metadata
license: creativeml-openrail-m
datasets:
- GEM/viggo
metrics:
- accuracy
library_name: transformers
tags:
- 'transformers '
- peft
- qlora
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
base_model_id = "mistralai/Mistral-7B-v0.1"
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_use_double_quant=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16
)
base_model = AutoModelForCausalLM.from_pretrained(
base_model_id, # Mistral, same as before
quantization_config=bnb_config, # Same quantization config as before
device_map="auto",
trust_remote_code=True,
use_auth_token=True
)
eval_tokenizer = AutoTokenizer.from_pretrained(
base_model_id,
add_bos_token=True,
trust_remote_code=True,
)
Now load the QLoRA adapter from the appropriate checkpoint directory ```