Note
This model trained in Flax/Jax Using OST Library
This Model Doesn't Contain Orginal LLama weights so its open source
or Use Colab Easy as much as possible
this model uses Task classification and the conversation is between <|prompter|> and Answer or <|ai|>:
Using Model in Huggingface Transformers
Examples 🚀
def prompt_to_instruction_lgem(text: str):
return f"<|prompter|> {text} </s><|ai|>:"
Generate Method to get res Text by Text
def generate(model_,input_ids_,tokeinzer_,max_length:int=256,temperature :float= 1,eos_token_id:int=2):
with torch.no_grad():
before_start = len(input_ids_[0])+1
for _ in range(max_length):
out = model_(
input_ids=input_ids_,
return_dict=True,
)
opa = torch.nn.functional.softmax(out.logits[:,-1,:]/temperature)
Camila = torch.multinomial(opa,1)
input_ids_ = torch.cat([input_ids_,Camila],-1)
clear_output(wait=True)
print(f"\r{tokeinzer_.decode(input_ids_[0],skip_special_tokens=True)[before_start:]}",end='')
if Camila[0].item() == eos_token_id:
break
yield tokeinzer_.decode(Camila[0],skip_special_tokens=True)
return f"{tokeinzer_.decode(input_ids_[0],skip_special_tokens=True)[before_start:]}"
Result
import socket
import time
def check_internet_connection():
try:
s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
s.connect(("www.google.com", 80))
print("Internet connection is active.")
except:
print("Internet connection is not active.")
if __name__ == "__main__":
check_internet_connection()
Using Model in OST
LGeM 🚀
-
what is LGeM, LGeM is a CausalLM Model that is trained on self instruct data (Alpaca data) and for initialization of the first train of the main model (weights are available) I used pre weights from Alpaca LoRA (open source)
-
it's Decoder Only
-
built-in Pytorch
-
you can simply import models like
from modules import LGeMForCausalLM
OR in Flax Jax
from modules import FlaxLGeMForCausalLM
- and Training code is available at jax_train.py (check source)
- training parameters
-
- learning rate 8e-5
-
- AdamW (weight decay 1e-2)
-
- batch 8
-
- TPU vm 3-8
-
- Train Time 130 hours
python3 LGeM-train.py