Pontus Aurdal

client-go: No cached connection was available

14

Hi, I'm running this on AKS and it works perfectly for a day. After that it will silently fail and when I view the pod-log I see a continuous list...

[Question] Missing creatures

11

Is there a reason why so many **Oramond** creatures are missing? I'm almost done with the Seacrest Serpent but it's really hard to find the right ID's. Should I wait...

Webhook 'output' event not fired, num_outputs done wrong?

4

### Webhook: output If `num_outputs` input parameter is > 1 the `predict` function will yield outputs while they are being generated (like here: https://github.com/anotherjesse/dream-templates/blob/main/controlnet-1.5-canny/predict.py#L313) I don't seem to receive the...

Trained on [a16z-infra/llama-2-7b-chat:7b0bfc9aff140d5b75bacbed23e91fd3c34b01a1e958d32132de6e0a19796e2c](https://replicate.com/a16z-infra/llama-2-7b-chat/versions/7b0bfc9aff140d5b75bacbed23e91fd3c34b01a1e958d32132de6e0a19796e2c) Inference error log: ``` [2023-08-23 08:08:21,585] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect) starting setup Downloading https://storage.googleapis.com/replicate-weights/llama-2-7b-chat/Llama-2-7b-chat/llama_7b_fp16.tensors to models/llama-2-7b-chat/model_artifacts/training_weights/llama_7b_fp16.tensors Downloading https://storage.googleapis.com/replicate-weights/llama-2-7b-chat/Llama-2-7b-chat/config.json to models/llama-2-7b-chat/model_artifacts/training_weights/config.json weights loaded in...

A `repetition_penalty` of `1.1` (or any custom value) will generate the following error: > Inplace update to inference tensor outside InferenceMode is not allowed.You can make a clone to get...