large language model (LLM)

A deep learning model trained on massive text corpora to understand and generate human-like text. Powers chatbots, code assistants, and content generators.

Syntax

generative-ai

input_tokens -> [transformer layers] -> output_tokens

Example

generative-ai

# Using an LLM via HuggingFace:
from transformers import pipeline

generator = pipeline(
    "text-generation",
    model="meta-llama/Llama-2-7b-chat-hf",
    max_new_tokens=200
)

output = generator("<s>[INST] Explain recursion simply [/INST]")
print(output[0]["generated_text"])