Fine-Tune Small Language Models with LoRA from R

[Up] [Top]

Documentation for package ‘dragonfarm’ version 0.3.3

Help Pages

dragon_app Launch the dragon-farm app
dragon_archived_runs Archived runs
dragon_archive_run Archive, restore, or delete a run
dragon_backend Inference backends
dragon_backend_local Inference backends
dragon_backend_ollama Inference backends
dragon_backend_server Inference backends
dragon_bundle Package a run for a cloud GPU
dragon_cancel Cancel a run
dragon_chat Talk to a model, with memory of the conversation
dragon_chat_load Talk to a model, with memory of the conversation
dragon_check Check the Python environment and hardware
dragon_code R code that reproduces a run
dragon_compare Compare runs side by side
dragon_conversations Multi-turn conversations as training data
dragon_dataset Create a dataset for fine-tuning
dragon_dataset.character Create a dataset for fine-tuning
dragon_dataset.data.frame Create a dataset for fine-tuning
dragon_delete_run Archive, restore, or delete a run
dragon_evaluate Evaluate a finished run
dragon_example_data Path to the bundled example dataset
dragon_export_gguf Export a merged model to GGUF
dragon_feedback Training data from chat feedback
dragon_generate Generate replies from a fine-tuned model
dragon_hardware Hardware settings
dragon_import Import results trained on another machine
dragon_judge Judge a run's replies with a language model
dragon_judge_anthropic Language models as functions: the Claude API and ellmer
dragon_judge_ellmer Language models as functions: the Claude API and ellmer
dragon_llm_anthropic Language models as functions: the Claude API and ellmer
dragon_llm_ellmer Language models as functions: the Claude API and ellmer
dragon_logs Inspect a run
dragon_lora LoRA settings
dragon_map Map dataset columns to prompt, response, and system text
dragon_map_pairs Map columns for preference optimization
dragon_map_prompts Map columns for reinforcement learning
dragon_merge Merge the adapter into the base model
dragon_metrics Task metrics for generated replies
dragon_metric_regex Task metrics for generated replies
dragon_pipeline Run several post-training stages as one pipeline
dragon_pipeline_cancel Cancel a pipeline
dragon_pipeline_status Progress of a pipeline
dragon_prefer Preference optimization with DPO or ORPO
dragon_presets Recommended small models
dragon_preview Preview mapped rows as chat turns
dragon_progress Inspect a run
dragon_prompts Prompts from a run's data files
dragon_publish Push a run's model to the Hugging Face Hub
dragon_python_requirements Python requirements used by dragonfarm
dragon_reinforce Reinforcement learning with verifiable rewards (GRPO)
dragon_remote Open a cloud GPU provider for a bundled run
dragon_remote_providers Cloud GPU providers
dragon_resume Resume a run from its latest checkpoint
dragon_reward Verifiable rewards for reinforcement learning
dragon_run Reopen an existing run
dragon_runs List runs
dragon_runs_dir Directory where runs are stored
dragon_serve_ollama Serve a run's model with Ollama
dragon_split Hold out rows for evaluation
dragon_status Inspect a run
dragon_step Steps of a post-training pipeline
dragon_step_evaluate Steps of a post-training pipeline
dragon_step_judge Steps of a post-training pipeline
dragon_step_merge Steps of a post-training pipeline
dragon_step_prefer Steps of a post-training pipeline
dragon_step_publish Steps of a post-training pipeline
dragon_step_reinforce Steps of a post-training pipeline
dragon_step_synthesize_pairs Steps of a post-training pipeline
dragon_step_train Steps of a post-training pipeline
dragon_synthesize Write fine-tuning data with a teacher model
dragon_synthesize_pairs Build preference pairs from a model's own samples
dragon_train Fine-tune a model with LoRA
dragon_train_args Training settings
dragon_unarchive_run Archive, restore, or delete a run
dragon_wait Wait for a run to finish
dragon_worker_stop Stop the local inference worker