With Jukebox, there are several lm_head modules that should be skipped using the llm_int8_skip_modules parameter in [BitsAndBytesConfig]:

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
model_id = "bigscience/bloom-1b7"
quantization_config = BitsAndBytesConfig(
    llm_int8_skip_modules=["lm_head"],
)
model_8bit = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    quantization_config=quantization_config,
)

Finetuning
With the PEFT library, you can finetune large models like flan-t5-large and facebook/opt-6.7b with 8-bit quantization.