Spaces:
Sleeping
Sleeping
File size: 1,034 Bytes
c5778e1 72c814f 925d43b c1e0503 60870dc c5778e1 60870dc 55b5608 60870dc 55b5608 60870dc 55b5608 60870dc 55b5608 60870dc 55b5608 c1e0503 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 |
import torch
from datasets import load_dataset
torch.cuda.is_available()
print("executed successfully")
dataset_name = "timdettmers/openassistant-guanaco"
dataset = load_dataset(dataset_name, split="train")
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
# quantizition configuration
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.float16,
)
# download model
model_name = "TinyPixel/Llama-2-7B-bf16-sharded"
model = AutoModelForCausalLM.from_pretrained(
model_name,
quantization_config=bnb_config,
trust_remote_code=True
)
model.config.use_cache = False
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
tokenizer.pad_token = tokenizer.eos_token
text = "What is a large language model?"
device = "cuda:0"
inputs = tokenizer(text, return_tensors="pt").to(device)
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|