Value error unknow quantization type

#7
by Maxz11 - opened

Got this error message after running model=AutoModelForCasual1LM.from_pretrained.
ValueError: Unknown quantization type, got exl2 - supported types are: ['awq', 'bitsandbytes_4bit', 'bitsandbytes_8bit', 'gptq', 'aqlm', 'quanto']

Yep, same here. Note that I get the same error even if I just cURL from HF with

curl https://api-inference.huggingface.co/models/hjhj3168/Llama-3-8b-Orthogonalized-exl2 \
    -X POST \
    -d '{"inputs": "Can you please let us know more details about your "}' \
    -H 'Content-Type: application/json' \
    -H "Authorization: Bearer [REDACTED]"

@Maxz11 hi, have you found a solution? I also encountered it here.

did you find a solution? Please share, I'm stuck and can use help

Sign up or log in to comment