LLaMA Prompt Builder
Build structured prompts in LLaMA instruct format with <<SYS>> and [INST] tags.
Assembled Prompt
0 tokens · 0 chars
Fill in the fields on the left to build your prompt...Format: LLaMA instruct template (<<SYS>> / [INST])
Related Tools
PBDAI Prompt BuilderNEW
Build structured AI prompts with role, task, context, and output format fields.
CLDClaude Prompt BuilderNEW
Build structured system prompts for Anthropic Claude using XML tags.
LMALLaMA Token CounterNEW
Count tokens for LLaMA 3.1 405B, 70B, 8B, and LLaMA 3.2 models.
LLMLLaMA Inference Cost CalculatorNEW
Estimate LLaMA 3.1 API costs on hosted inference providers.
OPTAI Prompt OptimizerNEW
Analyze and improve AI prompts with rule-based suggestions.
Learn More
FAQ
- What is the LLaMA instruct template?
- LLaMA instruct models expect a specific format: system content inside <<SYS>>...</<SYS>> tags and user instructions inside [INST]...[/INST] tags. This format was introduced with LLaMA 2 Chat and is used by most LLaMA-based fine-tunes.
- Does LLaMA 3 use the same prompt format as LLaMA 2?
- LLaMA 3 introduced a new special token format using <|begin_of_text|> and <|start_header_id|> tokens for Llama 3 instruct models. The <<SYS>>/[INST] format is primarily for LLaMA 2. This builder uses the widely-supported instruct convention.
- Can I use this format with Ollama or llama.cpp?
- Yes. Most local LLaMA runtimes including Ollama, llama.cpp, and LM Studio support the <<SYS>>/[INST] instruct template for LLaMA 2 Chat models.
Build well-structured prompts in the LLaMA instruct template format. System content is wrapped in <<SYS>>...</<SYS>> and user instructions in [INST]...[/INST] — the native format for LLaMA 2 and LLaMA 3 instruct models. Fill in role, task, context, constraints, output format, and examples.