├── README.md ├── blip3o ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-310.pyc │ ├── __init__.cpython-311.pyc │ ├── constants.cpython-310.pyc │ ├── constants.cpython-311.pyc │ ├── utils.cpython-310.pyc │ └── utils.cpython-311.pyc ├── constants.py ├── conversation.py ├── data │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-310.pyc │ │ ├── __init__.cpython-311.pyc │ │ ├── dataset.cpython-310.pyc │ │ └── dataset.cpython-311.pyc │ └── dataset.py ├── mm_utils.py ├── model │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-310.pyc │ │ ├── __init__.cpython-311.pyc │ │ ├── blip3o_arch.cpython-310.pyc │ │ ├── blip3o_arch.cpython-311.pyc │ │ ├── llava_arch.cpython-310.pyc │ │ └── llava_arch.cpython-311.pyc │ ├── blip3o_arch.py │ ├── builder.py │ ├── language_model │ │ ├── __pycache__ │ │ │ ├── blip3o_qwen.cpython-310.pyc │ │ │ ├── blip3o_qwen.cpython-311.pyc │ │ │ ├── blip3o_qwen_grpo.cpython-310.pyc │ │ │ ├── blip3o_qwen_grpo.cpython-311.pyc │ │ │ ├── blip3o_qwen_inference.cpython-310.pyc │ │ │ ├── blip3o_qwen_inference.cpython-311.pyc │ │ │ ├── llava_qwen.cpython-310.pyc │ │ │ ├── llava_qwen.cpython-311.pyc │ │ │ ├── llava_qwen_grpo.cpython-310.pyc │ │ │ ├── llava_qwen_grpo.cpython-311.pyc │ │ │ ├── llava_qwen_inference.cpython-310.pyc │ │ │ └── llava_qwen_inference.cpython-311.pyc │ │ ├── blip3o_qwen.py │ │ ├── blip3o_qwen_grpo.py │ │ └── blip3o_qwen_inference.py │ ├── multimodal_decoder │ │ ├── __pycache__ │ │ │ ├── builder.cpython-310.pyc │ │ │ ├── builder.cpython-311.pyc │ │ │ ├── ta_tok_encoder.cpython-310.pyc │ │ │ └── ta_tok_encoder.cpython-311.pyc │ │ └── builder.py │ └── multimodal_encoder │ │ ├── __pycache__ │ │ ├── builder.cpython-310.pyc │ │ ├── builder.cpython-311.pyc │ │ ├── ta_tok_encoder.cpython-310.pyc │ │ └── ta_tok_encoder.cpython-311.pyc │ │ ├── builder.py │ │ └── ta_tok_encoder.py ├── train │ ├── __pycache__ │ │ ├── blip3o_trainer.cpython-310.pyc │ │ ├── blip3o_trainer.cpython-311.pyc │ │ ├── grpo_trainer.cpython-311.pyc │ │ ├── llava_trainer.cpython-310.pyc │ │ └── llava_trainer.cpython-311.pyc │ ├── blip3o_trainer.py │ └── train.py └── utils.py ├── figure ├── arch.png ├── blip3o_next.png ├── image.png └── wechat_2.jpg ├── gradio ├── animal-compare.png └── funny_image.jpeg ├── inference.py ├── requirements.txt ├── scripts ├── debug.sh ├── run.sh ├── sft.sh ├── zero1.json └── zero2.json ├── setup.py ├── tok ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-310.pyc │ ├── __init__.cpython-311.pyc │ ├── mm_autoencoder.cpython-311.pyc │ ├── models.cpython-310.pyc │ ├── models.cpython-311.pyc │ ├── ta_tok.cpython-310.pyc │ ├── ta_tok.cpython-311.pyc │ ├── utils.cpython-310.pyc │ └── utils.cpython-311.pyc ├── ar_dtok │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-310.pyc │ │ ├── __init__.cpython-311.pyc │ │ ├── ar_model.cpython-311.pyc │ │ ├── bottleneck.cpython-310.pyc │ │ ├── bottleneck.cpython-311.pyc │ │ ├── generate.cpython-311.pyc │ │ ├── vqvae.cpython-310.pyc │ │ └── vqvae.cpython-311.pyc │ ├── ar_model.py │ ├── bottleneck.py │ ├── generate.py │ └── vqvae.py ├── mm_autoencoder.py ├── models.py ├── ta_tok.py └── utils.py └── trl ├── README.md ├── examples ├── README.md ├── accelerate_configs │ ├── deepspeed_zero1.yaml │ ├── deepspeed_zero2.yaml │ ├── deepspeed_zero3.yaml │ ├── fsdp1.yaml │ ├── fsdp2.yaml │ ├── multi_gpu.yaml │ └── single_gpu.yaml ├── cli_configs │ └── example_config.yaml ├── datasets │ ├── hh-rlhf-helpful-base.py │ ├── lm-human-preferences-descriptiveness.py │ ├── lm-human-preferences-sentiment.py │ ├── math_shepherd.py │ ├── prm800k.py │ ├── rlaif-v.py │ ├── tldr.py │ ├── tldr_preference.py │ ├── ultrafeedback-prompt.py │ └── ultrafeedback.py ├── notebooks │ ├── README.md │ ├── best_of_n.ipynb │ ├── gpt2-sentiment-control.ipynb │ └── gpt2-sentiment.ipynb ├── research_projects │ ├── README.md │ ├── layer_skip │ │ ├── README.md │ │ └── scripts │ │ │ ├── benchmark_layer_skip.py │ │ │ ├── config.py │ │ │ ├── custom_trainer.py │ │ │ └── layer_skip_sft.py │ ├── stack_llama │ │ └── scripts │ │ │ ├── README.md │ │ │ ├── merge_peft_adapter.py │ │ │ ├── reward_modeling.py │ │ │ ├── rl_training.py │ │ │ └── supervised_finetuning.py │ ├── stack_llama_2 │ │ └── scripts │ │ │ ├── README.md │ │ │ ├── dpo_llama2.py │ │ │ ├── requirements.txt │ │ │ └── sft_llama2.py │ └── toxicity │ │ ├── README.md │ │ └── scripts │ │ ├── evaluate-toxicity.py │ │ └── gpt-j-6b-toxicity.py └── scripts │ ├── alignprop.py │ ├── bco.py │ ├── cpo.py │ ├── ddpo.py │ ├── dpo.py │ ├── dpo_online.py │ ├── dpo_vlm.py │ ├── evals │ └── judge_tldr.py │ ├── gkd.py │ ├── grpo_vlm.py │ ├── kto.py │ ├── mpo_vlm.py │ ├── nash_md.py │ ├── orpo.py │ ├── ppo │ ├── ppo.py │ └── ppo_tldr.py │ ├── prm.py │ ├── reward_modeling.py │ ├── rloo │ ├── rloo.py │ └── rloo_tldr.py │ ├── sft.py │ ├── sft_gemma3.py │ ├── sft_video_llm.py │ ├── sft_vlm.py │ ├── sft_vlm_gemma3.py │ ├── sft_vlm_smol_vlm.py │ └── xpo.py ├── inference.py ├── ocr_train.txt ├── requirements.txt ├── run.sh ├── test_ocr.png ├── test_ocr.py ├── train_grpo.py └── trl ├── __init__.py ├── __pycache__ ├── __init__.cpython-310.pyc ├── __init__.cpython-311.pyc ├── data_utils.cpython-310.pyc ├── data_utils.cpython-311.pyc ├── import_utils.cpython-310.pyc ├── import_utils.cpython-311.pyc ├── mergekit_utils.cpython-310.pyc └── mergekit_utils.cpython-311.pyc ├── accelerate_configs ├── fsdp1.yaml ├── fsdp2.yaml ├── multi_gpu.yaml ├── single_gpu.yaml ├── zero1.yaml ├── zero2.yaml └── zero3.yaml ├── cli.py ├── core.py ├── data_utils.py ├── environment ├── __init__.py └── base_environment.py ├── extras ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-310.pyc │ ├── __init__.cpython-311.pyc │ ├── profiling.cpython-310.pyc │ ├── profiling.cpython-311.pyc │ ├── vllm_client.cpython-310.pyc │ └── vllm_client.cpython-311.pyc ├── best_of_n_sampler.py ├── dataset_formatting.py ├── profiling.py └── vllm_client.py ├── import_utils.py ├── mergekit_utils.py ├── models ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-310.pyc │ ├── __init__.cpython-311.pyc │ ├── modeling_base.cpython-310.pyc │ ├── modeling_base.cpython-311.pyc │ ├── modeling_value_head.cpython-310.pyc │ ├── modeling_value_head.cpython-311.pyc │ ├── utils.cpython-310.pyc │ └── utils.cpython-311.pyc ├── activation_offloading.py ├── auxiliary_modules.py ├── modeling_base.py ├── modeling_sd_base.py ├── modeling_value_head.py ├── sd_utils.py └── utils.py ├── rewards ├── __init__.py └── format_rewards.py ├── scripts ├── __init__.py ├── dpo.py ├── env.py ├── grpo.py ├── kto.py ├── sft.py ├── utils.py └── vllm_serve.py ├── templates └── lm_model_card.md └── trainer ├── __init__.py ├── __pycache__ ├── __init__.cpython-310.pyc ├── __init__.cpython-311.pyc ├── callbacks.cpython-310.pyc ├── callbacks.cpython-311.pyc ├── grpo_config.cpython-310.pyc ├── grpo_config.cpython-311.pyc ├── grpo_trainer.cpython-310.pyc ├── grpo_trainer.cpython-311.pyc ├── judges.cpython-310.pyc ├── judges.cpython-311.pyc ├── model_config.cpython-310.pyc ├── model_config.cpython-311.pyc ├── utils.cpython-310.pyc └── utils.cpython-311.pyc ├── alignprop_config.py ├── alignprop_trainer.py ├── bco_config.py ├── bco_trainer.py ├── callbacks.py ├── cpo_config.py ├── cpo_trainer.py ├── ddpo_config.py ├── ddpo_trainer.py ├── dpo_config.py ├── dpo_trainer.py ├── gkd_config.py ├── gkd_trainer.py ├── grpo_config.py ├── grpo_trainer.py ├── iterative_sft_config.py ├── iterative_sft_trainer.py ├── judges.py ├── kto_config.py ├── kto_trainer.py ├── model_config.py ├── nash_md_config.py ├── nash_md_trainer.py ├── online_dpo_config.py ├── online_dpo_trainer.py ├── orpo_config.py ├── orpo_trainer.py ├── ppo_config.py ├── ppo_trainer.py ├── prm_config.py ├── prm_trainer.py ├── reward_config.py ├── reward_trainer.py ├── rloo_config.py ├── rloo_trainer.py ├── sft_config.py ├── sft_trainer.py ├── utils.py ├── xpo_config.py └── xpo_trainer.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/README.md -------------------------------------------------------------------------------- /blip3o/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /blip3o/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/__pycache__/__init__.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/__pycache__/__init__.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/__pycache__/constants.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/__pycache__/constants.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/__pycache__/constants.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/__pycache__/constants.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/__pycache__/utils.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/__pycache__/utils.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/__pycache__/utils.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/__pycache__/utils.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/constants.py -------------------------------------------------------------------------------- /blip3o/conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/conversation.py -------------------------------------------------------------------------------- /blip3o/data/__init__.py: -------------------------------------------------------------------------------- 1 | from .dataset import * -------------------------------------------------------------------------------- /blip3o/data/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/data/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/data/__pycache__/__init__.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/data/__pycache__/__init__.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/data/__pycache__/dataset.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/data/__pycache__/dataset.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/data/__pycache__/dataset.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/data/__pycache__/dataset.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/data/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/data/dataset.py -------------------------------------------------------------------------------- /blip3o/mm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/mm_utils.py -------------------------------------------------------------------------------- /blip3o/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/__init__.py -------------------------------------------------------------------------------- /blip3o/model/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/model/__pycache__/__init__.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/__pycache__/__init__.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/model/__pycache__/blip3o_arch.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/__pycache__/blip3o_arch.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/model/__pycache__/blip3o_arch.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/__pycache__/blip3o_arch.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/model/__pycache__/llava_arch.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/__pycache__/llava_arch.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/model/__pycache__/llava_arch.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/__pycache__/llava_arch.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/model/blip3o_arch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/blip3o_arch.py -------------------------------------------------------------------------------- /blip3o/model/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/builder.py -------------------------------------------------------------------------------- /blip3o/model/language_model/__pycache__/blip3o_qwen.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/language_model/__pycache__/blip3o_qwen.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/model/language_model/__pycache__/blip3o_qwen.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/language_model/__pycache__/blip3o_qwen.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/model/language_model/__pycache__/blip3o_qwen_grpo.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/language_model/__pycache__/blip3o_qwen_grpo.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/model/language_model/__pycache__/blip3o_qwen_grpo.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/language_model/__pycache__/blip3o_qwen_grpo.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/model/language_model/__pycache__/blip3o_qwen_inference.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/language_model/__pycache__/blip3o_qwen_inference.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/model/language_model/__pycache__/blip3o_qwen_inference.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/language_model/__pycache__/blip3o_qwen_inference.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/model/language_model/__pycache__/llava_qwen.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/language_model/__pycache__/llava_qwen.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/model/language_model/__pycache__/llava_qwen.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/language_model/__pycache__/llava_qwen.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/model/language_model/__pycache__/llava_qwen_grpo.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/language_model/__pycache__/llava_qwen_grpo.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/model/language_model/__pycache__/llava_qwen_grpo.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/language_model/__pycache__/llava_qwen_grpo.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/model/language_model/__pycache__/llava_qwen_inference.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/language_model/__pycache__/llava_qwen_inference.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/model/language_model/__pycache__/llava_qwen_inference.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/language_model/__pycache__/llava_qwen_inference.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/model/language_model/blip3o_qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/language_model/blip3o_qwen.py -------------------------------------------------------------------------------- /blip3o/model/language_model/blip3o_qwen_grpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/language_model/blip3o_qwen_grpo.py -------------------------------------------------------------------------------- /blip3o/model/language_model/blip3o_qwen_inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/language_model/blip3o_qwen_inference.py -------------------------------------------------------------------------------- /blip3o/model/multimodal_decoder/__pycache__/builder.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/multimodal_decoder/__pycache__/builder.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/model/multimodal_decoder/__pycache__/builder.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/multimodal_decoder/__pycache__/builder.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/model/multimodal_decoder/__pycache__/ta_tok_encoder.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/multimodal_decoder/__pycache__/ta_tok_encoder.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/model/multimodal_decoder/__pycache__/ta_tok_encoder.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/multimodal_decoder/__pycache__/ta_tok_encoder.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/model/multimodal_decoder/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/multimodal_decoder/builder.py -------------------------------------------------------------------------------- /blip3o/model/multimodal_encoder/__pycache__/builder.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/multimodal_encoder/__pycache__/builder.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/model/multimodal_encoder/__pycache__/builder.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/multimodal_encoder/__pycache__/builder.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/model/multimodal_encoder/__pycache__/ta_tok_encoder.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/multimodal_encoder/__pycache__/ta_tok_encoder.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/model/multimodal_encoder/__pycache__/ta_tok_encoder.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/multimodal_encoder/__pycache__/ta_tok_encoder.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/model/multimodal_encoder/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/multimodal_encoder/builder.py -------------------------------------------------------------------------------- /blip3o/model/multimodal_encoder/ta_tok_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/model/multimodal_encoder/ta_tok_encoder.py -------------------------------------------------------------------------------- /blip3o/train/__pycache__/blip3o_trainer.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/train/__pycache__/blip3o_trainer.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/train/__pycache__/blip3o_trainer.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/train/__pycache__/blip3o_trainer.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/train/__pycache__/grpo_trainer.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/train/__pycache__/grpo_trainer.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/train/__pycache__/llava_trainer.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/train/__pycache__/llava_trainer.cpython-310.pyc -------------------------------------------------------------------------------- /blip3o/train/__pycache__/llava_trainer.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/train/__pycache__/llava_trainer.cpython-311.pyc -------------------------------------------------------------------------------- /blip3o/train/blip3o_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/train/blip3o_trainer.py -------------------------------------------------------------------------------- /blip3o/train/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/train/train.py -------------------------------------------------------------------------------- /blip3o/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/blip3o/utils.py -------------------------------------------------------------------------------- /figure/arch.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/figure/arch.png -------------------------------------------------------------------------------- /figure/blip3o_next.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/figure/blip3o_next.png -------------------------------------------------------------------------------- /figure/image.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/figure/image.png -------------------------------------------------------------------------------- /figure/wechat_2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/figure/wechat_2.jpg -------------------------------------------------------------------------------- /gradio/animal-compare.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/gradio/animal-compare.png -------------------------------------------------------------------------------- /gradio/funny_image.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/gradio/funny_image.jpeg -------------------------------------------------------------------------------- /inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/inference.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/requirements.txt -------------------------------------------------------------------------------- /scripts/debug.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/scripts/debug.sh -------------------------------------------------------------------------------- /scripts/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/scripts/run.sh -------------------------------------------------------------------------------- /scripts/sft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/scripts/sft.sh -------------------------------------------------------------------------------- /scripts/zero1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/scripts/zero1.json -------------------------------------------------------------------------------- /scripts/zero2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/scripts/zero2.json -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/setup.py -------------------------------------------------------------------------------- /tok/__init__.py: -------------------------------------------------------------------------------- 1 | from .ar_dtok import * -------------------------------------------------------------------------------- /tok/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /tok/__pycache__/__init__.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/__pycache__/__init__.cpython-311.pyc -------------------------------------------------------------------------------- /tok/__pycache__/mm_autoencoder.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/__pycache__/mm_autoencoder.cpython-311.pyc -------------------------------------------------------------------------------- /tok/__pycache__/models.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/__pycache__/models.cpython-310.pyc -------------------------------------------------------------------------------- /tok/__pycache__/models.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/__pycache__/models.cpython-311.pyc -------------------------------------------------------------------------------- /tok/__pycache__/ta_tok.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/__pycache__/ta_tok.cpython-310.pyc -------------------------------------------------------------------------------- /tok/__pycache__/ta_tok.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/__pycache__/ta_tok.cpython-311.pyc -------------------------------------------------------------------------------- /tok/__pycache__/utils.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/__pycache__/utils.cpython-310.pyc -------------------------------------------------------------------------------- /tok/__pycache__/utils.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/__pycache__/utils.cpython-311.pyc -------------------------------------------------------------------------------- /tok/ar_dtok/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/ar_dtok/__init__.py -------------------------------------------------------------------------------- /tok/ar_dtok/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/ar_dtok/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /tok/ar_dtok/__pycache__/__init__.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/ar_dtok/__pycache__/__init__.cpython-311.pyc -------------------------------------------------------------------------------- /tok/ar_dtok/__pycache__/ar_model.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/ar_dtok/__pycache__/ar_model.cpython-311.pyc -------------------------------------------------------------------------------- /tok/ar_dtok/__pycache__/bottleneck.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/ar_dtok/__pycache__/bottleneck.cpython-310.pyc -------------------------------------------------------------------------------- /tok/ar_dtok/__pycache__/bottleneck.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/ar_dtok/__pycache__/bottleneck.cpython-311.pyc -------------------------------------------------------------------------------- /tok/ar_dtok/__pycache__/generate.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/ar_dtok/__pycache__/generate.cpython-311.pyc -------------------------------------------------------------------------------- /tok/ar_dtok/__pycache__/vqvae.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/ar_dtok/__pycache__/vqvae.cpython-310.pyc -------------------------------------------------------------------------------- /tok/ar_dtok/__pycache__/vqvae.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/ar_dtok/__pycache__/vqvae.cpython-311.pyc -------------------------------------------------------------------------------- /tok/ar_dtok/ar_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/ar_dtok/ar_model.py -------------------------------------------------------------------------------- /tok/ar_dtok/bottleneck.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/ar_dtok/bottleneck.py -------------------------------------------------------------------------------- /tok/ar_dtok/generate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/ar_dtok/generate.py -------------------------------------------------------------------------------- /tok/ar_dtok/vqvae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/ar_dtok/vqvae.py -------------------------------------------------------------------------------- /tok/mm_autoencoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/mm_autoencoder.py -------------------------------------------------------------------------------- /tok/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/models.py -------------------------------------------------------------------------------- /tok/ta_tok.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/ta_tok.py -------------------------------------------------------------------------------- /tok/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/tok/utils.py -------------------------------------------------------------------------------- /trl/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/README.md -------------------------------------------------------------------------------- /trl/examples/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/README.md -------------------------------------------------------------------------------- /trl/examples/accelerate_configs/deepspeed_zero1.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/accelerate_configs/deepspeed_zero1.yaml -------------------------------------------------------------------------------- /trl/examples/accelerate_configs/deepspeed_zero2.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/accelerate_configs/deepspeed_zero2.yaml -------------------------------------------------------------------------------- /trl/examples/accelerate_configs/deepspeed_zero3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/accelerate_configs/deepspeed_zero3.yaml -------------------------------------------------------------------------------- /trl/examples/accelerate_configs/fsdp1.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/accelerate_configs/fsdp1.yaml -------------------------------------------------------------------------------- /trl/examples/accelerate_configs/fsdp2.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/accelerate_configs/fsdp2.yaml -------------------------------------------------------------------------------- /trl/examples/accelerate_configs/multi_gpu.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/accelerate_configs/multi_gpu.yaml -------------------------------------------------------------------------------- /trl/examples/accelerate_configs/single_gpu.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/accelerate_configs/single_gpu.yaml -------------------------------------------------------------------------------- /trl/examples/cli_configs/example_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/cli_configs/example_config.yaml -------------------------------------------------------------------------------- /trl/examples/datasets/hh-rlhf-helpful-base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/datasets/hh-rlhf-helpful-base.py -------------------------------------------------------------------------------- /trl/examples/datasets/lm-human-preferences-descriptiveness.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/datasets/lm-human-preferences-descriptiveness.py -------------------------------------------------------------------------------- /trl/examples/datasets/lm-human-preferences-sentiment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/datasets/lm-human-preferences-sentiment.py -------------------------------------------------------------------------------- /trl/examples/datasets/math_shepherd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/datasets/math_shepherd.py -------------------------------------------------------------------------------- /trl/examples/datasets/prm800k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/datasets/prm800k.py -------------------------------------------------------------------------------- /trl/examples/datasets/rlaif-v.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/datasets/rlaif-v.py -------------------------------------------------------------------------------- /trl/examples/datasets/tldr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/datasets/tldr.py -------------------------------------------------------------------------------- /trl/examples/datasets/tldr_preference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/datasets/tldr_preference.py -------------------------------------------------------------------------------- /trl/examples/datasets/ultrafeedback-prompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/datasets/ultrafeedback-prompt.py -------------------------------------------------------------------------------- /trl/examples/datasets/ultrafeedback.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/datasets/ultrafeedback.py -------------------------------------------------------------------------------- /trl/examples/notebooks/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/notebooks/README.md -------------------------------------------------------------------------------- /trl/examples/notebooks/best_of_n.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/notebooks/best_of_n.ipynb -------------------------------------------------------------------------------- /trl/examples/notebooks/gpt2-sentiment-control.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/notebooks/gpt2-sentiment-control.ipynb -------------------------------------------------------------------------------- /trl/examples/notebooks/gpt2-sentiment.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/notebooks/gpt2-sentiment.ipynb -------------------------------------------------------------------------------- /trl/examples/research_projects/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/README.md -------------------------------------------------------------------------------- /trl/examples/research_projects/layer_skip/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/layer_skip/README.md -------------------------------------------------------------------------------- /trl/examples/research_projects/layer_skip/scripts/benchmark_layer_skip.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/layer_skip/scripts/benchmark_layer_skip.py -------------------------------------------------------------------------------- /trl/examples/research_projects/layer_skip/scripts/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/layer_skip/scripts/config.py -------------------------------------------------------------------------------- /trl/examples/research_projects/layer_skip/scripts/custom_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/layer_skip/scripts/custom_trainer.py -------------------------------------------------------------------------------- /trl/examples/research_projects/layer_skip/scripts/layer_skip_sft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/layer_skip/scripts/layer_skip_sft.py -------------------------------------------------------------------------------- /trl/examples/research_projects/stack_llama/scripts/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/stack_llama/scripts/README.md -------------------------------------------------------------------------------- /trl/examples/research_projects/stack_llama/scripts/merge_peft_adapter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/stack_llama/scripts/merge_peft_adapter.py -------------------------------------------------------------------------------- /trl/examples/research_projects/stack_llama/scripts/reward_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/stack_llama/scripts/reward_modeling.py -------------------------------------------------------------------------------- /trl/examples/research_projects/stack_llama/scripts/rl_training.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/stack_llama/scripts/rl_training.py -------------------------------------------------------------------------------- /trl/examples/research_projects/stack_llama/scripts/supervised_finetuning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/stack_llama/scripts/supervised_finetuning.py -------------------------------------------------------------------------------- /trl/examples/research_projects/stack_llama_2/scripts/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/stack_llama_2/scripts/README.md -------------------------------------------------------------------------------- /trl/examples/research_projects/stack_llama_2/scripts/dpo_llama2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/stack_llama_2/scripts/dpo_llama2.py -------------------------------------------------------------------------------- /trl/examples/research_projects/stack_llama_2/scripts/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/stack_llama_2/scripts/requirements.txt -------------------------------------------------------------------------------- /trl/examples/research_projects/stack_llama_2/scripts/sft_llama2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/stack_llama_2/scripts/sft_llama2.py -------------------------------------------------------------------------------- /trl/examples/research_projects/toxicity/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/toxicity/README.md -------------------------------------------------------------------------------- /trl/examples/research_projects/toxicity/scripts/evaluate-toxicity.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/toxicity/scripts/evaluate-toxicity.py -------------------------------------------------------------------------------- /trl/examples/research_projects/toxicity/scripts/gpt-j-6b-toxicity.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/research_projects/toxicity/scripts/gpt-j-6b-toxicity.py -------------------------------------------------------------------------------- /trl/examples/scripts/alignprop.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/alignprop.py -------------------------------------------------------------------------------- /trl/examples/scripts/bco.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/bco.py -------------------------------------------------------------------------------- /trl/examples/scripts/cpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/cpo.py -------------------------------------------------------------------------------- /trl/examples/scripts/ddpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/ddpo.py -------------------------------------------------------------------------------- /trl/examples/scripts/dpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/dpo.py -------------------------------------------------------------------------------- /trl/examples/scripts/dpo_online.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/dpo_online.py -------------------------------------------------------------------------------- /trl/examples/scripts/dpo_vlm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/dpo_vlm.py -------------------------------------------------------------------------------- /trl/examples/scripts/evals/judge_tldr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/evals/judge_tldr.py -------------------------------------------------------------------------------- /trl/examples/scripts/gkd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/gkd.py -------------------------------------------------------------------------------- /trl/examples/scripts/grpo_vlm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/grpo_vlm.py -------------------------------------------------------------------------------- /trl/examples/scripts/kto.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/kto.py -------------------------------------------------------------------------------- /trl/examples/scripts/mpo_vlm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/mpo_vlm.py -------------------------------------------------------------------------------- /trl/examples/scripts/nash_md.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/nash_md.py -------------------------------------------------------------------------------- /trl/examples/scripts/orpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/orpo.py -------------------------------------------------------------------------------- /trl/examples/scripts/ppo/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/ppo/ppo.py -------------------------------------------------------------------------------- /trl/examples/scripts/ppo/ppo_tldr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/ppo/ppo_tldr.py -------------------------------------------------------------------------------- /trl/examples/scripts/prm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/prm.py -------------------------------------------------------------------------------- /trl/examples/scripts/reward_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/reward_modeling.py -------------------------------------------------------------------------------- /trl/examples/scripts/rloo/rloo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/rloo/rloo.py -------------------------------------------------------------------------------- /trl/examples/scripts/rloo/rloo_tldr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/rloo/rloo_tldr.py -------------------------------------------------------------------------------- /trl/examples/scripts/sft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/sft.py -------------------------------------------------------------------------------- /trl/examples/scripts/sft_gemma3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/sft_gemma3.py -------------------------------------------------------------------------------- /trl/examples/scripts/sft_video_llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/sft_video_llm.py -------------------------------------------------------------------------------- /trl/examples/scripts/sft_vlm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/sft_vlm.py -------------------------------------------------------------------------------- /trl/examples/scripts/sft_vlm_gemma3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/sft_vlm_gemma3.py -------------------------------------------------------------------------------- /trl/examples/scripts/sft_vlm_smol_vlm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/sft_vlm_smol_vlm.py -------------------------------------------------------------------------------- /trl/examples/scripts/xpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/examples/scripts/xpo.py -------------------------------------------------------------------------------- /trl/inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/inference.py -------------------------------------------------------------------------------- /trl/ocr_train.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/ocr_train.txt -------------------------------------------------------------------------------- /trl/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/requirements.txt -------------------------------------------------------------------------------- /trl/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/run.sh -------------------------------------------------------------------------------- /trl/test_ocr.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/test_ocr.png -------------------------------------------------------------------------------- /trl/test_ocr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/test_ocr.py -------------------------------------------------------------------------------- /trl/train_grpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/train_grpo.py -------------------------------------------------------------------------------- /trl/trl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/__init__.py -------------------------------------------------------------------------------- /trl/trl/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/__pycache__/__init__.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/__pycache__/__init__.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/__pycache__/data_utils.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/__pycache__/data_utils.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/__pycache__/data_utils.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/__pycache__/data_utils.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/__pycache__/import_utils.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/__pycache__/import_utils.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/__pycache__/import_utils.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/__pycache__/import_utils.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/__pycache__/mergekit_utils.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/__pycache__/mergekit_utils.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/__pycache__/mergekit_utils.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/__pycache__/mergekit_utils.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/accelerate_configs/fsdp1.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/accelerate_configs/fsdp1.yaml -------------------------------------------------------------------------------- /trl/trl/accelerate_configs/fsdp2.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/accelerate_configs/fsdp2.yaml -------------------------------------------------------------------------------- /trl/trl/accelerate_configs/multi_gpu.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/accelerate_configs/multi_gpu.yaml -------------------------------------------------------------------------------- /trl/trl/accelerate_configs/single_gpu.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/accelerate_configs/single_gpu.yaml -------------------------------------------------------------------------------- /trl/trl/accelerate_configs/zero1.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/accelerate_configs/zero1.yaml -------------------------------------------------------------------------------- /trl/trl/accelerate_configs/zero2.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/accelerate_configs/zero2.yaml -------------------------------------------------------------------------------- /trl/trl/accelerate_configs/zero3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/accelerate_configs/zero3.yaml -------------------------------------------------------------------------------- /trl/trl/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/cli.py -------------------------------------------------------------------------------- /trl/trl/core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/core.py -------------------------------------------------------------------------------- /trl/trl/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/data_utils.py -------------------------------------------------------------------------------- /trl/trl/environment/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/environment/__init__.py -------------------------------------------------------------------------------- /trl/trl/environment/base_environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/environment/base_environment.py -------------------------------------------------------------------------------- /trl/trl/extras/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/extras/__init__.py -------------------------------------------------------------------------------- /trl/trl/extras/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/extras/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/extras/__pycache__/__init__.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/extras/__pycache__/__init__.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/extras/__pycache__/profiling.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/extras/__pycache__/profiling.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/extras/__pycache__/profiling.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/extras/__pycache__/profiling.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/extras/__pycache__/vllm_client.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/extras/__pycache__/vllm_client.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/extras/__pycache__/vllm_client.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/extras/__pycache__/vllm_client.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/extras/best_of_n_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/extras/best_of_n_sampler.py -------------------------------------------------------------------------------- /trl/trl/extras/dataset_formatting.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/extras/dataset_formatting.py -------------------------------------------------------------------------------- /trl/trl/extras/profiling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/extras/profiling.py -------------------------------------------------------------------------------- /trl/trl/extras/vllm_client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/extras/vllm_client.py -------------------------------------------------------------------------------- /trl/trl/import_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/import_utils.py -------------------------------------------------------------------------------- /trl/trl/mergekit_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/mergekit_utils.py -------------------------------------------------------------------------------- /trl/trl/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/models/__init__.py -------------------------------------------------------------------------------- /trl/trl/models/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/models/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/models/__pycache__/__init__.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/models/__pycache__/__init__.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/models/__pycache__/modeling_base.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/models/__pycache__/modeling_base.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/models/__pycache__/modeling_base.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/models/__pycache__/modeling_base.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/models/__pycache__/modeling_value_head.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/models/__pycache__/modeling_value_head.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/models/__pycache__/modeling_value_head.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/models/__pycache__/modeling_value_head.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/models/__pycache__/utils.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/models/__pycache__/utils.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/models/__pycache__/utils.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/models/__pycache__/utils.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/models/activation_offloading.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/models/activation_offloading.py -------------------------------------------------------------------------------- /trl/trl/models/auxiliary_modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/models/auxiliary_modules.py -------------------------------------------------------------------------------- /trl/trl/models/modeling_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/models/modeling_base.py -------------------------------------------------------------------------------- /trl/trl/models/modeling_sd_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/models/modeling_sd_base.py -------------------------------------------------------------------------------- /trl/trl/models/modeling_value_head.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/models/modeling_value_head.py -------------------------------------------------------------------------------- /trl/trl/models/sd_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/models/sd_utils.py -------------------------------------------------------------------------------- /trl/trl/models/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/models/utils.py -------------------------------------------------------------------------------- /trl/trl/rewards/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/rewards/__init__.py -------------------------------------------------------------------------------- /trl/trl/rewards/format_rewards.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/rewards/format_rewards.py -------------------------------------------------------------------------------- /trl/trl/scripts/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/scripts/__init__.py -------------------------------------------------------------------------------- /trl/trl/scripts/dpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/scripts/dpo.py -------------------------------------------------------------------------------- /trl/trl/scripts/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/scripts/env.py -------------------------------------------------------------------------------- /trl/trl/scripts/grpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/scripts/grpo.py -------------------------------------------------------------------------------- /trl/trl/scripts/kto.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/scripts/kto.py -------------------------------------------------------------------------------- /trl/trl/scripts/sft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/scripts/sft.py -------------------------------------------------------------------------------- /trl/trl/scripts/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/scripts/utils.py -------------------------------------------------------------------------------- /trl/trl/scripts/vllm_serve.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/scripts/vllm_serve.py -------------------------------------------------------------------------------- /trl/trl/templates/lm_model_card.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/templates/lm_model_card.md -------------------------------------------------------------------------------- /trl/trl/trainer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/__init__.py -------------------------------------------------------------------------------- /trl/trl/trainer/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/trainer/__pycache__/__init__.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/__pycache__/__init__.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/trainer/__pycache__/callbacks.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/__pycache__/callbacks.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/trainer/__pycache__/callbacks.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/__pycache__/callbacks.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/trainer/__pycache__/grpo_config.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/__pycache__/grpo_config.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/trainer/__pycache__/grpo_config.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/__pycache__/grpo_config.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/trainer/__pycache__/grpo_trainer.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/__pycache__/grpo_trainer.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/trainer/__pycache__/grpo_trainer.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/__pycache__/grpo_trainer.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/trainer/__pycache__/judges.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/__pycache__/judges.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/trainer/__pycache__/judges.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/__pycache__/judges.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/trainer/__pycache__/model_config.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/__pycache__/model_config.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/trainer/__pycache__/model_config.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/__pycache__/model_config.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/trainer/__pycache__/utils.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/__pycache__/utils.cpython-310.pyc -------------------------------------------------------------------------------- /trl/trl/trainer/__pycache__/utils.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/__pycache__/utils.cpython-311.pyc -------------------------------------------------------------------------------- /trl/trl/trainer/alignprop_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/alignprop_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/alignprop_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/alignprop_trainer.py -------------------------------------------------------------------------------- /trl/trl/trainer/bco_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/bco_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/bco_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/bco_trainer.py -------------------------------------------------------------------------------- /trl/trl/trainer/callbacks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/callbacks.py -------------------------------------------------------------------------------- /trl/trl/trainer/cpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/cpo_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/cpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/cpo_trainer.py -------------------------------------------------------------------------------- /trl/trl/trainer/ddpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/ddpo_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/ddpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/ddpo_trainer.py -------------------------------------------------------------------------------- /trl/trl/trainer/dpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/dpo_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/dpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/dpo_trainer.py -------------------------------------------------------------------------------- /trl/trl/trainer/gkd_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/gkd_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/gkd_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/gkd_trainer.py -------------------------------------------------------------------------------- /trl/trl/trainer/grpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/grpo_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/grpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/grpo_trainer.py -------------------------------------------------------------------------------- /trl/trl/trainer/iterative_sft_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/iterative_sft_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/iterative_sft_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/iterative_sft_trainer.py -------------------------------------------------------------------------------- /trl/trl/trainer/judges.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/judges.py -------------------------------------------------------------------------------- /trl/trl/trainer/kto_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/kto_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/kto_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/kto_trainer.py -------------------------------------------------------------------------------- /trl/trl/trainer/model_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/model_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/nash_md_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/nash_md_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/nash_md_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/nash_md_trainer.py -------------------------------------------------------------------------------- /trl/trl/trainer/online_dpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/online_dpo_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/online_dpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/online_dpo_trainer.py -------------------------------------------------------------------------------- /trl/trl/trainer/orpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/orpo_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/orpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/orpo_trainer.py -------------------------------------------------------------------------------- /trl/trl/trainer/ppo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/ppo_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/ppo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/ppo_trainer.py -------------------------------------------------------------------------------- /trl/trl/trainer/prm_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/prm_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/prm_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/prm_trainer.py -------------------------------------------------------------------------------- /trl/trl/trainer/reward_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/reward_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/reward_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/reward_trainer.py -------------------------------------------------------------------------------- /trl/trl/trainer/rloo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/rloo_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/rloo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/rloo_trainer.py -------------------------------------------------------------------------------- /trl/trl/trainer/sft_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/sft_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/sft_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/sft_trainer.py -------------------------------------------------------------------------------- /trl/trl/trainer/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/utils.py -------------------------------------------------------------------------------- /trl/trl/trainer/xpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/xpo_config.py -------------------------------------------------------------------------------- /trl/trl/trainer/xpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JiuhaiChen/BLIP3o/HEAD/trl/trl/trainer/xpo_trainer.py --------------------------------------------------------------------------------