Sambit Kumar Barik

NaiveAttention

AI & ML interests

LLM | VLM | Natural Language Processing

Recent Activity

liked a Space 1 day ago

nanotron/ultrascale-playbook

reacted to ImranzamanML's post with 👍 7 months ago

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.

updated a model 8 months ago

NaiveAttention/LeVIT-364-Finetuned

View all activity

Organizations

liked a Space 1 day ago

2.77k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

reacted to ImranzamanML's post with 👍 7 months ago

Post

3910

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.