Skip to content

README.md

Latest commit

 

History

History
23 lines (16 loc) · 731 Bytes

README.md

File metadata and controls

23 lines (16 loc) · 731 Bytes
Raw

chat — interactive multi-turn REPL

Interactive chat that formats each turn with [LlamaModel::apply_chat_template], so prompts match the GGUF's chat template (Llama, Qwen, Mistral, …).

This example uses llama_cpp_4::prelude for imports (LlamaModel, LlamaContext, LlamaChatMessage, apply_chat_template, sampling, batching, and related types) instead of listing individual crate paths.

Run

cargo run -p chat -- local path/to/model.gguf
cargo run -p chat -- hf-model bartowski/Llama-3.2-1B-Instruct-GGUF Q4_K_M

With GPU backends:

cargo run -p chat --features metal -- local path/to/model.gguf