char min
yoursmin
·
AI & ML interests
None yet
Recent Activity
new activity
28 days ago
nvidia/DeepSeek-R1-FP4:FP4 in attention proj
liked
a model
30 days ago
nvidia/DeepSeek-R1-FP4
liked
a model
30 days ago
meta-llama/Llama-3.1-405B-Instruct
Organizations
None yet
yoursmin's activity
FP4 in attention proj
2
#9 opened 30 days ago
by
yoursmin
The Precision Difference in QKV Projection Weights: FP4 vs. BF16 in DeepSeek R1 FP4 Model
#2 opened 30 days ago
by
yoursmin
FP4 in attention proj
2
#9 opened 30 days ago
by
yoursmin