alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.3-lr-5e-6-avg-False-epoch-3
Updated • 3
alex shengzhi li
alexshengzhili
AI & ML interests
None yet
Recent Activity
upvoted a paper 15 days ago
IntelliAsk: Learning to Ask High-Quality Research Questions via RLVR commentedon a paper 23 days ago
Agent READMEs: An Empirical Study of Context Files for Agentic Coding updated a dataset 27 days ago
alexshengzhili/dataclaw-harbor-candidatesOrganizations
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.3-lr-5e-6-avg-False-epoch-2
Updated • 8
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.3-lr-5e-5-avg-False-epoch-3
Updated • 3
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.3-lr-5e-5-avg-False-epoch-2
Updated • 2
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.1-lr-5e-6-avg-False-epoch-3
Updated • 3
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.1-lr-5e-6-avg-False-epoch-2
Updated • 3
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.1-lr-5e-5-avg-False-epoch-3
Updated • 3
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.1-lr-5e-5-avg-False-epoch-2
Updated • 3
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.5-lr-5e-06-avg-False-epoch-3
Updated
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.5-lr-5e-05-avg-False-epoch-3
Updated
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.5-lr-5e-06-avg-False-epoch-2
Updated
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.1-lr-5e-05-avg-False-epoch-2
Updated
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.3-lr-5e-06-avg-False-epoch-3
Updated
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.3-lr-5e-06-avg-False-epoch-2
Updated
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.5-lr-5e-05-avg-False-epoch-2
Updated
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.3-lr-5e-05-avg-False-epoch-2
Updated
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.3-lr-5e-05-avg-False-epoch-3
Updated
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.1-lr-5e-06-avg-False-epoch-3
Updated
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.1-lr-5e-06-avg-False-epoch-2
Updated
alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.1-lr-5e-05-avg-False-epoch-3
Updated
alexshengzhili/steerllava-sft
Text Generation • Updated • 12
alexshengzhili/llava-steer-13b-1250attributesft-1117-3epoch-lora
Updated • 3
alexshengzhili/SciGraph-50-percent-further-ft-60k-interleaf-lora
Updated • 3
alexshengzhili/SciGraph-0-percent-further-ft-60k-interleaf-lora
Updated • 3
alexshengzhili/SciGraph-100-percent-further-ft-60k-interleaf-lora-merged
Text Generation • Updated • 11
alexshengzhili/SciGraph-100-percent-lora-merged
Text Generation • Updated • 12
alexshengzhili/SciGraph-50-percent-lora-merged
Text Generation • Updated • 7
alexshengzhili/SciGraph-50-percent-lora
Updated • 7
alexshengzhili/SciGraph-50-percent
Updated
alexshengzhili/july29_1000_hf_checkpoint
Updated