Amogh Mishra

How to create train, test and validation set?

1

The model reports only the train loss and no validation loss is provided. Although the anomalies were added synthetically, therefore we know the ground truth and can use metrics of...

Can GAE work in inductive setting?

1

In GAE, the decoder is trying to reconstruct the adjacency matrix. I presume that this approach makes the GVAE completely transductive because an unseen node will not be present in...

Application of GCN and R-GCN

1

I am new to the GCN research and was trying to differentiate which GCN is suitable for different problems. Here is what I think: 1. GCN is useful for undirected...

Number of generation doesn't give 'n' results on other LM clients (vllm, ollama) except OpenAI

4

The param `n` determines the total number of generations but it only works with openAI and not with vLLM or Ollama. From the ollama logs, it appears that its`/api/generate` endpoint...

Unable to run aviary on V100 GPU.

1

I was trying to run llama-2 on a machine with V100 GPU. I ran `aviary run --model ~/models/continuous_batching/meta-llama--Llama-2-7b-chat-hf.yaml` inside the docker container and got a stack trace: ```(ServeController pid=2420) INFO...