arxiv:2309.05516
He, Xin
xinhe
·
AI & ML interests
None yet
Recent Activity
new activity
21 days ago
deepseek-ai/DeepSeek-R1:'num_hidden_layers': 61, but layer 62 has weights.
authored
a paper
over 1 year ago
Optimize Weight Rounding via Signed Gradient Descent for the
Quantization of LLMs
new activity
over 2 years ago
Intel/bert-base-uncased-mrpc-int8-qat-inc:Quantized model inference
Organizations
Papers
1
models
None public yet
datasets
None public yet