Genghan/PTXBench-Qwen3.6-27B-s4
Image-Text-to-Text • Updated • 2
Genghan/PTXBench-Qwen3.6-27B-s3
Image-Text-to-Text • Updated • 4
Genghan/PTXBench-Qwen3.6-27B-s2
Image-Text-to-Text • Updated • 4
Genghan/PTXBench-Qwen3.6-27B-s1
Image-Text-to-Text • Updated • 4
Genghan/PTXBench-Qwen3.6-27B-s0
Image-Text-to-Text • Updated • 4
Genghan/sft-qwen-7b-instruct_GRPO_nki_pure_0920_cluster3
8B • Updated • 9
Genghan/deepseek-coder-33b-instruct_GRPO_nki_pure_0907_cluster1
33B • Updated • 24
Genghan/sft-deepseek-coder-33b-instruct_GRPO_nki_pure_0921_cluster4
33B • Updated • 23