zjxia/step-3.5-flash-eagle3-perfectblend-smoltalk-chinese-large-blend-regen-online
0.4B • Updated • 2
Zijie Xia
zjxia
AI & ML interests
None yet
Recent Activity
upvoted a paper 16 days ago
Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling new activity 23 days ago
deepseek-ai/DeepSeek-V4-Flash:support inference by sglang or vllm ? new activity 23 days ago
deepseek-ai/DeepSeek-V4-Pro:Update README.md to add SGLang deployment optionOrganizations
zjxia/step-3.5-flash-eagle3-perfectblend-smoltalk-chinese-blend-regen-online
0.4B • Updated • 7
zjxia/step-3.5-flash-eagle3-ultrachat-regen
0.4B • Updated • 3
zjxia/step-3.5-flash-eagle3-SpecForge-draft-epoch2
0.4B • Updated • 3
zjxia/step-3.5-flash-eagle3-SpecForge-draft
0.4B • Updated • 3
zjxia/Qwen3-4B-tau2-grpo-v1
Text Generation • 4B • Updated • 7
zjxia/Qwen3-4B-grpo-v1
Text Generation • 4B • Updated • 1
zjxia/Qwen3-4B-tau2-sft
Text Generation • 4B • Updated • 3
zjxia/Qwen3-4B-tau2-grpo-v0.1
Text Generation • 4B • Updated • 3 • 1
zjxia/Qwen3-4B-tau2-sft1
Text Generation • 4B • Updated • 3