Upload simplified ONNX weights
#7 opened 5 months ago
by
Xenova
(Attempt 3) Upload q4f16 ONNX weights (symmetric=False)
#5 opened 5 months ago
by
Xenova
(Attempt 2) Upload q4f16 ONNX weights
#4 opened 5 months ago
by
Xenova
fp16 KV I/O for q4 model
#3 opened 5 months ago
by
Xenova