metadata
library_name: transformers
license: bigcode-openrail-m
base_model:
- bigcode/starcoder2-15b
Bitsandbytes quantization of https://huggingface.co/bigcode/starcoder2-15b.
See https://huggingface.co/blog/4bit-transformers-bitsandbytes for instructions.
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers import BitsAndBytesConfig
import torch
nf4_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_use_double_quant=True,
bnb_4bit_compute_dtype=torch.bfloat16
)
model = AutoModelForCausalLM.from_pretrained("bigcode/starcoder2-15b", quantization_config=nf4_config)
tokenizer = AutoTokenizer.from_pretrained("bigcode/starcoder2-15b")
model.push_to_hub("onekq-ai/starcoder2-15b-bnb-4bit")
tokenizer.push_to_hub("onekq-ai/starcoder2-15b-bnb-4bit")