| archive | | | 5 items |
| getting_started | | | 10 items |
| kimi_k25 | | | 1 items |
| rl_environments | | | 6 items |
| testing | | | 6 items |
| __init__.py | 383 Bytes | | 11fe2a47 |
| advanced_features_demo.py | 16.3 kB | | 92d00c57 |
| advanced_optimization_techniques.py | 22.9 kB | | d5638da1 |
| api_client_example.py | 14.7 kB | | ff23ed21 |
| api_client_simple.py | 7.28 kB | | d8136b0f |
| auto_research.py | 6.18 kB | | 309916c5 |
| auto_research_quickstart.py | 11.1 kB | | 0e885a80 |
| backend_switch_demo.py | 2 kB | | fcbed0ae |
| complete_grpo_training.py | 11.4 kB | | fabb2a9b |
| continual_learning_planning.py | 3.03 kB | | 36a735f1 |
| custom_math_env.py | 8.34 kB | | ceb36b04 |
| custom_reward_functions.py | 25.2 kB | | fba1c4de |
| customer_service_agent.py | 15.8 kB | | c61f7621 |
| distributed_multi_gpu_training.py | 16.8 kB | | 174ee96c |
| finetune_code_assistant.py | 27.5 kB | | 15f34e16 |
| finetune_deepseek_v4_gspo.py | 741 Bytes | | a264d60b |
| finetune_gemma3_gspo.py | 12.9 kB | | 5acc94a0 |
| finetune_gemma4_31b_gspo.py | 750 Bytes | | a10fbb25 |
| finetune_glm5_1_gspo.py | 9.96 kB | | f5c00207 |
| finetune_glm5_2_gspo.py | 9.96 kB | | f527488b |
| finetune_gpt_oss_gspo.py | 719 Bytes | | 014c967f |
| finetune_gspo.py | 19.6 kB | | 756ab063 |
| finetune_kimi_k25_gspo.py | 15.2 kB | | 57473689 |
| finetune_kimi_k2_5_gspo.py | 1.63 kB | | 7b499d5d |
| finetune_kimi_k2_6_gspo.py | 745 Bytes | | be31c0a4 |
| finetune_kimi_k3_gspo.py | 737 Bytes | | 614f4b4b |
| finetune_llama3_gspo.py | 14.8 kB | | ead5cf36 |
| finetune_mistral_gspo.py | 15.6 kB | | 3b5e2ebe |
| finetune_muse_glimmer_gspo.py | 739 Bytes | | 8e980b70 |
| finetune_nemotron_3_5_gspo.py | 739 Bytes | | e83d470c |
| finetune_qwen3_5_0_8b_gspo.py | 757 Bytes | | f6000854 |
| finetune_qwen3_5_27b_gspo.py | 6.81 kB | | d5dbe77a |
| finetune_qwen3_8_27b_gspo.py | 735 Bytes | | 4e751aed |
| finetune_qwen3_coder_gspo.py | 735 Bytes | | 32978847 |
| finetune_qwen3_gspo.py | 20.6 kB | | be9d27f5 |
| gemma4_config.py | 2.01 kB | | dcaeb5fe |
| glm5_1_config.py | 1.94 kB | | 79e51609 |
| glm5_2_config.py | 1.94 kB | | 4096ab2b |
| grpo_showcase.py | 37.5 kB | | ce135c2c |
| hello_world.py | 4.14 kB | | 64fafc72 |
| hpo_training_example.py | 12.6 kB | | c1b55ca5 |
| interactive_chatbot.py | 11.1 kB | | da440470 |
| kimi_k25_config.py | 28.4 kB | | 6b384878 |
| kimi_k25_rewards.py | 14.5 kB | | a8e84a36 |
| kimi_k2_6_config.py | 1.95 kB | | 5f7ccd14 |
| kimi_k3_config.py | 1.86 kB | | 2995e46c |
| model_presets.py | 645 Bytes | | 55e61409 |
| nsr_verified_reward.py | 2.98 kB | | 97bd3721 |
| physics_symbolic_discovery.py | 3.8 kB | | 455cc87b |
| physics_symbolic_evaluate.py | 4.02 kB | | 58e41f6a |
| production_ready_customer_service.py | 11.2 kB | | b24982db |
| quick_start.py | 9.36 kB | | a28265ca |
| qwen3_5_config.py | 2.01 kB | | cca6f306 |
| qwen3b_gspo_demo.py | 6.12 kB | | c0dcf285 |
| rag_agent_example.py | 25 kB | | 26a7c2b8 |
| simple_rl_training.py | 3.26 kB | | e11bc282 |
| train_reward_model.py | 9.65 kB | | 1dad431f |
| train_with_gspo.py | 8.63 kB | | a486fe44 |
| train_with_trl_grpo.py | 13.9 kB | | f89f6c4e |
| training_modes_quickstart.py | 9 kB | | 446f5d70 |
| trl_grpo_demo.py | 4.39 kB | | ca38a08e |