diff --git a/README.md b/README.md index 9a09a5c..cac9306 100644 --- a/README.md +++ b/README.md @@ -20,7 +20,7 @@ - +

MiniCPM-V 4.0 🤗 🤖 | MiniCPM-o 2.6 🤗 🤖 | MiniCPM-V 2.6 🤗 🤖 | 🍳 Cookbook | 📄 Technical Blog [English/中文] @@ -3122,7 +3122,7 @@ pip install vllm ### Simple Fine-tuning -We support simple fine-tuning with Hugging Face for MiniCPM-o 2.6, MiniCPM-V 2.6, MiniCPM-Llama3-V 2.5 and MiniCPM-V 2.0. +We support simple fine-tuning with Hugging Face for MiniCPM-V 4.0, MiniCPM-o 2.6, MiniCPM-V 2.6, MiniCPM-Llama3-V 2.5 and MiniCPM-V 2.0. [Reference Document](./finetune/readme.md) @@ -3139,7 +3139,7 @@ Best Practices: [MiniCPM-o 2.6](https://github.com/PKU-Alignment/align-anything/ We support fine-tuning MiniCPM-o 2.6 and MiniCPM-V 2.6 with the LLaMA-Factory framework. LLaMA-Factory provides a solution for flexibly customizing the fine-tuning (Lora/Full/Qlora) of 200+ LLMs without the need for coding through the built-in web UI LLaMABoard. It supports various training methods like sft/ppo/dpo/kto and advanced algorithms like Galore/BAdam/LLaMA-Pro/Pissa/LongLoRA. -Best Practices: [MiniCPM-o 2.6 | MiniCPM-V 2.6](./docs/llamafactory_train_and_infer.md). +Best Practices: [MiniCPM-V 4.0 | MiniCPM-o 2.6 | MiniCPM-V 2.6](./docs/llamafactory_train_and_infer.md). ### With the SWIFT Framework diff --git a/README_zh.md b/README_zh.md index f1e7d19..d64ec39 100644 --- a/README_zh.md +++ b/README_zh.md @@ -16,7 +16,7 @@  🍳 使用指南  - +

MiniCPM-V 4.0 🤗 🤖 | MiniCPM-o 2.6 🤗 🤖 | MiniCPM-V 2.6 🤗 🤖 | 📄 技术报告 [中文/English] @@ -2987,7 +2987,7 @@ pip install vllm ### 简易微调 -我们支持使用 Huggingface Transformers 库简易地微调 MiniCPM-o 2.6、MiniCPM-V 2.6、MiniCPM-Llama3-V 2.5 和 MiniCPM-V 2.0 模型。 +我们支持使用 Huggingface Transformers 库简易地微调 MiniCPM-V 4.0、MiniCPM-o 2.6、MiniCPM-V 2.6、MiniCPM-Llama3-V 2.5 和 MiniCPM-V 2.0 模型。 [参考文档](./finetune/readme.md) @@ -3003,7 +3003,7 @@ pip install vllm 我们支持使用 LLaMA-Factory 微调 MiniCPM-o 2.6 和 MiniCPM-V 2.6。LLaMA-Factory 提供了一种灵活定制 200 多个大型语言模型（LLM）微调（Lora/Full/Qlora）解决方案，无需编写代码，通过内置的 Web 用户界面 LLaMABoard 即可实现训练/推理/评估。它支持多种训练方法，如 sft/ppo/dpo/kto，并且还支持如 Galore/BAdam/LLaMA-Pro/Pissa/LongLoRA 等高级算法。 -最佳实践: [MiniCPM-o 2.6 | MiniCPM-V 2.6](./docs/llamafactory_train_and_infer.md). +最佳实践: [MiniCPM-V 4.0 | MiniCPM-o 2.6 | MiniCPM-V 2.6](./docs/llamafactory_train_and_infer.md). ### 使用 SWIFT 框架 diff --git a/docs/llamafactory_train_and_infer.md b/docs/llamafactory_train_and_infer.md index 9ad34a2..47cba3b 100644 --- a/docs/llamafactory_train_and_infer.md +++ b/docs/llamafactory_train_and_infer.md @@ -13,6 +13,7 @@ - [Inference](#Inference) ## Support Models +* [openbmb/MiniCPM-V-4](https://huggingface.co/openbmb/MiniCPM-V-4) * [openbmb/MiniCPM-o-2_6](https://huggingface.co/openbmb/MiniCPM-o-2_6) * [openbmb/MiniCPM-V-2_6](https://huggingface.co/openbmb/MiniCPM-V-2_6) diff --git a/finetune/readme.md b/finetune/readme.md index 74c1dab..188670f 100644 --- a/finetune/readme.md +++ b/finetune/readme.md @@ -1,7 +1,7 @@ -# MiniCPM-V Finetuning +# MiniCPM-V & o Finetuning -We offer the official scripts for easy finetuning of the pretrained **MiniCPM-o-2_6**, **MiniCPM-V-2_6**, **MiniCPM-Llama3-V 2.5** and **MiniCPM-V 2.0** on downstream tasks. Our finetune scripts use transformers Trainer and DeepSpeed by default. +We offer the official scripts for easy finetuning of the pretrained **MiniCPM-V 4.0**, **MiniCPM-o 2.6**, **MiniCPM-V 2.6**, **MiniCPM-Llama3-V 2.5** and **MiniCPM-V 2.0** on downstream tasks. Our finetune scripts use transformers Trainer and DeepSpeed by default. ### Data preparation @@ -96,11 +96,10 @@ If the total token count exceeds `max_length`, truncation will be applied. For m Full-parameter parameter finetuning requires updating all parameters of LLM in the whole training process. Please specify the correct MODEL path, DATA path and LLM_TYPE in the shell scripts. ```shell -MODEL="MiniCPM-o-2_6" # or "openbmb/MiniCPM-V-2_6", openbmb/MiniCPM-Llama3-V-2_5, openbmb/MiniCPM-V-2 -DATA="path/to/trainging_data" # json file -EVAL_DATA="path/to/test_data" # json file -LLM_TYPE="qwen" # if use openbmb/MiniCPM-V-2, please set LLM_TYPE=minicpm, if use openbmb/MiniCPM-Llama3-V-2_5, please set LLM_TYPE="llama3", -# if use openbmb/MiniCPM-o-2_6 or openbmb/MiniCPM-V-2_6, please set LLM_TYPE=qwen +MODEL="MiniCPM-o-2_6" # or "openbmb/MiniCPM-V-2_6", "openbmb/MiniCPM-Llama3-V-2_5", "openbmb/MiniCPM-V-2" +DATA="path/to/training_data.json" +EVAL_DATA="path/to/test_data.json" +LLM_TYPE="qwen" # llama for MiniCPM-V-4, minicpm for MiniCPM-V-2, llama3 for MiniCPM-Llama3-V-2_5, qwen for MiniCPM-o-2_6/MiniCPM-V-2_6 ``` To launch your training, run the following script: