AngelSpec
AI & ML interests
Model Compression
Recent Activity
The collection of eagle3 series models for Qwen3 and Hunyuan.
The collection of quantization models of Qwen3
The collection of quantization models of DeepSeek and Deepseek_r1_distill
The collection of quantization models of Qwen3-VL
-
SpecExit: Accelerating Large Reasoning Model via Speculative Exit
Paper • 2509.24248 • Published • 3 -
Tequila: Trapping-free Ternary Quantization for Large Language Models
Paper • 2509.23809 • Published • 4 -
Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification
Paper • 2601.07892 • Published • 4
The collection of quantization models of Qwen2 and Qwen2.5
AngelSpec
The collection of eagle3 series models for Qwen3 and Hunyuan.
The collection of quantization models of Qwen3-VL
The collection of quantization models of Qwen3
-
SpecExit: Accelerating Large Reasoning Model via Speculative Exit
Paper • 2509.24248 • Published • 3 -
Tequila: Trapping-free Ternary Quantization for Large Language Models
Paper • 2509.23809 • Published • 4 -
Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification
Paper • 2601.07892 • Published • 4
The collection of quantization models of DeepSeek and Deepseek_r1_distill
The collection of quantization models of Qwen2 and Qwen2.5