Engui comments

Results 4 comments of


                                            Engui

Could not find the quantized model in .pt or .safetensors format, exiting...

> Removing `--wbits 4 --groupsize 128` flags worked for me with the OPT model. I was getting same error. i got another error ``` Loading anon8231489123_gpt4-x-alpaca-13b-native-4bit-128g... Loading checkpoint shards: 0%|...

IndexError: list index out of range (when uploading my model in the Inference Notebook)

if you don't have hubert model ckpt, the problem occur. you have to download model ckpt.

IndexError: list index out of range (when uploading my model in the Inference Notebook)

join the discord server you can see the pre-trained-model channel model ckpt is there

Api extension with llama13b/30b has weird behaviour (or there's lack of documentation)

> Turns out this line https://github.com/oobabooga/text-generation-webui/blob/main/extensions/api/script.py#L77 must be incorrect, because if I change it to > > ``` > response = json.dumps({ > 'results': [{ > 'text': answer > }]...