LocalLLaMA

14 readers

1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 2 years ago

MODERATORS

communick@poweruser.forum

Why there are quantized models in the hugging face hug? (alien.top)

submitted 2 years ago by Motylde@alien.top to c/localllama@poweruser.forum

4 comments fedilink hide all child comments

Hi. I'm using Llama-2 for my project in python with transformers library. There is an option to use quantization on any normal model:

model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-2-13b-chat-hf",
    load_in_4bit=True,
)

If it's just a matter of single flag, and nothing is recomputed, then why there is so much already quantized models in the hub? Are they better than adding this one line?

you are viewing a single comment's thread
view the rest of the comments

[–] mcmoose1900@alien.top 1 points 2 years ago

Many reasons:

AutoModelForCausalLM is extremely slow compared to other backends/quantizations, even with augmentations like BetterTransformers.
It also uses much more VRAM than other quantization, especially at high context.
Its size is inflexible.
Loads slower
No CPU offloading
Its potentially lower quality than other quantization at the same bpw