5456es/bees_prune_Llama-3.2-1B-Instruct_prune_0.3-sigmoid
1B • Updated • 1
Shenzhennan
5456es
AI & ML interests
None yet
Recent Activity
authored a paper about 4 hours ago
JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency authored a paper about 4 hours ago
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents authored a paper about 4 hours ago
On the Geometry of On-Policy DistillationOrganizations
5456es/last_layer_prune_Llama-3.2-3B-Instruct_prune_0.7-sigmoid
3B • Updated
5456es/implicit_reward_Llama-3.2-3B-Instruct_prune_0.7-sigmoid
3B • Updated • 1
5456es/last_layer_prune_Llama-3.1-8B-Instruct_prune_0.5-sigmoid
8B • Updated • 4
5456es/implicit_reward_Llama-3.2-1B-Instruct_prune_0.5-sigmoid
1B • Updated
5456es/selective_dpo_Qwen2.5-0.5B-Instruct_prune_0.5-sigmoid
0.5B • Updated
5456es/selective_dpo_Llama-3.2-1B-Instruct_prune_0.5-sigmoid
1B • Updated
5456es/selective_dpo_Qwen2.5-0.5B-Instruct_prune_0.3-sigmoid
0.5B • Updated
5456es/last_layer_prune_Llama-3.1-8B-Instruct_prune_0.6-sigmoid
8B • Updated • 4
5456es/bees_prune_Qwen2.5-0.5B-Instruct_prune_0.7-sigmoid
0.5B • Updated
5456es/last_layer_prune_Llama-3.2-3B-Instruct_prune_0.4-sigmoid
3B • Updated • 1
5456es/selective_dpo_Llama-3.2-3B-Instruct_prune_0.7-sigmoid
3B • Updated • 1
5456es/bees_prune_Qwen2.5-1.5B-Instruct_prune_0.5-sigmoid
2B • Updated
5456es/cluster_prune_Qwen2.5-0.5B-Instruct_prune_0.5-sigmoid
0.5B • Updated
5456es/random_prune_Qwen2.5-7B-Instruct_prune_0.5-sigmoid
8B • Updated • 2
5456es/random_prune_Llama-3.1-8B-Instruct_prune_0.7-sigmoid
8B • Updated • 4
5456es/implicit_reward_Llama-3.2-3B-Instruct_prune_0.3-sigmoid
3B • Updated
5456es/implicit_reward_Qwen2.5-1.5B-Instruct_prune_0.3-sigmoid
2B • Updated
5456es/random_prune_Llama-3.2-1B-Instruct_prune_0.3-sigmoid
1B • Updated
5456es/selective_dpo_Llama-3.2-1B-Instruct_prune_0.3-sigmoid
1B • Updated • 2
5456es/last_layer_prune_Llama-3.2-1B-Instruct_prune_0.4-sigmoid
1B • Updated
5456es/bees_prune_Llama-3.2-3B-Instruct_prune_0.5-sigmoid
3B • Updated
5456es/cluster_prune_Qwen2.5-0.5B-Instruct_prune_0.7-sigmoid
0.5B • Updated
5456es/selective_dpo_Qwen2.5-1.5B-Instruct_prune_0.3-sigmoid
2B • Updated
5456es/last_layer_prune_Llama-3.2-3B-Instruct_prune_0.6-sigmoid
3B • Updated • 2
5456es/random_prune_Qwen2.5-7B-Instruct_prune_0.3-sigmoid
8B • Updated • 2
5456es/selective_dpo_Qwen2.5-0.5B-Instruct_prune_0.7-sigmoid
0.5B • Updated
5456es/last_layer_prune_Llama-3.2-3B-Instruct_prune_0.2-sigmoid
3B • Updated • 2
5456es/random_prune_Llama-3.2-3B-Instruct_prune_0.4-sigmoid
3B • Updated • 1
5456es/cluster_prune_Qwen2.5-0.5B-Instruct_prune_0.3-sigmoid
0.5B • Updated