Train one epoch SFT on UltraChat200K
Zizhuo Zhang PRO
resistz
AI & ML interests
None yet
Recent Activity
upvoted a paper 8 days ago
Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems upvoted a paper 16 days ago
Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory updated a model 6 months ago
resistz/GT-GRPO_Llama-3.2-3B-Instruct_NQ-HotpotQAOrganizations
models 10
resistz/GT-GRPO_Llama-3.2-3B-Instruct_NQ-HotpotQA
Updated
resistz/sft_Llama-3.2-1B_ultra200k
Text Generation • 0.3B • Updated • 2
resistz/sft_Qwen3-8B-Base_ultra200k_merged
8B • Updated
resistz/sft_Qwen3-8B-Base_ultra200k_lora32
Text Generation • Updated • 2
resistz/sft_Qwen3-4B-Base_ultra200k
Text Generation • 1B • Updated • 1
resistz/sft_Qwen3-1.7B-Base_ultra200k
Text Generation • 0.4B • Updated
resistz/sft_Qwen3-0.6B-Base_ultra200k
Text Generation • 0.8B • Updated • 1
resistz/sft_Llama-3.2-3B_ultra200k
Text Generation • 0.8B • Updated • 1
resistz/sft_Llama-3.1-8B_ultra200k_merged
8B • Updated • 1
resistz/sft_Llama-3.1-8B_ultra200k_lora
Text Generation • Updated • 1
datasets 0
None public yet