arxiv:2407.02068
Kaixin Xu
kartmannXu
AI & ML interests
Neural Network Compression, Efficient AI
Recent Activity
updated
a model
2 days ago
kartmannXu/Qwen2.5-3B-ch-0.3-tuned
published
a model
3 days ago
kartmannXu/Qwen2.5-3B-ch-0.3-tuned
updated
a model
3 days ago
kartmannXu/deepseek-llm-7b-chat-bl-0.3
Organizations
None yet
Papers
3
models
19
kartmannXu/Qwen2.5-3B-ch-0.3-tuned
Text Generation
•
Updated
•
56
kartmannXu/deepseek-llm-7b-chat-bl-0.3
Text Generation
•
Updated
kartmannXu/Qwen2.5-3B-ch-0.3
Text Generation
•
Updated
•
25
kartmannXu/Qwen2.5-2.1Bgptq-int4
Text Generation
•
Updated
•
7
kartmannXu/Qwen2.5-2.1B
Updated
kartmannXu/Qwen2.5-2.1B-GPTQ-int4
Text Generation
•
Updated
•
8
kartmannXu/llava-prune-token-weight-76.12
Updated
•
6
kartmannXu/MiniCPM-2B-128k-pruned-0.3-onnx
Updated
•
8
kartmannXu/MiniCPM-2B-128k-q4f16_1_mlc
Updated
kartmannXu/MiniCPM-2B-128k-prune-ch-0.3-q0f16-mlc
Updated
datasets
None public yet