Spaces:
Paused
Paused
File size: 3,883 Bytes
ff8f4ba 22b462e ff8f4ba 22b462e ff8f4ba |
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 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 |
import os
import subprocess
from typing import Any, Dict, List, Optional, Tuple, Union
from numba import cuda
import nvidia_smi
from .utils.lru_cache import LRUCache
from .lib.finetune import train
class Global:
version = None
data_dir: str = ""
load_8bit: bool = False
default_base_model_name: str = ""
# Functions
train_fn: Any = train
# Training Control
should_stop_training = False
# Generation Control
should_stop_generating = False
generation_force_stopped_at = None
# Model related
loaded_models = LRUCache(1)
loaded_tokenizers = LRUCache(1)
new_base_model_that_is_ready_to_be_used = None
name_of_new_base_model_that_is_ready_to_be_used = None
# GPU Info
gpu_cc = None # GPU compute capability
gpu_sms = None # GPU total number of SMs
gpu_total_cores = None # GPU total cores
gpu_total_memory = None
# UI related
ui_title: str = "LLaMA-Adapter Tuner"
ui_emoji: str = "🦙🎛️"
ui_subtitle: str = "Toolkit for evaluating and fine-tuning LLaMA models with lightweight adaption with zero init attention (https://arxiv.org/abs/2303.16199)."
ui_show_sys_info: bool = True
ui_dev_mode: bool = False
ui_dev_mode_title_prefix: str = "[UI DEV MODE] "
def get_package_dir():
current_file_path = os.path.abspath(__file__)
parent_directory_path = os.path.dirname(current_file_path)
return os.path.abspath(parent_directory_path)
def get_git_commit_hash():
try:
original_cwd = os.getcwd()
project_dir = get_package_dir()
try:
os.chdir(project_dir)
commit_hash = subprocess.check_output(
['git', 'rev-parse', 'HEAD']).strip().decode('utf-8')
return commit_hash
except Exception as e:
print(f"Cannot get git commit hash: {e}")
finally:
os.chdir(original_cwd)
except Exception as e:
print(f"Cannot get git commit hash: {e}")
commit_hash = get_git_commit_hash()
if commit_hash:
Global.version = commit_hash[:8]
def load_gpu_info():
try:
cc_cores_per_SM_dict = {
(2, 0): 32,
(2, 1): 48,
(3, 0): 192,
(3, 5): 192,
(3, 7): 192,
(5, 0): 128,
(5, 2): 128,
(6, 0): 64,
(6, 1): 128,
(7, 0): 64,
(7, 5): 64,
(8, 0): 64,
(8, 6): 128,
(8, 9): 128,
(9, 0): 128
}
# the above dictionary should result in a value of "None" if a cc match
# is not found. The dictionary needs to be extended as new devices become
# available, and currently does not account for all Jetson devices
device = cuda.get_current_device()
device_sms = getattr(device, 'MULTIPROCESSOR_COUNT')
device_cc = device.compute_capability
cores_per_sm = cc_cores_per_SM_dict.get(device_cc)
total_cores = cores_per_sm*device_sms
print("GPU compute capability: ", device_cc)
print("GPU total number of SMs: ", device_sms)
print("GPU total cores: ", total_cores)
Global.gpu_cc = device_cc
Global.gpu_sms = device_sms
Global.gpu_total_cores = total_cores
nvidia_smi.nvmlInit()
handle = nvidia_smi.nvmlDeviceGetHandleByIndex(0)
info = nvidia_smi.nvmlDeviceGetMemoryInfo(handle)
total_memory = info.total
total_memory_mb = total_memory / (1024 ** 2)
total_memory_gb = total_memory / (1024 ** 3)
# Print the memory size
print(
f"GPU total memory: {total_memory} bytes ({total_memory_mb:.2f} MB) ({total_memory_gb:.2f} GB)")
Global.gpu_total_memory = total_memory
except Exception as e:
print(f"Notice: cannot get GPU info: {e}")
load_gpu_info()
|