Local Large Language Model Inference Engine

Documentation for package ‘edgemodelr’ version 0.1.4

build_chat_prompt	Build chat prompt from conversation history
edge_benchmark	Performance benchmarking for model inference
edge_chat_stream	Interactive chat session with streaming responses
edge_clean_cache	Clean up cache directory and manage storage
edge_completion	Generate text completion using loaded model
edge_download_model	Download a GGUF model from Hugging Face
edge_download_url	Download a model from a direct URL
edge_find_gguf_models	Find and prepare GGUF models for use with edgemodelr
edge_find_ollama_models	Find and load Ollama models
edge_free_model	Free model context and release memory
edge_list_models	List popular pre-configured models
edge_load_model	Load a local GGUF model for inference
edge_load_ollama_model	Load an Ollama model by partial SHA-256 hash
edge_quick_setup	Quick setup for a popular model
edge_set_verbose	Control llama.cpp logging verbosity
edge_small_model_config	Get optimized configuration for small language models
edge_stream_completion	Stream text completion with real-time token generation
is_valid_model	Check if model context is valid
test_ollama_model_compatibility	Test if an Ollama model blob can be used with edgemodelr