fine-tuning
Repo for fine tuning examples and sample datasets
파일 탐색기
최종 버전 다운로드 (.zip)- azure-ai-fine-tuning
- azure-ai-fine-tuning
- bug_report.md
- feature_request.md
- azure-ai-fine-tuning
- countdown_eval_25.jsonl
- countdown_train_25.jsonl
- countdown_valid_10.jsonl
- .funcignore
- .gitignore
- demo.ipynb
- function_app.py
- grader.py
- host.json
- main.bicep
- main.parameters.json
- README.md
- requirements-demo.txt
- requirements.txt
- test-bad.json
- test-text.json
- test.json
- train_tool.jsonl
- valid_tool.jsonl
- function.json
- .gitignore
- function_app.py
- host.json
- requirements.txt
- run_local.cmd
- README.md
- requirements.txt
- rft-tool-call.ipynb
- mcp.png
- README.md
- RFT_Best_Practice.md
- eval_utils.py
- .gitignore
- baseline.jsonl
- qa.jsonl
- README.md
- requirements.txt
- sarcasm.ipynb
- .env.template
- dpo_finetuning_intel_orca.ipynb
- README.md
- requirements.txt
- training.jsonl
- validation.jsonl
- audio_utils.py
- eval_utils.py
- image_utils.py
- audio_evals_example.ipynb
- image_evals_example.ipynb
- latency_summary.csv
- latency_summary_trimmed.csv
- per_request_latencies.csv
- accuracy_base_vs_ft_models.png
- cnn_training_cli.png
- dogs.png
- ft_job.png
- FT_training_cost.png
- latency_boxplot.png
- latency_histogram.png
- .env.sample
- .gitignore
- cnn_baseline.py
- cnn_best.pt
- cnn_per_class_accuracy.csv
- cnn_test_metrics.txt
- cnn_training_history.csv
- images_classification_vlm.ipynb
- latency_base_ft_models.ipynb
- LICENSE
- README.md
- requirements.txt
- .env.template
- fine-tune-aoai-gpt4-1-for-chart-analysis.ipynb
- qna.png
- README.md
- requirements.txt
- .gitignore
- README.md
- requirements.txt
- Text_to_Python_Fine_Tuning.ipynb
- training_data.jsonl
- validation_data.jsonl
- countdown_eval_100.jsonl
- countdown_train_100.jsonl
- countdown_train_25.jsonl
- countdown_train_raw.jsonl
- countdown_valid_15.jsonl
- countdown_valid_50.jsonl
- countdown_valid_raw.jsonl
- grader_config_aoai.json
- grader_prompt.txt
- response_schema.json
- system_prompt.txt
- AIFoundry_logo.jpg
- md_sp_rs_cg.PNG
- outro.png
- system_prompt.PNG
- title2.png
- dataset_utils.py
- eval_utils.py
- finetune_utils.py
- io_utils.py
- .env.template
- demo.ipynb
- demo_with_python_grader.ipynb
- readme.md
- requirements.txt
- .env.template
- README.md
- requirements.txt
- rft_math_reasoning.ipynb
- training_rft.jsonl
- validation_rft.jsonl
- .env.template
- .gitignore
- Bug_Detection_Fine_Tuning.ipynb
- README.md
- requirements.txt
- .env.template
- README.md
- requirements.txt
- sft_cnn_dailymail.ipynb
- training.jsonl
- validation.jsonl
- .env.template
- README.md
- requirements.txt
- sft_pubmed_summarization.ipynb
- training.jsonl
- validation.jsonl
- zava_tools_openai.json
- zava_tools_openapi.json
- notebook.ipynb
- README.md
- push_prompts.py
- zava_system_prompt.md
- zava_tools.json
- notebook.ipynb
- README.md
- .env.template
- fine-tune-aoai-gpt4-1-action-detection.ipynb
- frame-samples.png
- README.md
- requirements.txt
- VideoFTTools.py
- 01_conversation_length_distribution.png
- 02_message_role_distribution.png
- 03_tool_frequency.png
- 04_tool_sequence_heatmap.png
- 05_topic_distribution.png
- 06_dataset_split.png
- 07_conversation_turns.png
- 08_tool_combinations.png
- 09_ai_classification.png
- 10_cluster_visualization.png
- 11_cluster_sizes.png
- 01_price_distribution.png
- 02_order_status.png
- 03_user_locations.png
- 04_payment_methods.png
- 05_orders_per_user.png
- 06_order_values.png
- 07_top_products.png
- 08_product_availability.png
- 09_user_spending_patterns.png
- 10_order_size_heatmap.png
- 11_product_category_analysis.png
- 12_customer_segmentation.png
- 13_payment_value_correlation.png
- 14_order_status_flow.png
- 15_product_variant_diversity.png
- 16_user_tier_analysis.png
- analysis_summary.json
- box_plot_comparison.png
- comparison_table.png
- cumulative_distribution.png
- detailed_metrics_table.png
- error_distributions.png
- pass_rate_comparison.png
- percentile_comparison.png
- score_distributions.png
- combined_data.json
- download_summary.json
- Step_0.json
- Step_12.json
- Step_15.json
- Step_18.json
- Step_3.json
- Step_6.json
- Step_9.json
- scenario_9_best_output.txt
- scenario_9_comparison.txt
- scenario_9_detailed.json
- scenario_9_detailed_table.png
- scenario_9_scores.png
- scenario_9_summary.csv
- scenario_9_worst_output.txt
- analysis_summary.json
- improvement_delta.png
- outcome_breakdown.png
- pass_rate_progression.png
- scenario_heatmap.png
- scenario_trajectories.png
- score_distributions.png
- score_progression.png
- combined_data.json
- download_summary.json
- Step_0.json
- Step_12.json
- Step_15.json
- Step_3.json
- Step_6.json
- Step_9.json
- scenario_9_best_output.txt
- scenario_9_comparison.txt
- scenario_9_detailed.json
- scenario_9_detailed_table.png
- scenario_9_summary.csv
- scenario_9_worst_output.txt
- analysis_summary.json
- improvement_delta.png
- outcome_breakdown.png
- pass_rate_progression.png
- scenario_heatmap.png
- scenario_trajectories.png
- score_distributions.png
- score_progression.png
- datagen-ToolUse-FineTuneSupervised-train.jsonl
- datagen-ToolUse-FineTuneSupervised-valid.jsonl
- db.json
- eval.jsonl
- openapi_with_policy.json
- policy.md
- retail_tools.json
- rft_eval_step_0_fix.jsonl
- rft_grader-config.json
- rft_test.jsonl
- rft_test_fixed.jsonl
- rft_tools-config.json
- rft_train.jsonl
- rft_train_fixed.jsonl
- rft_train_step_0_fix.jsonl
- sft_test.jsonl
- sft_test_eval.jsonl
- sft_test_eval_expanded.jsonl
- sft_train.jsonl
- tool_call_grader.py
- try.json
- agenda.png
- architecture.png
- cli_base_model.png
- cli_sft.png
- datagen_cluster_analysis.png
- datagen_ui.png
- evals_with_sft.png
- intro2.png
- outro.png
- playground_base_scenario.png
- rft_101.png
- rft_auto_evals.png
- rft_flow.png
- rft_metrics.png
- rft_output_comp.png
- rft_rewards.png
- rft_sample_output_comparision.png
- rft_sample_scores.png
- rft_sample_scores_progression.png
- sft_metrics.png
- eval_create_util.py
- analyze_db_json.py
- analyze_eval_run.py
- analyze_rft_eval.py
- analyze_rft_results.py
- analyze_rft_test_scenario.py
- analyze_synthetic_datagen.py
- convert_to_eval.py
- retail_agent.py
- test_mcp_connectivity.py
- test_retail_agent.py
- .env.example
- .gitignore
- DataAnalysisScripts.md
- demo.ipynb
- README.md
- requirements.txt
- rft_test_scenarios.md
- test_item_fields.py
- TOOLS_README.md
- README.md
- LICENSE.md
- README.md
- training.jsonl
- validation.jsonl
- SCHEMA.md
- clause_matching_training.jsonl
- clause_matching_validation.jsonl
- LICENSE.md
- model_grader.json
- multi_grader.json
- README.md
- schema.json
- LICENSE.md
- medmcq_training.jsonl
- medmcq_validation.jsonl
- README.md
- stringcheck_grader.json
- SCHEMA.md
- LICENSE.md
- README.md
- training.jsonl
- validation.jsonl
- training_data.jsonl
- validation_data.jsonl
- chat_train.jsonl
- chat_validation.jsonl
- LICENSE.md
- README.md
- chat_train.jsonl
- chat_validation.jsonl
- LICENSE.md
- README.md
- README.md
- stock_toolcall_training.jsonl
- stock_toolcall_validation.jsonl
- SCHEMA.md
- README.md
- dpo_sample.jsonl
- rft_sample.jsonl
- sft_sample.jsonl
- agentic-rft.md
- cost-management.md
- data-generation-api.md
- dataset-formats.md
- deployment-formats.md
- distillation.md
- evaluation-methodology.md
- foundry-cli.md
- grader-design.md
- hyperparameters.md
- large-file-uploads.md
- platform-bugs.md
- reward-hacking-prevention.md
- training-curve-analysis.md
- training-types.md
- vision-fine-tuning.md
- __init__.py
- data_stats.py
- validate_dpo.py
- validate_rft.py
- validate_sft.py
- auto_finetune.py
- auto_rft.py
- calibrate_grader.py
- check_training.py
- chunk_and_generate.py
- cleanup.py
- common.py
- content_safety_check.py
- convert_dataset.py
- deploy_model.py
- diagnose_iteration.py
- evaluate_model.py
- generate_dataset.py
- generate_distillation_data.py
- monitor_training.py
- quality_filter.py
- score_dataset.py
- submit_training.py
- transform_traces_jsonl.py
- cobol_intro.md
- retail_openapi.json
- retail_tools.json
- conftest.py
- test_data_generation_e2e.py
- test_skills.py
- auto-finetune.md
- dataset-creation.md
- diagnose-poor-results.md
- experiment-review.md
- full-pipeline.md
- iterative-training.md
- quickstart.md
- synthetic-datagen.md
- traces-to-dataset.md
- .env.template
- pytest.ini
- README.md
- SKILL.md
- .gitignore
- CHANGELOG.md
- code_of_conduct.md
- CONTRIBUTING.md
- GETTING_STARTED.md
- LICENSE
- README.md
- SECURITY.md
// repository documentation
Was this content helpful?
(0 ratings)