-
Topics could include:
- Bayesian model selection
- Bayesian model averaging
- Stepwise regression vs likelihood ratio tests
- Diagnostics for glms and other models where the residuals are expecte…
-
What is the best way to implement model ensembling per time step in Tensorflow? Models are ensembled by averaging the output probabilities at each decoding step. Is there a way to do this using `raw_r…
-
Another important aspect to consider here: some agencies report `max_sustained_wind` as 1-minute averages (US agencies) and other as 10-minutes averages (e.g. BOM) or even different.
I suggest that a…
-
Hi @serena-psc,
I started drafting a response to your Cross-Validated post but I have just seen that it was closed. Sorry about that, it seems the moderators want a more focused question from you. Bu…
-
Hey there,
firstly, thanks for the nice work!
I am attempting to reproduce the results from the paper. I re-ran the experiments with 10 seeds (averaging the results). However, I am only reproduc…
-
Congratulations on such remarkable results that surpass VVC!
I ran the test code with the pre-trained model you provided and I reproduced the results you reported in the paper.
Unluckily, when I…
-
The idea is to create a generic assembly, or a special type of assembly / component, that can do model aggregation. Several models that have similar I/Os for similar purpose would be able to be run in…
-
Hello,
I've been deploying my VQA (Vision Query Answer) model using Triton Server and utilizing the `perf_analyzer` tool for benchmarking. However, using random data for the VQA model leads to unde…
-
## What
Make our codes support a model soup method.
## Why
I think a model soup method is one of the best generalization method. I think if we support model soup method, we can provide users mo…
-
I see people are trying to extract the Mistral-22b ancestor from the MoE model by averaging the MLP layers and wondered if the 'model stock' method in Mergekit could be inverted:
- Use the averaged…