12 1 20

Debasish Dhal

DebasishDhal99

AI & ML interests

None yet

Recent Activity

updated a dataset 10 days ago

DebasishDhal99/IAST-corpus

liked a model 13 days ago

microsoft/Llama2-7b-WhoIsHarryPotter

new activity 14 days ago

DebasishDhal99/IAST-corpus:[bot] Conversion to Parquet

View all activity

Organizations

DebasishDhal99's activity

updated a dataset 10 days ago

DebasishDhal99/IAST-corpus

Viewer • Updated 10 days ago • 738k • 21

liked a model 13 days ago

microsoft/Llama2-7b-WhoIsHarryPotter

Text Generation • Updated Oct 4, 2023 • 94 • 37

New activity in DebasishDhal99/IAST-corpus 14 days ago

[bot] Conversion to Parquet

#1 opened 14 days ago by

parquet-converter

reacted to ImranzamanML's post with 👍 23 days ago

Post

1676

Here is how we can calculate the size of any LLM model:

Each parameter in LLM models is typically stored as a floating-point number. The size of each parameter in bytes depends on the precision.

32-bit precision: Each parameter takes 4 bytes.
16-bit precision: Each parameter takes 2 bytes

To calculate the total memory usage of the model:
Memory usage (in bytes) = No. of Parameters × Size of Each Parameter

For example:
32-bit Precision (FP32)
In 32-bit floating-point precision, each parameter takes 4 bytes.
Memory usage in bytes = 1 billion parameters × 4 bytes
1,000,000,000 × 4 = 4,000,000,000 bytes
In gigabytes: ≈ 3.73 GB

16-bit Precision (FP16)
In 16-bit floating-point precision, each parameter takes 2 bytes.
Memory usage in bytes = 1 billion parameters × 2 bytes
1,000,000,000 × 2 = 2,000,000,000 bytes
In gigabytes: ≈ 1.86 GB

It depends on whether you use 32-bit or 16-bit precision, a model with 1 billion parameters would use approximately 3.73 GB or 1.86 GB of memory, respectively.