QLora-ready Coding Models
Collection
For Finetuning. GPU is needed for both quantization and inference.
•
29 items
•
Updated
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")
- Downloads last month
- 6
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for onekq-ai/starcoder2-15b-bnb-4bit
Base model
bigcode/starcoder2-15b