-
my result is
flops(G) 5.283031296
params(M) 3.085449
Total params: 3.12M
but the flops in your paper is 1.3G
-
-
Hi:
I wonder if u know how to calculate the flops of this https://github.com/alxndrTL/mamba.py/blob/dcd6a326ad92eb2dd375e1c1ff67b48823246364/mambapy/mamba2.py#L256 function. Thanks.
-
### Song Name
Gucci flip flops x jumper
### Artist Name
theoneindiegamer
### Source
Youtube
### Youtube Link
2VMl3ISpeKc
### Direct File Link
_No response_
### Song ID
6
### Start Offset […
-
Hello, author, first of all, thank you very much for your work. I recently wanted to make some improvements in lightweight. I used the following code, but I found that an error occurred when testing y…
-
In modeling_qwen2_vl.py https://github.com/huggingface/transformers/blob/main/src/transformers/models/qwen2_vl/modeling_qwen2_vl.py#L343
The attention_mask is set for each frame, when not set the f…
-
How to obtain the floats and params of this model? The result I obtained using thop is 0.
-
### 🚀 The feature, motivation and pitch
I am able to run the training with the FSDP. But then add the "--flop_counter" flag. It gives the following issue. Could someone take a look at this issue? …
-
hi:
thanks for your work. I am interested in the calculation about mamba2's flops for SSD part. My calculation for https://github.com/state-spaces/mamba/blob/main/mamba_ssm/modules/ssd_minimal.py i…
-
Hi, the FLOPs calculation of a KAN layer is $$(d_{in} \times d_{out}) \times [9\times K \times (G + 1.5\times K) + 2\times G - 2.5 \times K - 1]$$. I understand the terms $$d_{in} \times d_{out}$$ an…