Release v0.1.7

Former-commit-id: 81abe8d6cabaa1ebe74dc32a5dc143389e4c9f31

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

README.md

@@ -12,21 +12,25 @@
 
 ## Changelog
 
+[23/08/18] Now we support **resuming training**, upgrade `transformers` to `4.31.0` to enjoy this feature.
+
+[23/08/12] Now we support **RoPE scaling** to extend the context length of the LLaMA models. Try `--rope_scaling linear` argument in training and `--rope_scaling dynamic` argument at inference to extrapolate the position embeddings.
+
 [23/08/11] Now we support **[DPO training](https://arxiv.org/abs/2305.18290)** for instruction-tuned models. See [this example](#dpo-training) to train your models (experimental feature).
 
 [23/08/03] Now we support training the **Qwen-7B** model in this repo. Try `--model_name_or_path Qwen/Qwen-7B-Chat` and `--lora_target c_attn` arguments to train the Qwen-7B model. Remember to use `--template chatml` argument when you are using the Qwen-7B-Chat model.
 
-[23/07/31] Now we support dataset streaming. Try `--streaming` and `--max_steps 100` arguments to stream your dataset.
+[23/07/31] Now we support **dataset streaming**. Try `--streaming` and `--max_steps 10000` arguments to load your dataset in streaming mode.
 
 [23/07/29] We release two instruction-tuned 13B models at Hugging Face. See these Hugging Face Repos ([LLaMA-2](https://huggingface.co/hiyouga/Llama-2-Chinese-13b-chat) / [Baichuan](https://huggingface.co/hiyouga/baichuan-13b-sft)) for details.
 
 [23/07/19] Now we support training the **LLaMA-2** models in this repo. Try `--model_name_or_path meta-llama/Llama-2-7b-hf` argument to use the LLaMA-2 model. Remember to use `--template llama2` argument when you are using the LLaMA-2-chat model.
 
-[23/07/18] Now we develop an all-in-one Web UI for training, evaluation and inference. Try `train_web.py` to fine-tune models in your Web browser. Thank [@KanadeSiina](https://github.com/KanadeSiina) and [@codemayq](https://github.com/codemayq) for their efforts in the development.
+[23/07/18] Now we develop an **all-in-one Web UI** for training, evaluation and inference. Try `train_web.py` to fine-tune models in your Web browser. Thank [@KanadeSiina](https://github.com/KanadeSiina) and [@codemayq](https://github.com/codemayq) for their efforts in the development.
 
 [23/07/11] Now we support training the **Baichuan-13B** model in this repo. Try `--model_name_or_path baichuan-inc/Baichuan-13B-Base` and `--lora_target W_pack` arguments to train the Baichuan-13B model. Remember to use `--template baichuan` argument when you are using the Baichuan-13B-Chat model.
 
-[23/07/09] Now we release [FastEdit](https://github.com/hiyouga/FastEdit)⚡🩹, an easy-to-use package for editing the factual knowledge of large language models efficiently. Please follow [FastEdit](https://github.com/hiyouga/FastEdit) if you are interested.
+[23/07/09] Now we release **[FastEdit](https://github.com/hiyouga/FastEdit)** ⚡🩹, an easy-to-use package for editing the factual knowledge of large language models efficiently. Please follow [FastEdit](https://github.com/hiyouga/FastEdit) if you are interested.
 
 [23/07/07] Now we support training the **InternLM-7B** model in this repo. Try `--model_name_or_path internlm/internlm-7b` argument to use the InternLM model. Remember to use `--template intern` argument when you are using the InternLM-chat model.
 
@@ -63,12 +67,14 @@
 ## Supported Training Approaches
 
 | Approach               |   Full-parameter   | Partial-parameter  |       LoRA         |       QLoRA        |
-| ---------------------- | -------------- | ----------------- | ---- | ----- |
-| Pre-Training           | ✅            | ✅                | ✅   | ✅   |
-| Supervised Fine-Tuning | ✅            | ✅                | ✅   | ✅   |
-| Reward Model Training  |                |                   | ✅   | ✅   |
-| PPO Training           |                |                   | ✅   | ✅   |
-| DPO Training           | ✅            |                    | ✅   | ✅   |
+| ---------------------- | ------------------ | ------------------ | ------------------ | ------------------ |
+| Pre-Training           | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+| Supervised Fine-Tuning | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+| Reward Modeling        |                    |                    | :white_check_mark: | :white_check_mark: |
+| PPO Training           |                    |                    | :white_check_mark: | :white_check_mark: |
+| DPO Training           | :white_check_mark: |                    | :white_check_mark: | :white_check_mark: |
+
+- Use `--quantization_bit 4/8` argument to enable QLoRA.
 
 ## Provided Datasets
 
@@ -99,7 +105,7 @@
   - [Web QA (zh)](https://huggingface.co/datasets/suolyer/webqa)
   - [UltraChat (en)](https://github.com/thunlp/UltraChat)
   - [WebNovel (zh)](https://huggingface.co/datasets/zxbsmk/webnovel_cn)
-- For reward modelling or DPO training:
+- For reward modeling or DPO training:
   - [HH-RLHF (en)](https://huggingface.co/datasets/Anthropic/hh-rlhf)
   - [Open Assistant (multilingual)](https://huggingface.co/datasets/OpenAssistant/oasst1)
   - [GPT-4 Generated Data (en&zh)](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM)
@@ -154,18 +160,23 @@ pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/downl
 CUDA_VISIBLE_DEVICES=0 python src/train_web.py
 ```
 
+We strongly recommend using the all-in-one Web UI for newcomers since it can also generate training scripts **automatically**.
+
 Currently the web UI only supports training on **a single GPU**.
 
-### Pre-Training
+### Train on a single GPU
+
+#### Pre-Training
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --stage pt \
-    --model_name_or_path path_to_your_model \
+    --model_name_or_path path_to_llama_model \
     --do_train \
     --dataset wiki_demo \
     --template default \
     --finetuning_type lora \
+    --lora_target q_proj,v_proj \
     --output_dir path_to_pt_checkpoint \
     --overwrite_cache \
     --per_device_train_batch_size 4 \
@@ -179,16 +190,17 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --fp16
 ```
 
-### Supervised Fine-Tuning
+#### Supervised Fine-Tuning
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --stage sft \
-    --model_name_or_path path_to_your_model \
+    --model_name_or_path path_to_llama_model \
     --do_train \
     --dataset alpaca_gpt4_en \
     --template default \
     --finetuning_type lora \
+    --lora_target q_proj,v_proj \
     --output_dir path_to_sft_checkpoint \
     --overwrite_cache \
     --per_device_train_batch_size 4 \
@@ -202,18 +214,17 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --fp16
 ```
 
-Remember to specify `--lora_target W_pack` if you are using Baichuan models.
-
-### Reward Model Training
+#### Reward Modeling
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --stage rm \
-    --model_name_or_path path_to_your_model \
+    --model_name_or_path path_to_llama_model \
     --do_train \
     --dataset comparison_gpt4_en \
     --template default \
     --finetuning_type lora \
+    --lora_target q_proj,v_proj \
     --resume_lora_training False \
     --checkpoint_dir path_to_sft_checkpoint \
     --output_dir path_to_rm_checkpoint \
@@ -222,22 +233,23 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --lr_scheduler_type cosine \
     --logging_steps 10 \
     --save_steps 1000 \
-    --learning_rate 1e-5 \
+    --learning_rate 1e-6 \
     --num_train_epochs 1.0 \
     --plot_loss \
     --fp16
 ```
 
-### PPO Training
+#### PPO Training
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --stage ppo \
-    --model_name_or_path path_to_your_model \
+    --model_name_or_path path_to_llama_model \
     --do_train \
     --dataset alpaca_gpt4_en \
     --template default \
     --finetuning_type lora \
+    --lora_target q_proj,v_proj \
     --resume_lora_training False \
     --checkpoint_dir path_to_sft_checkpoint \
     --reward_model path_to_rm_checkpoint \
@@ -249,19 +261,21 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --save_steps 1000 \
     --learning_rate 1e-5 \
     --num_train_epochs 1.0 \
-    --plot_loss
+    --plot_loss \
+    --fp16
 ```
 
-### DPO Training
+#### DPO Training
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --stage dpo \
-    --model_name_or_path path_to_your_model \
+    --model_name_or_path path_to_llama_model \
     --do_train \
     --dataset comparison_gpt4_en \
     --template default \
     --finetuning_type lora \
+    --lora_target q_proj,v_proj \
     --resume_lora_training False \
     --checkpoint_dir path_to_sft_checkpoint \
     --output_dir path_to_dpo_checkpoint \
@@ -278,12 +292,14 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
 
 ### Distributed Training
 
+#### Use Huggingface Accelerate
+
 ```bash
 accelerate config # configure the environment
 accelerate launch src/train_bash.py # arguments (same as above)
 ```
 
-<details><summary>Example configuration for full-tuning with DeepSpeed ZeRO-2</summary>
+<details><summary>Example config.yaml for training with DeepSpeed ZeRO-2</summary>
 
 ```yaml
 compute_environment: LOCAL_MACHINE
@@ -311,12 +327,93 @@ use_cpu: false
 
 </details>
 
+#### Use DeepSpeed
+
+```bash
+deepspeed --num_gpus 8 --master_port=9901 src/train_bash.py \
+    --deepspeed ds_config.json \
+    ... # arguments (same as above)
+```
+
+<details><summary>Example ds_config.json for training with DeepSpeed ZeRO-2</summary>
+
+```json
+{
+  "train_micro_batch_size_per_gpu": "auto",
+  "gradient_accumulation_steps": "auto",
+  "gradient_clipping": "auto",
+  "zero_allow_untested_optimizer": true,
+  "fp16": {
+    "enabled": "auto",
+    "loss_scale": 0,
+    "initial_scale_power": 16,
+    "loss_scale_window": 1000,
+    "hysteresis": 2,
+    "min_loss_scale": 1
+  },  
+  "zero_optimization": {
+    "stage": 2,
+    "allgather_partitions": true,
+    "allgather_bucket_size": 5e8,
+    "reduce_scatter": true,
+    "reduce_bucket_size": 5e8,
+    "overlap_comm": false,
+    "contiguous_gradients": true
+  }
+}
+```
+
+</details>
+
+### Export model
+
+```bash
+python src/export_model.py \
+    --model_name_or_path path_to_llama_model \
+    --template default \
+    --finetuning_type lora \
+    --checkpoint_dir path_to_checkpoint \
+    --output_dir path_to_export
+```
+
+### API Demo
+
+```bash
+python src/api_demo.py \
+    --model_name_or_path path_to_llama_model \
+    --template default \
+    --finetuning_type lora \
+    --checkpoint_dir path_to_checkpoint
+```
+
+Visit `http://localhost:8000/docs` for API documentation.
+
+### CLI Demo
+
+```bash
+python src/cli_demo.py \
+    --model_name_or_path path_to_llama_model \
+    --template default \
+    --finetuning_type lora \
+    --checkpoint_dir path_to_checkpoint
+```
+
+### Web Demo
+
+```bash
+python src/web_demo.py \
+    --model_name_or_path path_to_llama_model \
+    --template default \
+    --finetuning_type lora \
+    --checkpoint_dir path_to_checkpoint
+```
+
 ### Evaluation (BLEU and ROUGE_CHINESE)
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --stage sft \
-    --model_name_or_path path_to_your_model \
+    --model_name_or_path path_to_llama_model \
     --do_eval \
     --dataset alpaca_gpt4_en \
     --template default \
@@ -335,7 +432,7 @@ We recommend using `--per_device_eval_batch_size=1` and `--max_target_length 128
 ```bash
 CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --stage sft \
-    --model_name_or_path path_to_your_model \
+    --model_name_or_path path_to_llama_model \
     --do_predict \
     --dataset alpaca_gpt4_en \
     --template default \
@@ -347,49 +444,6 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --predict_with_generate
 ```
 
-### API Demo
-
-```bash
-python src/api_demo.py \
-    --model_name_or_path path_to_your_model \
-    --template default \
-    --finetuning_type lora \
-    --checkpoint_dir path_to_checkpoint
-```
-
-Visit `http://localhost:8000/docs` for API documentation.
-
-### CLI Demo
-
-```bash
-python src/cli_demo.py \
-    --model_name_or_path path_to_your_model \
-    --template default \
-    --finetuning_type lora \
-    --checkpoint_dir path_to_checkpoint
-```
-
-### Web Demo
-
-```bash
-python src/web_demo.py \
-    --model_name_or_path path_to_your_model \
-    --template default \
-    --finetuning_type lora \
-    --checkpoint_dir path_to_checkpoint
-```
-
-### Export model
-
-```bash
-python src/export_model.py \
-    --model_name_or_path path_to_your_model \
-    --template default \
-    --finetuning_type lora \
-    --checkpoint_dir path_to_checkpoint \
-    --output_dir path_to_export
-```
-
 ## TODO
 
 - [ ] Supporting flash attention ([torch](https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html) / [xformers](https://github.com/facebookresearch/xformers) / [flashattn](https://github.com/Dao-AILab/flash-attention)).

README_zh.md

@@ -12,33 +12,37 @@
 
 ## 更新日志
 
+[23/08/18] 现在我们支持了**训练状态恢复**，请将 `transformers` 升级至 `4.31.0` 以启用此功能。
+
+[23/08/12] 现在我们支持了 **RoPE 插值**来扩展 LLaMA 模型的上下文长度。请尝试使用 `--rope_scaling linear` 参数训练模型或使用 `--rope_scaling dynamic` 参数评估模型。
+
 [23/08/11] 现在我们支持了指令模型的 **[DPO 训练](https://arxiv.org/abs/2305.18290)**。详情请参阅[此示例](#dpo-训练)（实验性功能）。
 
-[23/08/03] 现在我们支持了 **Qwen-7B** 模型的训练。请尝试使用 `--model_name_or_path Qwen/Qwen-7B-Chat` 和 `--lora_target c_attn` 参数。使用 Qwen-7B-Chat 模型请添加 `--template chatml` 参数。
+[23/08/03] 现在我们支持了 **Qwen-7B** 模型的训练。请尝试使用 `--model_name_or_path Qwen/Qwen-7B-Chat` 和 `--lora_target c_attn` 参数。使用 Qwen-7B-Chat 模型时请添加 `--template chatml` 参数。
 
-[23/07/31] 现在我们支持了训练数据流式加载。请尝试使用 `--streaming` 和 `--max_steps 100` 参数来流式加载数据集。
+[23/07/31] 现在我们支持了**数据流式加载**。请尝试使用 `--streaming` 和 `--max_steps 10000` 参数来流式加载数据集。
 
 [23/07/29] 我们在 Hugging Face 发布了两个 13B 指令微调模型。详细内容请查阅我们的 Hugging Face 项目（[LLaMA-2](https://huggingface.co/hiyouga/Llama-2-Chinese-13b-chat) / [Baichuan](https://huggingface.co/hiyouga/baichuan-13b-sft)）。
 
-[23/07/19] 现在我们支持了 **LLaMA-2** 模型的训练。请尝试使用 `--model_name_or_path meta-llama/Llama-2-7b-hf` 参数。请注意使用 LLaMA-2-chat 模型需要添加 `--template llama2` 参数。
+[23/07/19] 现在我们支持了 **LLaMA-2** 模型的训练。请尝试使用 `--model_name_or_path meta-llama/Llama-2-7b-hf` 参数。使用 LLaMA-2-chat 模型时请添加 `--template llama2` 参数。
 
-[23/07/18] 我们开发了支持训练和测试的浏览器一键微调界面。请尝试使用 `train_web.py` 在您的浏览器中微调模型。感谢 [@KanadeSiina](https://github.com/KanadeSiina) 和 [@codemayq](https://github.com/codemayq) 在该功能开发中付出的努力。
+[23/07/18] 我们开发了支持训练和测试的**浏览器一体化界面**。请尝试使用 `train_web.py` 在您的浏览器中微调模型。感谢 [@KanadeSiina](https://github.com/KanadeSiina) 和 [@codemayq](https://github.com/codemayq) 在该功能开发中付出的努力。
 
-[23/07/11] 现在我们支持了 **Baichuan-13B** 模型的训练。请尝试使用 `--model_name_or_path baichuan-inc/Baichuan-13B-Base` 和 `--lora_target W_pack` 参数。请注意使用 Baichuan-13B-Chat 模型需要添加 `--template baichuan` 参数。
+[23/07/11] 现在我们支持了 **Baichuan-13B** 模型的训练。请尝试使用 `--model_name_or_path baichuan-inc/Baichuan-13B-Base` 和 `--lora_target W_pack` 参数。使用 Baichuan-13B-Chat 模型时请添加 `--template baichuan` 参数。
 
-[23/07/09] 我们开源了 [FastEdit](https://github.com/hiyouga/FastEdit)⚡🩹，一个简单易用的、能迅速编辑大模型事实记忆的工具包。如果您感兴趣请关注我们的 [FastEdit](https://github.com/hiyouga/FastEdit) 项目。
+[23/07/09] 我们开源了 **[FastEdit](https://github.com/hiyouga/FastEdit)** ⚡🩹，一个简单易用的、能迅速编辑大模型事实记忆的工具包。如果您感兴趣请关注我们的 [FastEdit](https://github.com/hiyouga/FastEdit) 项目。
 
-[23/07/07] 现在我们支持了 **InternLM-7B** 模型的训练。请尝试使用 `--model_name_or_path internlm/internlm-7b` 参数。请注意使用 InternLM-chat 模型需要添加 `--template intern` 参数。
+[23/07/07] 现在我们支持了 **InternLM-7B** 模型的训练。请尝试使用 `--model_name_or_path internlm/internlm-7b` 参数。使用 InternLM-chat 模型时请添加 `--template intern` 参数。
 
 [23/07/05] 现在我们支持了 **Falcon-7B/40B** 模型的训练。请尝试使用 `--model_name_or_path tiiuae/falcon-7b` 和 `--lora_target query_key_value` 参数。
 
 [23/06/29] 我们提供了一个**可复现的**指令模型微调示例，详细内容请查阅 [Hugging Face 项目](https://huggingface.co/hiyouga/baichuan-7b-sft)。
 
-[23/06/22] 我们对齐了[示例 API](src/api_demo.py) 与 [OpenAI API](https://platform.openai.com/docs/api-reference/chat) 的格式，您可以将微调模型接入任意基于 ChatGPT 的应用中。
+[23/06/22] 我们对齐了[示例 API](src/api_demo.py) 与 [OpenAI API](https://platform.openai.com/docs/api-reference/chat) 的格式，您可以将微调模型接入**任意基于 ChatGPT 的应用**中。
 
 [23/06/15] 现在我们支持了 **Baichuan-7B** 模型的训练。请尝试使用 `--model_name_or_path baichuan-inc/Baichuan-7B` 和 `--lora_target W_pack` 参数。
 
-[23/06/03] 现在我们实现了 4 比特的 LoRA 训练（也称 [QLoRA](https://github.com/artidoro/qlora)）。请尝试使用 `--quantization_bit 4` 参数进行 4 比特量化微调。
+[23/06/03] 现在我们实现了 4 比特的 LoRA 训练（也称 **[QLoRA](https://github.com/artidoro/qlora)**）。请尝试使用 `--quantization_bit 4` 参数进行 4 比特量化微调。
 
 [23/05/31] 现在我们支持了 **BLOOM & BLOOMZ** 模型的训练。请尝试使用 `--model_name_or_path bigscience/bloomz-7b1-mt` 和 `--lora_target query_key_value` 参数。
 
@@ -55,6 +59,7 @@
 | [InternLM](https://github.com/InternLM/InternLM)         | 7B                          | q_proj,v_proj     | intern   |
 | [Qwen](https://github.com/QwenLM/Qwen-7B)                | 7B                          | c_attn            | chatml   |
 | [XVERSE](https://github.com/xverse-ai/XVERSE-13B)        | 13B                         | q_proj,v_proj     | -        |
+| [ChatGLM2](https://github.com/THUDM/ChatGLM2-6B)         | 6B                          | query_key_value   | chatglm2 |
 
 - **默认模块**是 `--lora_target` 参数的部分可选项。请使用 `python src/train_bash.py -h` 查看全部可选项。
 - 对于所有“基座”（Base）模型，`--template` 参数可以是 `default`, `alpaca`, `vicuna` 等任意值。但“对话”（Chat）模型请务必使用对应的模板。
@@ -62,12 +67,14 @@
 ## 训练方法
 
 | 方法                   |     全参数训练      |    部分参数训练     |       LoRA         |       QLoRA        |
-| ---------- | ---------- | ----------- | ---- | ----- |
-| 预训练      | ✅        | ✅         | ✅   | ✅   |
-| 指令监督微调 | ✅        | ✅         | ✅   | ✅   |
-| 奖励模型训练 |           |             | ✅   | ✅   |
-| PPO 训练    |           |             | ✅   | ✅   |
-| DPO 训练    | ✅        |             | ✅   | ✅   |
+| ---------------------- | ------------------ | ------------------ | ------------------ | ------------------ |
+| 预训练                 | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+| 指令监督微调            | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+| 奖励模型训练            |                    |                    | :white_check_mark: | :white_check_mark: |
+| PPO 训练               |                    |                    | :white_check_mark: | :white_check_mark: |
+| DPO 训练               | :white_check_mark: |                    | :white_check_mark: | :white_check_mark: |
+
+- 使用 `--quantization_bit 4/8` 参数来启用 QLoRA 训练。
 
 ## 数据集
 
@@ -147,24 +154,29 @@ pip install -r requirements.txt
 pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.39.1-py3-none-win_amd64.whl
 ```
 
-### 浏览器一键微调/测试
+### 浏览器一体化界面
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 python src/train_web.py
 ```
 
+我们极力推荐新手使用浏览器一体化界面，因为它还可以**自动**生成运行所需的命令行脚本。
+
 目前网页 UI 仅支持**单卡训练**。
 
-### 预训练
+### 单 GPU 训练
+
+#### 预训练
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --stage pt \
-    --model_name_or_path path_to_your_model \
+    --model_name_or_path path_to_llama_model \
     --do_train \
     --dataset wiki_demo \
     --template default \
     --finetuning_type lora \
+    --lora_target q_proj,v_proj \
     --output_dir path_to_pt_checkpoint \
     --overwrite_cache \
     --per_device_train_batch_size 4 \
@@ -178,16 +190,17 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --fp16
 ```
 
-### 指令监督微调
+#### 指令监督微调
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --stage sft \
-    --model_name_or_path path_to_your_model \
+    --model_name_or_path path_to_llama_model \
     --do_train \
     --dataset alpaca_gpt4_zh \
     --template default \
     --finetuning_type lora \
+    --lora_target q_proj,v_proj \
     --output_dir path_to_sft_checkpoint \
     --overwrite_cache \
     --per_device_train_batch_size 4 \
@@ -201,18 +214,17 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --fp16
 ```
 
-使用 Baichuan 模型时请指定 `--lora_target W_pack` 参数。
-
-### 奖励模型训练
+#### 奖励模型训练
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --stage rm \
-    --model_name_or_path path_to_your_model \
+    --model_name_or_path path_to_llama_model \
     --do_train \
     --dataset comparison_gpt4_zh \
     --template default \
     --finetuning_type lora \
+    --lora_target q_proj,v_proj \
     --resume_lora_training False \
     --checkpoint_dir path_to_sft_checkpoint \
     --output_dir path_to_rm_checkpoint \
@@ -221,22 +233,23 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --lr_scheduler_type cosine \
     --logging_steps 10 \
     --save_steps 1000 \
-    --learning_rate 1e-5 \
+    --learning_rate 1e-6 \
     --num_train_epochs 1.0 \
     --plot_loss \
     --fp16
 ```
 
-### PPO 训练
+#### PPO 训练
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --stage ppo \
-    --model_name_or_path path_to_your_model \
+    --model_name_or_path path_to_llama_model \
     --do_train \
     --dataset alpaca_gpt4_zh \
     --template default \
     --finetuning_type lora \
+    --lora_target q_proj,v_proj \
     --resume_lora_training False \
     --checkpoint_dir path_to_sft_checkpoint \
     --reward_model path_to_rm_checkpoint \
@@ -251,16 +264,17 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --plot_loss
 ```
 
-### DPO 训练
+#### DPO 训练
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
     --stage dpo \
-    --model_name_or_path path_to_your_model \
+    --model_name_or_path path_to_llama_model \
     --do_train \
     --dataset comparison_gpt4_zh \
     --template default \
     --finetuning_type lora \
+    --lora_target q_proj,v_proj \
     --resume_lora_training False \
     --checkpoint_dir path_to_sft_checkpoint \
     --output_dir path_to_dpo_checkpoint \
@@ -277,6 +291,8 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
 
 ### 多 GPU 分布式训练
 
+#### 使用 Huggingface Accelerate
+
 ```bash
 accelerate config # 首先配置分布式环境
 accelerate launch src/train_bash.py # 参数同上
@@ -310,47 +326,60 @@ use_cpu: false
 
 </details>
 
-### 指标评估（BLEU分数和汉语ROUGE分数）
+#### 使用 DeepSpeed
 
 ```bash
-CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
-    --stage sft \
-    --model_name_or_path path_to_your_model \
-    --do_eval \
-    --dataset alpaca_gpt4_zh \
-    --template default \
-    --finetuning_type lora \
-    --checkpoint_dir path_to_checkpoint \
-    --output_dir path_to_eval_result \
-    --per_device_eval_batch_size 8 \
-    --max_samples 100 \
-    --predict_with_generate
+deepspeed --num_gpus 8 --master_port=9901 src/train_bash.py \
+    --deepspeed ds_config.json \
+    ... # 参数同上
 ```
 
-我们建议在量化模型的评估中使用 `--per_device_eval_batch_size=1` 和 `--max_target_length 128` 参数。
+<details><summary>使用 DeepSpeed ZeRO-2 进行全参数微调的 DeepSpeed 配置示例</summary>
 
-### 模型预测
+```json
+{
+  "train_micro_batch_size_per_gpu": "auto",
+  "gradient_accumulation_steps": "auto",
+  "gradient_clipping": "auto",
+  "zero_allow_untested_optimizer": true,
+  "fp16": {
+    "enabled": "auto",
+    "loss_scale": 0,
+    "initial_scale_power": 16,
+    "loss_scale_window": 1000,
+    "hysteresis": 2,
+    "min_loss_scale": 1
+  },  
+  "zero_optimization": {
+    "stage": 2,
+    "allgather_partitions": true,
+    "allgather_bucket_size": 5e8,
+    "reduce_scatter": true,
+    "reduce_bucket_size": 5e8,
+    "overlap_comm": false,
+    "contiguous_gradients": true
+  }
+}
+```
+
+</details>
+
+### 导出微调后的模型
 
 ```bash
-CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
-    --stage sft \
-    --model_name_or_path path_to_your_model \
-    --do_predict \
-    --dataset alpaca_gpt4_zh \
+python src/export_model.py \
+    --model_name_or_path path_to_llama_model \
     --template default \
     --finetuning_type lora \
     --checkpoint_dir path_to_checkpoint \
-    --output_dir path_to_predict_result \
-    --per_device_eval_batch_size 8 \
-    --max_samples 100 \
-    --predict_with_generate
+    --output_dir path_to_export
 ```
 
 ### API 服务
 
 ```bash
 python src/api_demo.py \
-    --model_name_or_path path_to_your_model \
+    --model_name_or_path path_to_llama_model \
     --template default \
     --finetuning_type lora \
     --checkpoint_dir path_to_checkpoint
@@ -362,7 +391,7 @@ python src/api_demo.py \
 
 ```bash
 python src/cli_demo.py \
-    --model_name_or_path path_to_your_model \
+    --model_name_or_path path_to_llama_model \
     --template default \
     --finetuning_type lora \
     --checkpoint_dir path_to_checkpoint
@@ -372,21 +401,46 @@ python src/cli_demo.py \
 
 ```bash
 python src/web_demo.py \
-    --model_name_or_path path_to_your_model \
+    --model_name_or_path path_to_llama_model \
     --template default \
     --finetuning_type lora \
     --checkpoint_dir path_to_checkpoint
 ```
 
-### 导出微调模型
+### 指标评估（BLEU 分数和汉语 ROUGE 分数）
 
 ```bash
-python src/export_model.py \
-    --model_name_or_path path_to_your_model \
+CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
+    --stage sft \
+    --model_name_or_path path_to_llama_model \
+    --do_eval \
+    --dataset alpaca_gpt4_zh \
     --template default \
     --finetuning_type lora \
     --checkpoint_dir path_to_checkpoint \
-    --output_dir path_to_export
+    --output_dir path_to_eval_result \
+    --per_device_eval_batch_size 8 \
+    --max_samples 100 \
+    --predict_with_generate
+```
+
+我们建议在量化模型的评估中使用 `--per_device_eval_batch_size=1` 和 `--max_target_length 128`。
+
+### 模型预测
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
+    --stage sft \
+    --model_name_or_path path_to_llama_model \
+    --do_predict \
+    --dataset alpaca_gpt4_zh \
+    --template default \
+    --finetuning_type lora \
+    --checkpoint_dir path_to_checkpoint \
+    --output_dir path_to_predict_result \
+    --per_device_eval_batch_size 8 \
+    --max_samples 100 \
+    --predict_with_generate
 ```
 
 ## TODO
@@ -408,6 +462,8 @@ python src/export_model.py \
 - [Baichuan](https://huggingface.co/baichuan-inc/baichuan-7B/resolve/main/baichuan-7B%20%E6%A8%A1%E5%9E%8B%E8%AE%B8%E5%8F%AF%E5%8D%8F%E8%AE%AE.pdf)
 - [InternLM](https://github.com/InternLM/InternLM#open-source-license)
 - [Qwen](https://huggingface.co/Qwen/Qwen-7B-Chat/blob/main/LICENSE)
+- [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf)
+- [ChatGLM2](https://github.com/THUDM/ChatGLM2-6B/blob/main/MODEL_LICENSE)
 
 ## 引用
 

src/llmtuner/__init__.py

@@ -6,4 +6,4 @@ from llmtuner.tuner import export_model, run_exp
 from llmtuner.webui import create_ui, create_web_demo
 
 
-__version__ = "0.1.6"
+__version__ = "0.1.7"

src/llmtuner/api/app.py

@@ -47,15 +47,15 @@ def create_app(chat_model: ChatModel) -> FastAPI:
 
     @app.post("/v1/chat/completions", response_model=ChatCompletionResponse)
     async def create_chat_completion(request: ChatCompletionRequest):
-        if request.messages[-1].role != Role.USER:
+        if len(request.messages) < 1 or request.messages[-1].role != Role.USER:
             raise HTTPException(status_code=400, detail="Invalid request")
 
         query = request.messages[-1].content
         prev_messages = request.messages[:-1]
         if len(prev_messages) > 0 and prev_messages[0].role == Role.SYSTEM:
-            prefix = prev_messages.pop(0).content
+            system = prev_messages.pop(0).content
         else:
-            prefix = None
+            system = None
 
         history = []
         if len(prev_messages) % 2 == 0:
@@ -64,11 +64,11 @@ def create_app(chat_model: ChatModel) -> FastAPI:
                     history.append([prev_messages[i].content, prev_messages[i+1].content])
 
         if request.stream:
-            generate = predict(query, history, prefix, request)
+            generate = predict(query, history, system, request)
             return EventSourceResponse(generate, media_type="text/event-stream")
 
         response, (prompt_length, response_length) = chat_model.chat(
-            query, history, prefix, temperature=request.temperature, top_p=request.top_p, max_new_tokens=request.max_tokens
+            query, history, system, temperature=request.temperature, top_p=request.top_p, max_new_tokens=request.max_tokens
         )
 
         usage = ChatCompletionResponseUsage(
@@ -85,7 +85,7 @@ def create_app(chat_model: ChatModel) -> FastAPI:
 
         return ChatCompletionResponse(model=request.model, choices=[choice_data], usage=usage)
 
-    async def predict(query: str, history: List[Tuple[str, str]], prefix: str, request: ChatCompletionRequest):
+    async def predict(query: str, history: List[Tuple[str, str]], system: str, request: ChatCompletionRequest):
         choice_data = ChatCompletionResponseStreamChoice(
             index=0,
             delta=DeltaMessage(role=Role.ASSISTANT),
@@ -95,7 +95,7 @@ def create_app(chat_model: ChatModel) -> FastAPI:
         yield chunk.json(exclude_unset=True, ensure_ascii=False)
 
         for new_text in chat_model.stream_chat(
-            query, history, prefix, temperature=request.temperature, top_p=request.top_p, max_new_tokens=request.max_tokens
+            query, history, system, temperature=request.temperature, top_p=request.top_p, max_new_tokens=request.max_tokens
         ):
             if len(new_text) == 0:
                 continue

src/llmtuner/chat/stream_chat.py

@@ -1,10 +1,9 @@
 import torch
-from types import MethodType
 from typing import Any, Dict, Generator, List, Optional, Tuple
 from threading import Thread
-from transformers import PreTrainedModel, TextIteratorStreamer
+from transformers import TextIteratorStreamer
 
-from llmtuner.extras.misc import dispatch_model, get_logits_processor, get_stopping_criteria
+from llmtuner.extras.misc import dispatch_model, get_logits_processor
 from llmtuner.extras.template import get_template_and_fix_tokenizer
 from llmtuner.tuner.core import get_infer_args, load_model_and_tokenizer
 
@@ -15,22 +14,21 @@ class ChatModel:
         model_args, data_args, finetuning_args, self.generating_args = get_infer_args(args)
         self.model, self.tokenizer = load_model_and_tokenizer(model_args, finetuning_args)
         self.model = dispatch_model(self.model)
-        self.model = self.model.eval() # change to eval mode
+        self.model = self.model.eval() # enable evaluation mode
         self.template = get_template_and_fix_tokenizer(data_args.template, self.tokenizer)
-        self.source_prefix = data_args.source_prefix
-        self.model.generate = MethodType(PreTrainedModel.generate, self.model) # disable custom method (for Qwen)
+        self.system_prompt = data_args.system_prompt
 
     def process_args(
         self,
         query: str,
         history: Optional[List[Tuple[str, str]]] = None,
-        prefix: Optional[str] = None,
+        system: Optional[str] = None,
         **input_kwargs
     ) -> Tuple[Dict[str, Any], int]:
-        prefix = prefix or self.source_prefix
+        system = system or self.system_prompt
 
         prompt, _ = self.template.encode_oneturn(
-            tokenizer=self.tokenizer, query=query, resp="", history=history, prefix=prefix
+            tokenizer=self.tokenizer, query=query, resp="", history=history, system=system
         )
         input_ids = torch.tensor([prompt], device=self.model.device)
         prompt_length = len(input_ids[0])
@@ -51,8 +49,9 @@ class ChatModel:
             top_p=top_p or gen_kwargs["top_p"],
             top_k=top_k or gen_kwargs["top_k"],
             repetition_penalty=repetition_penalty or gen_kwargs["repetition_penalty"],
-            logits_processor=get_logits_processor(),
-            stopping_criteria=get_stopping_criteria(self.tokenizer.additional_special_tokens_ids)
+            eos_token_id=list(set([self.tokenizer.eos_token_id] + self.tokenizer.additional_special_tokens_ids)),
+            pad_token_id=self.tokenizer.pad_token_id,
+            logits_processor=get_logits_processor()
         ))
 
         if max_length:
@@ -70,10 +69,10 @@ class ChatModel:
         self,
         query: str,
         history: Optional[List[Tuple[str, str]]] = None,
-        prefix: Optional[str] = None,
+        system: Optional[str] = None,
         **input_kwargs
     ) -> Tuple[str, Tuple[int, int]]:
-        gen_kwargs, prompt_length = self.process_args(query, history, prefix, **input_kwargs)
+        gen_kwargs, prompt_length = self.process_args(query, history, system, **input_kwargs)
         generation_output = self.model.generate(**gen_kwargs)
         outputs = generation_output.tolist()[0][prompt_length:]
         response = self.tokenizer.decode(outputs, skip_special_tokens=True)
@@ -85,10 +84,10 @@ class ChatModel:
         self,
         query: str,
         history: Optional[List[Tuple[str, str]]] = None,
-        prefix: Optional[str] = None,
+        system: Optional[str] = None,
         **input_kwargs
     ) -> Generator[str, None, None]:
-        gen_kwargs, _ = self.process_args(query, history, prefix, **input_kwargs)
+        gen_kwargs, _ = self.process_args(query, history, system, **input_kwargs)
         streamer = TextIteratorStreamer(self.tokenizer, timeout=60.0, skip_prompt=True, skip_special_tokens=True)
         gen_kwargs["streamer"] = streamer
 

src/llmtuner/dsets/loader.py

@@ -1,48 +1,25 @@
 import os
-import hashlib
-from typing import TYPE_CHECKING, List, Optional
+from typing import TYPE_CHECKING, List, Union
 
-from datasets import Value, concatenate_datasets, interleave_datasets, load_dataset
+from datasets import concatenate_datasets, interleave_datasets, load_dataset
 
+from llmtuner.dsets.utils import checksum, EXT2TYPE
 from llmtuner.extras.logging import get_logger
 
 if TYPE_CHECKING:
-    from datasets import Dataset
+    from datasets import Dataset, IterableDataset
     from llmtuner.hparams import ModelArguments, DataArguments
 
 
 logger = get_logger(__name__)
 
 
-EXT2TYPE = {
-    "csv": "csv",
-    "json": "json",
-    "jsonl": "json",
-    "txt": "text"
-}
-
-
-def checksum(data_files: List[str], file_sha1: Optional[str] = None) -> None:
-    if file_sha1 is None:
-        logger.warning("Checksum failed: missing SHA-1 hash value in dataset_info.json.")
-        return
-
-    if len(data_files) != 1:
-        logger.warning("Checksum failed: too many files.")
-        return
-
-    with open(data_files[0], "rb") as f:
-        sha1 = hashlib.sha1(f.read()).hexdigest()
-        if sha1 != file_sha1:
-            logger.warning("Checksum failed: mismatched SHA-1 hash value at {}.".format(data_files[0]))
-
-
 def get_dataset(
     model_args: "ModelArguments",
     data_args: "DataArguments"
-) -> "Dataset":
+) -> Union["Dataset", "IterableDataset"]:
     max_samples = data_args.max_samples
-    all_datasets: List["Dataset"] = [] # support multiple datasets
+    all_datasets: List[Union["Dataset", "IterableDataset"]] = [] # support multiple datasets
 
     for dataset_attr in data_args.dataset_list:
         logger.info("Loading dataset {}...".format(dataset_attr))
@@ -92,14 +69,11 @@ def get_dataset(
             if getattr(dataset_attr, column_name) and getattr(dataset_attr, column_name) != column_name:
                 dataset = dataset.rename_column(getattr(dataset_attr, column_name), column_name)
 
-        if dataset_attr.source_prefix: # add prefix
+        if dataset_attr.system_prompt: # add system prompt
             if data_args.streaming:
-                features = dataset.features
-                features["prefix"] = Value(dtype="string", id=None)
-                dataset = dataset.map(lambda _: {"prefix": dataset_attr.source_prefix}, features=features)
+                dataset = dataset.map(lambda _: {"system": dataset_attr.system_prompt})
             else:
-                prefix_data = [dataset_attr.source_prefix] * len(dataset)
-                dataset = dataset.add_column("prefix", prefix_data)
+                dataset = dataset.add_column("system", [dataset_attr.system_prompt] * len(dataset))
 
         all_datasets.append(dataset)
 

src/llmtuner/dsets/preprocess.py

@@ -1,25 +1,25 @@
 import tiktoken
-from typing import TYPE_CHECKING, Any, Dict, Generator, List, Literal
+from typing import TYPE_CHECKING, Any, Dict, Generator, List, Literal, Union
 from itertools import chain
 
 from llmtuner.extras.constants import IGNORE_INDEX
 from llmtuner.extras.template import get_template_and_fix_tokenizer
 
 if TYPE_CHECKING:
-    from datasets import Dataset
+    from datasets import Dataset, IterableDataset
     from transformers import Seq2SeqTrainingArguments
     from transformers.tokenization_utils import PreTrainedTokenizer
     from llmtuner.hparams import DataArguments
 
 
 def preprocess_dataset(
-    dataset: "Dataset",
+    dataset: Union["Dataset", "IterableDataset"],
     tokenizer: "PreTrainedTokenizer",
     data_args: "DataArguments",
     training_args: "Seq2SeqTrainingArguments",
     stage: Literal["pt", "sft", "rm", "ppo"]
-) -> "Dataset":
-    column_names = list(dataset.column_names)
+) -> Union["Dataset", "IterableDataset"]:
+    column_names = list(next(iter(dataset)).keys())
     template = get_template_and_fix_tokenizer(data_args.template, tokenizer)
 
     def construct_example(examples: Dict[str, List[Any]]) -> Generator[Any, None, None]:
@@ -27,8 +27,8 @@ def preprocess_dataset(
             query, response = examples["prompt"][i], examples["response"][i]
             query = query + "\n" + examples["query"][i] if "query" in examples and examples["query"][i] else query
             history = examples["history"][i] if "history" in examples else None
-            prefix = examples["prefix"][i] if "prefix" in examples else None
-            yield query, response, history, prefix
+            system = examples["system"][i] if "system" in examples else None
+            yield query, response, history, system
 
     def preprocess_pretrain_dataset(examples: Dict[str, List[Any]]) -> Dict[str, Any]:
         # build grouped texts with format `X1 X2 X3 ...` (without <eos>)
@@ -56,10 +56,10 @@ def preprocess_dataset(
         model_inputs = {"input_ids": [], "attention_mask": [], "labels": []}
         max_length = data_args.max_source_length + data_args.max_target_length
 
-        for query, response, history, prefix in construct_example(examples):
+        for query, response, history, system in construct_example(examples):
             input_ids, labels = [], []
 
-            for source_ids, target_ids in template.encode_multiturn(tokenizer, query, response, history, prefix):
+            for source_ids, target_ids in template.encode_multiturn(tokenizer, query, response, history, system):
                 if len(source_ids) > data_args.max_source_length:
                     source_ids = source_ids[:data_args.max_source_length]
                 if len(target_ids) > data_args.max_target_length:
@@ -78,11 +78,11 @@ def preprocess_dataset(
         return model_inputs
 
     def preprocess_unsupervised_dataset(examples: Dict[str, List[Any]]) -> Dict[str, Any]:
-        # build inputs with format `<bos> X` and labels with format `<bos> Y`
+        # build inputs with format `<bos> X` and labels with format `Y <eos>`
         model_inputs = {"input_ids": [], "attention_mask": [], "labels": []}
 
-        for query, response, history, prefix in construct_example(examples):
-            source_ids, target_ids = template.encode_oneturn(tokenizer, query, response, history, prefix)
+        for query, response, history, system in construct_example(examples):
+            source_ids, target_ids = template.encode_oneturn(tokenizer, query, response, history, system)
 
             if len(source_ids) > data_args.max_source_length:
                 source_ids = source_ids[:data_args.max_source_length]
@@ -98,9 +98,9 @@ def preprocess_dataset(
     def preprocess_pairwise_dataset(examples):
         # build input pairs with format `<bos> X`, `Y1 <eos>` and `Y2 <eos>`
         model_inputs = {"prompt_ids": [], "chosen_ids": [], "rejected_ids": []}
-        for query, response, history, prefix in construct_example(examples):
-            prompt_ids, chosen_ids = template.encode_oneturn(tokenizer, query, response[0], history, prefix)
-            _, rejected_ids = template.encode_oneturn(tokenizer, query, response[1], history, prefix)
+        for query, response, history, system in construct_example(examples):
+            prompt_ids, chosen_ids = template.encode_oneturn(tokenizer, query, response[0], history, system)
+            _, rejected_ids = template.encode_oneturn(tokenizer, query, response[1], history, system)
 
             if len(prompt_ids) > data_args.max_source_length:
                 prompt_ids = prompt_ids[:data_args.max_source_length]

src/llmtuner/dsets/utils.py

@@ -1,4 +1,7 @@
-from typing import TYPE_CHECKING, Dict, Union
+import hashlib
+from typing import TYPE_CHECKING, Dict, List, Optional, Union
+
+from llmtuner.extras.logging import get_logger
 
 if TYPE_CHECKING:
     from datasets import Dataset, IterableDataset
@@ -6,6 +9,32 @@ if TYPE_CHECKING:
     from llmtuner.hparams import DataArguments
 
 
+logger = get_logger(__name__)
+
+
+EXT2TYPE = {
+    "csv": "csv",
+    "json": "json",
+    "jsonl": "json",
+    "txt": "text"
+}
+
+
+def checksum(data_files: List[str], file_sha1: Optional[str] = None) -> None:
+    if file_sha1 is None:
+        logger.warning("Checksum failed: missing SHA-1 hash value in dataset_info.json.")
+        return
+
+    if len(data_files) != 1:
+        logger.warning("Checksum failed: too many files.")
+        return
+
+    with open(data_files[0], "rb") as f:
+        sha1 = hashlib.sha1(f.read()).hexdigest()
+        if sha1 != file_sha1:
+            logger.warning("Checksum failed: mismatched SHA-1 hash value at {}.".format(data_files[0]))
+
+
 def split_dataset(
     dataset: Union["Dataset", "IterableDataset"],
     data_args: "DataArguments",

src/llmtuner/extras/constants.py

@@ -10,6 +10,14 @@ LAYERNORM_NAMES = ["norm", "ln_f", "ln_attn", "ln_mlp"]
 
 METHODS = ["full", "freeze", "lora"]
 
+STAGES = [
+    "SFT",
+    "Reward Modeling",
+    "PPO",
+    "DPO",
+    "Pre-Training"
+]
+
 SUPPORTED_MODELS = {
     "LLaMA-7B": "huggyllama/llama-7b",
     "LLaMA-13B": "huggyllama/llama-13b",
@@ -21,6 +29,10 @@ SUPPORTED_MODELS = {
     "LLaMA2-7B-Chat": "meta-llama/Llama-2-7b-chat-hf",
     "LLaMA2-13B-Chat": "meta-llama/Llama-2-13b-chat-hf",
     "LLaMA2-70B-Chat": "meta-llama/Llama-2-70b-chat-hf",
+    "ChineseLLaMA2-7B": "ziqingyang/chinese-llama-2-7b",
+    "ChineseLLaMA2-13B": "ziqingyang/chinese-llama-2-13b",
+    "ChineseLLaMA2-7B-Chat": "ziqingyang/chinese-alpaca-2-7b",
+    "ChineseLLaMA2-13B-Chat": "ziqingyang/chinese-alpaca-2-13b",
     "BLOOM-560M": "bigscience/bloom-560m",
     "BLOOM-3B": "bigscience/bloom-3b",
     "BLOOM-7B1": "bigscience/bloom-7b1",
@@ -39,12 +51,13 @@ SUPPORTED_MODELS = {
     "Qwen-7B": "Qwen/Qwen-7B",
     "Qwen-7B-Chat": "Qwen/Qwen-7B-Chat",
     "XVERSE-13B": "xverse/XVERSE-13B",
-    "ChatGLM2-6B": "THUDM/chatglm2-6b"
+    "ChatGLM2-6B-Chat": "THUDM/chatglm2-6b"
 }
 
 DEFAULT_MODULE = {
     "LLaMA": "q_proj,v_proj",
     "LLaMA2": "q_proj,v_proj",
+    "ChineseLLaMA2": "q_proj,v_proj",
     "BLOOM": "query_key_value",
     "BLOOMZ": "query_key_value",
     "Falcon": "query_key_value",
@@ -54,3 +67,12 @@ DEFAULT_MODULE = {
     "XVERSE": "q_proj,v_proj",
     "ChatGLM2": "query_key_value"
 }
+
+DEFAULT_TEMPLATE = {
+    "LLaMA2": "llama2",
+    "ChineseLLaMA2": "llama2_zh",
+    "Baichuan": "baichuan",
+    "InternLM": "intern",
+    "Qwen": "chatml",
+    "ChatGLM2": "chatglm2"
+}

src/llmtuner/extras/logging.py

@@ -8,6 +8,9 @@ class LoggerHandler(logging.Handler):
         super().__init__()
         self.log = ""
 
+    def reset(self):
+        self.log = ""
+
     def emit(self, record):
         if record.name == "httpx":
             return

src/llmtuner/extras/misc.py

@@ -1,11 +1,6 @@
 import torch
 from typing import TYPE_CHECKING, List, Optional, Tuple
-from transformers import (
-    LogitsProcessor,
-    LogitsProcessorList,
-    StoppingCriteria,
-    StoppingCriteriaList
-)
+from transformers import InfNanRemoveLogitsProcessor, LogitsProcessorList
 
 from llmtuner.extras.constants import LAYERNORM_NAMES
 
@@ -33,37 +28,12 @@ class AverageMeter:
         self.avg = self.sum / self.count
 
 
-class InvalidScoreLogitsProcessor(LogitsProcessor):
-
-    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor) -> torch.FloatTensor:
-        if torch.isnan(scores).any() or torch.isinf(scores).any():
-            scores.zero_()
-            scores[..., 0] = 1.0
-        return scores
-
-
 def get_logits_processor() -> LogitsProcessorList:
     logits_processor = LogitsProcessorList()
-    logits_processor.append(InvalidScoreLogitsProcessor())
+    logits_processor.append(InfNanRemoveLogitsProcessor())
     return logits_processor
 
 
-class StopWordsCriteria(StoppingCriteria):
-
-    def __init__(self, stop_ids: List[int]) -> None:
-        super().__init__()
-        self.stop_ids = stop_ids
-
-    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
-        return any([stop_id in input_ids[:, -1] for stop_id in self.stop_ids])
-
-
-def get_stopping_criteria(stop_ids: List[int]) -> StoppingCriteriaList:
-    stopping_criteria = StoppingCriteriaList()
-    stopping_criteria.append(StopWordsCriteria(stop_ids))
-    return stopping_criteria
-
-
 def count_parameters(model: torch.nn.Module) -> Tuple[int, int]:
     r"""
     Returns the number of trainable parameters and number of all parameters in the model.
@@ -95,7 +65,6 @@ def prepare_model_for_training(
     use_gradient_checkpointing: Optional[bool] = True,
     layer_norm_names: Optional[List[str]] = LAYERNORM_NAMES
 ) -> "PreTrainedModel":
-
     for name, param in model.named_parameters():
         if param.ndim == 1 and any(layer_norm_name in name for layer_norm_name in layer_norm_names):
             param.data = param.data.to(torch.float32)
@@ -112,9 +81,6 @@ def prepare_model_for_training(
         model.config.use_cache = False # turn off when gradient checkpointing is enabled
 
     if finetuning_type != "full" and hasattr(model, output_layer_name):
-        if hasattr(model, "config") and hasattr(model.config, "pretraining_tp"):
-            model.config.pretraining_tp = 1 # disable TP for LoRA (https://github.com/huggingface/peft/pull/728)
-
         output_layer: torch.nn.Linear = getattr(model, output_layer_name)
         input_dtype = output_layer.weight.dtype
 
@@ -142,6 +108,9 @@ def dispatch_model(model: "PreTrainedModel") -> "PreTrainedModel":
     Dispatches a pre-trained model to GPUs with balanced memory.
     Borrowed from: https://github.com/huggingface/transformers/blob/v4.31.0/src/transformers/modeling_utils.py#L2803
     """
+    if getattr(model, "is_loaded_in_8bit", False) or getattr(model, "is_loaded_in_4bit", False): # do nothing
+        return model
+
     if torch.cuda.device_count() > 1:
         from accelerate import dispatch_model
         from accelerate.utils import infer_auto_device_map, get_balanced_memory

src/llmtuner/extras/template.py

@@ -16,6 +16,7 @@ class Template:
 
     prefix: List[Union[str, Dict[str, str]]]
     prompt: List[Union[str, Dict[str, str]]]
+    system: str
     sep: List[Union[str, Dict[str, str]]]
     stop_words: List[str]
     use_history: bool
@@ -26,18 +27,18 @@ class Template:
         query: str,
         resp: str,
         history: Optional[List[Tuple[str, str]]] = None,
-        prefix: Optional[str] = None
+        system: Optional[str] = None
     ) -> Tuple[List[int], List[int]]:
         r"""
         Returns a single pair of token ids representing prompt and response respectively.
         """
-        prefix, history = self._format(query, resp, history, prefix)
-        encoded_pairs = self._encode(tokenizer, prefix, history)
+        system, history = self._format(query, resp, history, system)
+        encoded_pairs = self._encode(tokenizer, system, history)
         prompt_ids = []
         for query_ids, resp_ids in encoded_pairs[:-1]:
             prompt_ids = prompt_ids + query_ids + resp_ids
-        prompt_ids = prompt_ids + encoded_pairs[-1][0]
-        return prompt_ids, encoded_pairs[-1][1]
+        prompt_ids, answer_ids = prompt_ids + encoded_pairs[-1][0], encoded_pairs[-1][1]
+        return prompt_ids, answer_ids
 
     def encode_multiturn(
         self,
@@ -45,13 +46,13 @@ class Template:
         query: str,
         resp: str,
         history: Optional[List[Tuple[str, str]]] = None,
-        prefix: Optional[str] = None
+        system: Optional[str] = None
     ) -> List[Tuple[List[int], List[int]]]:
         r"""
         Returns multiple pairs of token ids representing prompts and responses respectively.
         """
-        prefix, history = self._format(query, resp, history, prefix)
-        encoded_pairs = self._encode(tokenizer, prefix, history)
+        system, history = self._format(query, resp, history, system)
+        encoded_pairs = self._encode(tokenizer, system, history)
         return encoded_pairs
 
     def _format(
@@ -59,26 +60,29 @@ class Template:
         query: str,
         resp: str,
         history: Optional[List[Tuple[str, str]]] = None,
-        prefix: Optional[str] = None
-    ) -> Tuple[List[Union[str, Dict[str, str]]], List[Tuple[str, str]]]:
+        system: Optional[str] = None
+    ) -> Tuple[str, List[Tuple[str, str]]]:
         r"""
         Aligns inputs to the standard format.
         """
-        prefix = [prefix] if prefix else self.prefix # use prefix if provided
+        system = system or self.system # use system if provided
         history = history if (history and self.use_history) else []
         history = history + [(query, resp)]
-        return prefix, history
+        return system, history
 
     def _get_special_ids(
         self,
         tokenizer: "PreTrainedTokenizer"
     ) -> Tuple[List[int], List[int]]:
-        if tokenizer.bos_token_id:
+        if (
+            tokenizer.bos_token_id is not None
+            and getattr(tokenizer, "add_bos_token", True)
+        ): # baichuan-13b has no bos token
             bos_ids = [tokenizer.bos_token_id]
         else:
             bos_ids = [] # bos token is optional
 
-        if tokenizer.eos_token_id:
+        if tokenizer.eos_token_id is not None:
             eos_ids = [tokenizer.eos_token_id]
         else:
             raise ValueError("EOS token is required.")
@@ -88,7 +92,7 @@ class Template:
     def _encode(
         self,
         tokenizer: "PreTrainedTokenizer",
-        prefix: List[Union[str, Dict[str, str]]],
+        system: str,
         history: List[Tuple[str, str]]
     ) -> List[Tuple[List[int], List[int]]]:
         r"""
@@ -101,8 +105,9 @@ class Template:
         encoded_pairs = []
         for turn_idx, (query, resp) in enumerate(history):
             if turn_idx == 0:
-                if prefix: # has prefix
-                    prefix_ids = bos_ids + self._convert_inputs_to_ids(tokenizer, context=prefix) + sep_ids
+                prefix_ids = self._convert_inputs_to_ids(tokenizer, context=self.prefix, system=system)
+                if len(prefix_ids) != 0: # has prefix
+                    prefix_ids = bos_ids + prefix_ids + sep_ids
                 else:
                     prefix_ids = bos_ids
             else:
@@ -117,8 +122,9 @@ class Template:
         self,
         tokenizer: "PreTrainedTokenizer",
         context: List[Union[str, Dict[str, str]]],
-        query: Optional[str] = "",
-        idx: Optional[str] = ""
+        system: Optional[str] = None,
+        query: Optional[str] = None,
+        idx: Optional[str] = None
     ) -> List[int]:
         r"""
         Converts context to token ids.
@@ -131,13 +137,15 @@ class Template:
         token_ids = []
         for elem in context:
             if isinstance(elem, str):
-                elem = elem.replace("{{query}}", query, 1)
-                elem = elem.replace("{{idx}}", idx, 1)
+                elem = elem.replace("{{system}}", system, 1) if system is not None else elem
+                elem = elem.replace("{{query}}", query, 1) if query is not None else elem
+                elem = elem.replace("{{idx}}", idx, 1) if idx is not None else elem
                 token_ids = token_ids + tokenizer.encode(elem, **kwargs)
             elif isinstance(elem, dict):
                 token_ids = token_ids + [tokenizer.convert_tokens_to_ids(elem.get("token"))]
             else:
                 raise NotImplementedError
+
         return token_ids
 
 
@@ -147,7 +155,7 @@ class Llama2Template(Template):
     def _encode(
         self,
         tokenizer: "PreTrainedTokenizer",
-        prefix: List[Union[str, Dict[str, str]]],
+        system: str,
         history: List[Tuple[str, str]]
     ) -> List[Tuple[List[int], List[int]]]:
         r"""
@@ -157,10 +165,9 @@ class Llama2Template(Template):
         """
         bos_ids, eos_ids = self._get_special_ids(tokenizer)
         encoded_pairs = []
-        assert isinstance(prefix[0], str), "LLaMA-2 template only accepts list containing a single string."
         for turn_idx, (query, resp) in enumerate(history):
-            if turn_idx == 0: # llama2 template has not sep_ids
-                query = prefix[0] + query
+            if turn_idx == 0: # llama2 template has no sep_ids
+                query = self.prefix[0].replace("{{system}}", system) + query
             query_ids = self._convert_inputs_to_ids(tokenizer, context=self.prompt, query=query)
             resp_ids = self._convert_inputs_to_ids(tokenizer, context=[resp])
             encoded_pairs.append((bos_ids + query_ids, resp_ids + eos_ids))
@@ -174,14 +181,16 @@ def register_template(
     name: str,
     prefix: List[Union[str, Dict[str, str]]],
     prompt: List[Union[str, Dict[str, str]]],
+    system: str,
     sep: List[Union[str, Dict[str, str]]],
-    stop_words: List[str],
-    use_history: bool
+    stop_words: Optional[List[str]] = [],
+    use_history: Optional[bool] = True
 ) -> None:
     template_class = Llama2Template if "llama2" in name else Template
     templates[name] = template_class(
         prefix=prefix,
         prompt=prompt,
+        system=system,
         sep=sep,
         stop_words=stop_words,
         use_history=use_history
@@ -195,8 +204,13 @@ def get_template_and_fix_tokenizer(
     template = templates.get(name, None)
     assert template is not None, "Template {} does not exist.".format(name)
 
+    additional_special_tokens = template.stop_words
     if len(template.stop_words): # inplace method
-        tokenizer.eos_token = template.stop_words[0]
+        if tokenizer.eos_token_id is not None:
+            additional_special_tokens.append(tokenizer.eos_token)
+
+        tokenizer.eos_token = additional_special_tokens[0] # use the first stop word as eos token
+        additional_special_tokens.pop(0)
         logger.info("Replace eos token: {}".format(tokenizer.eos_token))
 
     if tokenizer.eos_token_id is None:
@@ -204,10 +218,13 @@ def get_template_and_fix_tokenizer(
         logger.info("Add eos token: {}".format(tokenizer.eos_token))
 
     if tokenizer.pad_token_id is None:
+        if tokenizer.unk_token_id is not None:
+            tokenizer.pad_token = tokenizer.unk_token
+        else:
             tokenizer.pad_token = tokenizer.eos_token
         logger.info("Add pad token: {}".format(tokenizer.pad_token))
 
-    tokenizer.add_special_tokens(dict(additional_special_tokens=template.stop_words))
+    tokenizer.add_special_tokens(dict(additional_special_tokens=additional_special_tokens))
     return template
 
 
@@ -220,8 +237,8 @@ register_template(
     prompt=[
         "{{query}}"
     ],
+    system="",
     sep=[],
-    stop_words=[],
     use_history=False
 )
 
@@ -232,17 +249,18 @@ Default template.
 register_template(
     name="default",
     prefix=[
-        "A chat between a curious user and an artificial intelligence assistant. "
-        "The assistant gives helpful, detailed, and polite answers to the user's questions."
+        "{{system}}"
     ],
     prompt=[
         "Human: {{query}}\nAssistant: "
     ],
+    system=(
+        "A chat between a curious user and an artificial intelligence assistant. "
+        "The assistant gives helpful, detailed, and polite answers to the user's questions."
+    ),
     sep=[
         "\n"
-    ],
-    stop_words=[],
-    use_history=True
+    ]
 )
 
 
@@ -254,38 +272,39 @@ Supports: https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
 register_template(
     name="llama2",
     prefix=[
-        "<<SYS>>\nYou are a helpful, respectful and honest assistant. "
+        "<<SYS>>\n{{system}}\n<</SYS>>\n\n"
+    ],
+    prompt=[
+        "[INST] {{query}} [/INST] "
+    ],
+    system=(
+        "You are a helpful, respectful and honest assistant. "
         "Always answer as helpfully as possible, while being safe.  "
         "Your answers should not include any harmful, unethical, "
         "racist, sexist, toxic, dangerous, or illegal content. "
         "Please ensure that your responses are socially unbiased and positive in nature.\n"
         "If a question does not make any sense, or is not factually coherent, "
         "explain why instead of answering something not correct. "
-        "If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n\n"
-    ],
-    prompt=[
-        "[INST] {{query}} [/INST] "
-    ],
-    sep=[],
-    stop_words=[],
-    use_history=True
+        "If you don't know the answer to a question, please don't share false information."
+    ),
+    sep=[]
 )
 
 
 r"""
 Supports: https://github.com/ymcui/Chinese-LLaMA-Alpaca-2
+          https://huggingface.co/ziqingyang/chinese-alpaca-2-7b
 """
 register_template(
     name="llama2_zh",
     prefix=[
-        "<<SYS>>\nYou are a helpful assistant. 你是一个乐于助人的助手。\n<</SYS>>\n\n"
+        "<<SYS>>\n{{system}}\n<</SYS>>\n\n"
     ],
     prompt=[
         "[INST] {{query}} [/INST] "
     ],
-    sep=[],
-    stop_words=[],
-    use_history=True
+    system="You are a helpful assistant. 你是一个乐于助人的助手。",
+    sep=[]
 )
 
 
@@ -296,17 +315,18 @@ Supports: https://huggingface.co/tatsu-lab/alpaca-7b-wdiff
 register_template(
     name="alpaca",
     prefix=[
-        "Below is an instruction that describes a task. "
-        "Write a response that appropriately completes the request."
+        "{{system}}"
     ],
     prompt=[
         "### Instruction:\n{{query}}\n\n### Response:\n"
     ],
+    system=(
+        "Below is an instruction that describes a task. "
+        "Write a response that appropriately completes the request."
+    ),
     sep=[
         "\n\n"
-    ],
-    stop_words=[],
-    use_history=True
+    ]
 )
 
 
@@ -317,15 +337,16 @@ Supports: https://huggingface.co/lmsys/vicuna-7b-delta-v1.1
 register_template(
     name="vicuna",
     prefix=[
-        "A chat between a curious user and an artificial intelligence assistant. "
-        "The assistant gives helpful, detailed, and polite answers to the user's questions."
+        "{{system}}"
     ],
     prompt=[
         "USER: {{query}} ASSISTANT: "
     ],
-    sep=[],
-    stop_words=[],
-    use_history=True
+    system=(
+        "A chat between a curious user and an artificial intelligence assistant. "
+        "The assistant gives helpful, detailed, and polite answers to the user's questions."
+    ),
+    sep=[]
 )
 
 
@@ -334,15 +355,16 @@ Supports: https://huggingface.co/BelleGroup/BELLE-LLaMA-EXT-13B
 """
 register_template(
     name="belle",
-    prefix=[],
+    prefix=[
+        "{{system}}"
+    ],
     prompt=[
         "Human: {{query}}\n\nBelle: "
     ],
+    system="",
     sep=[
         "\n\n"
-    ],
-    stop_words=[],
-    use_history=True
+    ]
 )
 
 
@@ -351,15 +373,16 @@ Supports: https://github.com/CVI-SZU/Linly
 """
 register_template(
     name="linly",
-    prefix=[],
+    prefix=[
+        "{{system}}"
+    ],
     prompt=[
         "User: {{query}}\nBot: "
     ],
+    system="",
     sep=[
         "\n"
-    ],
-    stop_words=[],
-    use_history=True
+    ]
 )
 
 
@@ -368,15 +391,16 @@ Supports: https://github.com/Neutralzz/BiLLa
 """
 register_template(
     name="billa",
-    prefix=[],
+    prefix=[
+        "{{system}}"
+    ],
     prompt=[
         "Human: {{query}}\nAssistant: "
     ],
+    system="",
     sep=[
         "\n"
-    ],
-    stop_words=[],
-    use_history=True
+    ]
 )
 
 
@@ -385,18 +409,19 @@ Supports: https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-v1
 """
 register_template(
     name="ziya",
-    prefix=[],
+    prefix=[
+        "{{system}}"
+    ],
     prompt=[
         {"token": "<human>"},
         ":{{query}}\n",
         {"token": "<bot>"},
         ":"
     ],
+    system="",
     sep=[
         "\n"
-    ],
-    stop_words=[],
-    use_history=True
+    ]
 )
 
 
@@ -406,17 +431,18 @@ Supports: https://huggingface.co/qhduan/aquilachat-7b
 register_template(
     name="aquila",
     prefix=[
-        "A chat between a curious human and an artificial intelligence assistant. "
-        "The assistant gives helpful, detailed, and polite answers to the human's questions."
+        "{{system}}"
     ],
     prompt=[
         "Human: {{query}}###Assistant: "
     ],
+    system=(
+        "A chat between a curious human and an artificial intelligence assistant. "
+        "The assistant gives helpful, detailed, and polite answers to the human's questions."
+    ),
     sep=[
         "###"
-    ],
-    stop_words=[],
-    use_history=True
+    ]
 )
 
 
@@ -425,19 +451,22 @@ Supports: https://huggingface.co/internlm/internlm-chat-7b
 """
 register_template(
     name="intern",
-    prefix=[],
+    prefix=[
+        "{{system}}"
+    ],
     prompt=[
         "<|User|>:{{query}}",
         {"token": "<eoh>"},
         "\n<|Bot|>:"
     ],
+    system="",
     sep=[
         "\n"
     ],
     stop_words=[
+        "</s>", # internlm cannot replace eos token
         "<eoa>"
-    ],
-    use_history=True
+    ]
 )
 
 
@@ -447,17 +476,18 @@ Supports: https://huggingface.co/baichuan-inc/Baichuan-13B-Chat
 register_template(
     name="baichuan",
     prefix=[
-        {"token": "<reserved_102>"} # user token (a little difference in the first turn)
+        "{{system}}",
+        {"token": "<reserved_102>"} # user token
     ],
     prompt=[
         "{{query}}",
         {"token": "<reserved_103>"} # assistant token
     ],
+    system="",
     sep=[],
     stop_words=[
         "<reserved_102>" # user token
-    ],
-    use_history=True
+    ]
 )
 
 
@@ -469,7 +499,7 @@ register_template(
     name="starchat",
     prefix=[
         {"token": "<|system|>"},
-        "\n",
+        "\n{{system}}",
         {"token": "<|end|>"}
     ],
     prompt=[
@@ -479,13 +509,13 @@ register_template(
         "\n",
         {"token": "<|assistant|>"}
     ],
+    system="",
     sep=[
         "\n"
     ],
     stop_words=[
         "<|end|>"
-    ],
-    use_history=True
+    ]
 )
 
 
@@ -496,7 +526,7 @@ register_template(
     name="chatml",
     prefix=[
         {"token": "<|im_start|>"},
-        "system\nYou are a helpful assistant.",
+        "system\n{{system}}",
         {"token": "<|im_end|>"}
     ],
     prompt=[
@@ -507,13 +537,13 @@ register_template(
         {"token": "<|im_start|>"},
         "assistant\n"
     ],
+    system="You are a helpful assistant.",
     sep=[
         "\n"
     ],
     stop_words=[
         "<|im_end|>"
-    ],
-    use_history=True
+    ]
 )
 
 
@@ -524,14 +554,14 @@ register_template(
     name="chatglm2",
     prefix=[
         {"token": "[gMASK]"},
-        {"token": "sop"}
+        {"token": "sop"},
+        "{{system}}"
     ],
     prompt=[
         "[Round {{idx}}]\n\n问：{{query}}\n\n答："
     ],
+    system="",
     sep=[
         "\n\n"
-    ],
-    stop_words=[],
-    use_history=True
+    ]
 )

src/llmtuner/hparams/data_args.py

@@ -10,7 +10,7 @@ class DatasetAttr:
     load_from: str
     dataset_name: Optional[str] = None
     dataset_sha1: Optional[str] = None
-    source_prefix: Optional[str] = None
+    system_prompt: Optional[str] = None
 
     def __repr__(self) -> str:
         return self.dataset_name
@@ -86,9 +86,9 @@ class DataArguments:
         default=True,
         metadata={"help": "Whether to ignore the tokens corresponding to padded labels in the loss computation or not."}
     )
-    source_prefix: Optional[str] = field(
+    system_prompt: Optional[str] = field(
         default=None,
-        metadata={"help": "A prefix to add before every source text. Use `|` to separate multiple prefixes in training."}
+        metadata={"help": "System prompt to add before the user query. Use `|` to separate multiple prompts in training."}
     )
     val_size: Optional[float] = field(
         default=0,
@@ -100,12 +100,9 @@ class DataArguments:
         with open(os.path.join(self.dataset_dir, "dataset_info.json"), "r") as f:
             dataset_info = json.load(f)
 
-        if self.source_prefix is not None:
-            prefix_list = self.source_prefix.split("|")
-            prefix_list = prefix_list * len(dataset_names) if len(prefix_list) == 1 else prefix_list
-            assert len(prefix_list) == len(dataset_names), "The number of prefixes should be either identical with datasets or 1."
-        else:
-            prefix_list = [None] * len(dataset_names)
+        prompt_list = self.system_prompt.split("|") if self.system_prompt else [None]
+        prompt_list = prompt_list * (len(dataset_names) // len(prompt_list))
+        assert len(prompt_list) == len(dataset_names), "Number of system prompts should be equal to datasets or 1."
 
         if self.interleave_probs is not None:
             self.interleave_probs = [float(prob.strip()) for prob in self.interleave_probs.split(",")]
@@ -126,12 +123,11 @@ class DataArguments:
                     dataset_sha1=dataset_info[name].get("file_sha1", None)
                 )
 
-            dataset_attr.source_prefix = prefix_list[i]
-
             if "columns" in dataset_info[name]:
                 dataset_attr.prompt = dataset_info[name]["columns"].get("prompt", None)
                 dataset_attr.query = dataset_info[name]["columns"].get("query", None)
                 dataset_attr.response = dataset_info[name]["columns"].get("response", None)
                 dataset_attr.history = dataset_info[name]["columns"].get("history", None)
 
+            dataset_attr.system_prompt = prompt_list[i]
             self.dataset_list.append(dataset_attr)

src/llmtuner/hparams/finetuning_args.py

@@ -8,7 +8,7 @@ class FinetuningArguments:
     r"""
     Arguments pertaining to which techniques we are going to fine-tuning with.
     """
-    finetuning_type: Optional[Literal["none", "freeze", "lora", "full"]] = field(
+    finetuning_type: Optional[Literal["lora", "freeze", "full", "none"]] = field(
         default="lora",
         metadata={"help": "Which fine-tuning method to use."}
     )
@@ -49,7 +49,7 @@ class FinetuningArguments:
         metadata={"help": "Dropout rate for the LoRA fine-tuning."}
     )
     lora_target: Optional[str] = field(
-        default="q_proj,v_proj",
+        default=None,
         metadata={"help": "Name(s) of target modules to apply LoRA. Use commas to separate multiple modules. \
                   LLaMA choices: [\"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\", \"gate_proj\", \"up_proj\", \"down_proj\"], \
                   BLOOM & Falcon choices: [\"query_key_value\", \"self_attention.dense\", \"mlp.dense\"], \
@@ -61,6 +61,10 @@ class FinetuningArguments:
         default=True,
         metadata={"help": "Whether to resume training from the last LoRA weights or create new weights after merging them."}
     )
+    ppo_score_norm: Optional[bool] = field(
+        default=False,
+        metadata={"help": "Use score normalization in PPO Training."}
+    )
     dpo_beta: Optional[float] = field(
         default=0.1,
         metadata={"help": "The beta parameter for the DPO loss."}
@@ -77,7 +81,7 @@ class FinetuningArguments:
 
         self.trainable_layers = ["{:d}.{}".format(idx, self.name_module_trainable) for idx in trainable_layer_ids]
 
-        assert self.finetuning_type in ["none", "freeze", "lora", "full"], "Invalid fine-tuning method."
+        assert self.finetuning_type in ["lora", "freeze", "full", "none"], "Invalid fine-tuning method."
 
     def save_to_json(self, json_path: str):
         r"""Saves the content of this instance in JSON format inside `json_path`."""

src/llmtuner/hparams/model_args.py

@@ -43,9 +43,9 @@ class ModelArguments:
         default=True,
         metadata={"help": "Whether to use double quantization in int4 training or not."}
     )
-    compute_dtype: Optional[torch.dtype] = field(
+    rope_scaling: Optional[Literal["linear", "dynamic"]] = field(
         default=None,
-        metadata={"help": "Used in quantization configs. Do not specify this argument manually."}
+        metadata={"help": "Adopt scaled rotary positional embeddings."}
     )
     checkpoint_dir: Optional[str] = field(
         default=None,
@@ -63,8 +63,19 @@ class ModelArguments:
         default=None,
         metadata={"help": "Auth token to log in with Hugging Face Hub."}
     )
+    compute_dtype: Optional[torch.dtype] = field(
+        default=None,
+        metadata={"help": "Used in quantization configs. Do not specify this argument manually."}
+    )
+    model_max_length: Optional[int] = field(
+        default=None,
+        metadata={"help": "Used in rope scaling. Do not specify this argument manually."}
+    )
 
     def __post_init__(self):
+        if self.compute_dtype is not None or self.model_max_length is not None:
+            raise ValueError("These arguments cannot be specified.")
+
         if self.checkpoint_dir is not None: # support merging multiple lora weights
             self.checkpoint_dir = [cd.strip() for cd in self.checkpoint_dir.split(",")]
 

src/llmtuner/tuner/core/loader.py

@@ -1,5 +1,7 @@
 import os
+import math
 import torch
+from types import MethodType
 from typing import TYPE_CHECKING, Literal, Optional, Tuple
 
 from transformers import (
@@ -66,16 +68,62 @@ def load_model_and_tokenizer(
         **config_kwargs
     )
 
-    if model_args.checkpoint_dir is not None and finetuning_args.finetuning_type == "full":
+    if finetuning_args.finetuning_type == "full" and model_args.checkpoint_dir is not None:
         model_to_load = model_args.checkpoint_dir[0]
     else:
         model_to_load = model_args.model_name_or_path
 
     config = AutoConfig.from_pretrained(model_to_load, **config_kwargs)
-    is_mergeable = True
+
+    if hasattr(config, "fp16") and hasattr(config, "bf16"): # fix Qwen config
+        if model_args.compute_dtype == torch.bfloat16:
+            setattr(config, "bf16", True)
+        else:
+            setattr(config, "fp16", True)
+
+    # Set RoPE scaling
+    if model_args.rope_scaling is not None:
+        if hasattr(config, "use_dynamic_ntk"): # for Qwen models
+            if is_trainable:
+                logger.warning("Qwen model does not support RoPE scaling in training.")
+            else:
+                setattr(config, "use_dynamic_ntk", True)
+                setattr(config, "use_logn_attn", True)
+                logger.info("Using dynamic NTK scaling.")
+
+        elif hasattr(config, "rope_scaling"): # for LLaMA models
+            require_version("transformers>=4.31.0", "RoPE scaling requires transformers>=4.31.0")
+
+            if is_trainable:
+                if model_args.rope_scaling == "dynamic":
+                    logger.warning(
+                        "Dynamic NTK may not work well with fine-tuning. "
+                        "See: https://github.com/huggingface/transformers/pull/24653"
+                    )
+
+                current_max_length = getattr(config, "max_position_embeddings", None)
+                if current_max_length and model_args.model_max_length > current_max_length:
+                    scaling_factor = float(math.ceil(model_args.model_max_length / current_max_length))
+                else:
+                    logger.warning("Input length is smaller than max length. Consider increase input length.")
+                    scaling_factor = 1.0
+            else:
+                scaling_factor = 2.0
+
+            setattr(config, "rope_scaling", {"type": model_args.rope_scaling, "factor": scaling_factor})
+            logger.info("Using {} scaling strategy and setting scaling factor to {}".format(
+                model_args.rope_scaling, scaling_factor
+            ))
+
+        else:
+            logger.warning("Current model does not support RoPE scaling.")
 
     # Quantization configurations (using bitsandbytes library).
+    is_mergeable = True
     if model_args.quantization_bit is not None:
+        if is_deepspeed_zero3_enabled():
+            raise ValueError("DeepSpeed ZeRO-3 is incompatible with quantization.")
+
         if model_args.quantization_bit == 8:
             require_version("bitsandbytes>=0.37.0", "To fix: pip install bitsandbytes>=0.37.0")
             config_kwargs["load_in_8bit"] = True
@@ -92,18 +140,26 @@ def load_model_and_tokenizer(
             )
 
         is_mergeable = False
-        config_kwargs["device_map"] = {"": int(os.environ.get("LOCAL_RANK", "0"))}
+        config_kwargs["device_map"] = {"": int(os.environ.get("LOCAL_RANK", "0"))} if is_trainable else "auto"
         logger.info("Quantizing model to {} bit.".format(model_args.quantization_bit))
 
-    # Load and prepare pretrained models (without valuehead).
+    # Load and prepare pre-trained models (without valuehead).
     model = AutoModelForCausalLM.from_pretrained(
         model_to_load,
         config=config,
-        torch_dtype=torch.bfloat16 if model_args.compute_dtype == torch.bfloat16 else torch.float16,
+        torch_dtype=model_args.compute_dtype,
         low_cpu_mem_usage=(not is_deepspeed_zero3_enabled()),
         **config_kwargs
     )
 
+    # Disable custom generate method (for Qwen)
+    if "GenerationMixin" not in str(model.generate.__func__):
+        model.generate = MethodType(PreTrainedModel.generate, model)
+
+    # Fix LM head (for ChatGLM2)
+    if not hasattr(model, "lm_head") and hasattr(model, "transformer"):
+        setattr(model, "lm_head", model.transformer.output_layer)
+
     # Register auto class to save the custom code files.
     if isinstance(config, PretrainedConfig) and "AutoConfig" in getattr(config, "auto_map", {}):
         config.__class__.register_for_auto_class()
@@ -116,10 +172,10 @@ def load_model_and_tokenizer(
     model = prepare_model_for_training(model, finetuning_args.finetuning_type) if is_trainable else model
     model = init_adapter(model, model_args, finetuning_args, is_trainable, is_mergeable)
 
-    if stage == "rm" or stage == "ppo": # add value head
-        model: "AutoModelForCausalLMWithValueHead" = AutoModelForCausalLMWithValueHead.from_pretrained(model)
+    # Prepare model with valuehead for RLHF
+    if stage == "rm" or stage == "ppo":
+        model: AutoModelForCausalLMWithValueHead = AutoModelForCausalLMWithValueHead.from_pretrained(model)
         reset_logging()
-
         if stage == "rm" and model_args.checkpoint_dir is not None: # load valuehead weights to evaluate reward model
             logger.warning("Only the last checkpoint containing valuehead will be loaded as the valuehead.")
             if load_valuehead_params(model, model_args.checkpoint_dir[-1]):
@@ -133,9 +189,11 @@ def load_model_and_tokenizer(
             model.pretrained_model.load_adapter(model_args.reward_model, "reward", is_trainable=False)
             assert load_valuehead_params(model, model_args.reward_model), "Reward model is not correctly loaded."
 
+    # Prepare model for inference
     if not is_trainable:
         model.requires_grad_(False) # fix all model params
-        model = model.half() if model_args.quantization_bit is None else model # cast from fp32 to fp16
+        infer_dtype = torch.bfloat16 if torch.cuda.is_bf16_supported() else torch.float16 # detect cuda capability
+        model = model.to(infer_dtype) if model_args.quantization_bit is None else model
 
     trainable_params, all_param = count_parameters(model)
     logger.info("trainable params: {:d} || all params: {:d} || trainable%: {:.4f}".format(

src/llmtuner/tuner/core/parser.py

@@ -5,6 +5,7 @@ import datasets
 import transformers
 from typing import Any, Dict, Optional, Tuple
 from transformers import HfArgumentParser, Seq2SeqTrainingArguments
+from transformers.trainer_utils import get_last_checkpoint
 
 from llmtuner.extras.logging import get_logger
 from llmtuner.hparams import (
@@ -97,30 +98,36 @@ def get_train_args(
     if general_args.stage != "sft" and training_args.predict_with_generate:
         raise ValueError("`predict_with_generate` cannot be set as True except SFT.")
 
-    if training_args.do_train and training_args.predict_with_generate:
-        raise ValueError("`predict_with_generate` cannot be set as True while training.")
-
     if general_args.stage == "sft" and training_args.do_predict and not training_args.predict_with_generate:
         raise ValueError("Please enable `predict_with_generate` to save model predictions.")
 
     if general_args.stage in ["rm", "ppo"] and finetuning_args.finetuning_type != "lora":
-        raise ValueError("RM and PPO training can only be performed with the LoRA method.")
+        raise ValueError("RM and PPO stages can only be performed with the LoRA method.")
+
+    if general_args.stage in ["rm", "ppo"] and training_args.resume_from_checkpoint is not None:
+        raise ValueError("RM and PPO stages do not support `resume_from_checkpoint`.")
 
     if general_args.stage in ["ppo", "dpo"] and not training_args.do_train:
-        raise ValueError("PPO and DPO stage can only be performed at training.")
+        raise ValueError("PPO and DPO stages can only be performed at training.")
 
     if general_args.stage == "ppo" and model_args.reward_model is None:
         raise ValueError("Reward model is necessary for PPO training.")
 
-    if training_args.max_steps == -1 and data_args.streaming:
-        raise ValueError("Please specify `max_steps` in streaming mode.")
-
     if general_args.stage == "ppo" and data_args.streaming:
         raise ValueError("Streaming mode does not suppport PPO training currently.")
 
+    if training_args.max_steps == -1 and data_args.streaming:
+        raise ValueError("Please specify `max_steps` in streaming mode.")
+
     if data_args.val_size > 1e-6 and data_args.val_size < 1 and data_args.streaming:
         raise ValueError("Streaming mode should have an integer val size.")
 
+    if training_args.do_train and training_args.predict_with_generate:
+        raise ValueError("`predict_with_generate` cannot be set as True while training.")
+
+    if training_args.do_train and finetuning_args.finetuning_type == "lora" and finetuning_args.lora_target is None:
+        raise ValueError("Please specify `lora_target` in LoRA training.")
+
     if model_args.quantization_bit is not None and finetuning_args.finetuning_type != "lora":
         raise ValueError("Quantization is only compatible with the LoRA method.")
 
@@ -134,9 +141,15 @@ def get_train_args(
     if model_args.quantization_bit is not None and (not training_args.do_train):
         logger.warning("Evaluating model in 4/8-bit mode may cause lower scores.")
 
-    if training_args.do_train and (not training_args.fp16):
-        logger.warning("We recommend enable fp16 mixed precision training.")
+    if training_args.do_train and (not training_args.fp16) and (not training_args.bf16):
+        logger.warning("We recommend enable mixed precision training.")
 
+    # postprocess data_args
+    if data_args.max_samples is not None and data_args.streaming:
+        logger.warning("`max_samples` is incompatible with `streaming`. Disabling max_samples.")
+        data_args.max_samples = None
+
+    # postprocess training_args
     if (
         training_args.local_rank != -1
         and training_args.ddp_find_unused_parameters is None
@@ -145,24 +158,39 @@ def get_train_args(
         logger.warning("`ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training.")
         training_args.ddp_find_unused_parameters = False
 
-    if data_args.max_samples is not None and data_args.streaming:
-        logger.warning("`max_samples` is incompatible with `streaming`. Disabling max_samples.")
-        data_args.max_samples = None
+    if training_args.optim == "adamw_hf":
+        training_args.optim = "adamw_torch" # suppress warning
 
-    training_args.optim = "adamw_torch" if training_args.optim == "adamw_hf" else training_args.optim # suppress warning
+    if (
+        training_args.resume_from_checkpoint is None
+        and training_args.do_train
+        and os.path.isdir(training_args.output_dir)
+        and not training_args.overwrite_output_dir
+    ):
+        last_checkpoint = get_last_checkpoint(training_args.output_dir)
+        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
+            raise ValueError("Output directory already exists and is not empty. Use `overwrite_output_dir`.")
 
-    if model_args.quantization_bit is not None:
-        if training_args.fp16:
-            model_args.compute_dtype = torch.float16
-        elif training_args.bf16:
+        if last_checkpoint is not None:
+            training_args.resume_from_checkpoint = last_checkpoint
+            logger.info(
+                "Resuming from checkpoint. Change `output_dir` or use `overwrite_output_dir` to avoid."
+            )
+
+    # postprocess model_args
+    if training_args.bf16:
+        if not torch.cuda.is_bf16_supported():
+            raise ValueError("Current device does not support bf16 training.")
         model_args.compute_dtype = torch.bfloat16
     else:
-            model_args.compute_dtype = torch.float32
+        model_args.compute_dtype = torch.float16
+
+    model_args.model_max_length = data_args.max_source_length + data_args.max_target_length
 
     # Log on each process the small summary:
-    logger.info("Process rank: {}, device: {}, n_gpu: {}\n  distributed training: {}, 16-bits training: {}".format(
+    logger.info("Process rank: {}, device: {}, n_gpu: {}\n  distributed training: {}, compute dtype: {}".format(
         training_args.local_rank, training_args.device, training_args.n_gpu,
-        bool(training_args.local_rank != -1), training_args.fp16
+        bool(training_args.local_rank != -1), str(model_args.compute_dtype)
     ))
     logger.info(f"Training/evaluation parameters {training_args}")
 

src/llmtuner/tuner/dpo/trainer.py

@@ -2,7 +2,7 @@ import torch
 from collections import defaultdict
 from peft import PeftModel
 from typing import TYPE_CHECKING, Dict, Optional, Tuple, Union
-from transformers import Trainer
+from transformers import BatchEncoding, Trainer
 from trl import DPOTrainer
 
 from llmtuner.extras.constants import IGNORE_INDEX
@@ -32,32 +32,34 @@ class DPOPeftTrainer(PeftModelMixin, DPOTrainer):
         self._stored_metrics = defaultdict(lambda: defaultdict(list))
 
         Trainer.__init__(self, **kwargs)
-        if ref_model is not None:
-            if hasattr(self, "accelerator"):
-                self.ref_model = self.accelerator.prepare_model(self.ref_model, evaluation_mode=True)
-            else:
+        if not hasattr(self, "accelerator"):
             raise AttributeError("Please update `transformers`.")
 
+        if ref_model is not None:
+            self.ref_model = self.accelerator.prepare_model(self.ref_model, evaluation_mode=True)
+
     def concatenated_forward(
         self,
         model: Optional[torch.nn.Module] = None,
         batch: Optional[Dict[str, torch.Tensor]] = None
     ) -> Tuple[torch.FloatTensor, torch.FloatTensor, torch.FloatTensor, torch.FloatTensor]:
+        batch_copied = BatchEncoding({k: v.detach().clone() for k, v in batch.items()}) # avoid error
         unwrapped_model: "PreTrainedModel" = self.accelerator.unwrap_model(self.model)
+
         if not torch.is_grad_enabled():
             unwrapped_model.gradient_checkpointing_disable()
 
         if model is None and isinstance(unwrapped_model, PeftModel): # peft model has no ref_model
             with unwrapped_model.disable_adapter():
-                all_logits: torch.Tensor = self.model(
-                    batch["input_ids"],
-                    attention_mask=batch["attention_mask"],
+                all_logits = self.model(
+                    input_ids=batch_copied["input_ids"],
+                    attention_mask=batch_copied["attention_mask"],
                     return_dict=True
                 ).logits.to(torch.float32)
         else:
-            all_logits: torch.Tensor = model(
-                batch["input_ids"],
-                attention_mask=batch["attention_mask"],
+            all_logits = model(
+                input_ids=batch_copied["input_ids"],
+                attention_mask=batch_copied["attention_mask"],
                 return_dict=True
             ).logits.to(torch.float32)
 

src/llmtuner/tuner/dpo/workflow.py

@@ -50,7 +50,7 @@ def run_dpo(
 
     # Training
     if training_args.do_train:
-        train_result = trainer.train()
+        train_result = trainer.train(resume_from_checkpoint=training_args.resume_from_checkpoint)
         trainer.log_metrics("train", train_result.metrics)
         trainer.save_metrics("train", train_result.metrics)
         trainer.save_state()

src/llmtuner/tuner/ppo/trainer.py

@@ -7,12 +7,12 @@ from typing import TYPE_CHECKING, Callable, Dict, List, Optional, Tuple
 from transformers import TrainerState, TrainerControl
 
 from trl import PPOTrainer
-from trl.core import LengthSampler
+from trl.core import LengthSampler, PPODecorators, logprobs_from_logits
 
 from llmtuner.extras.logging import get_logger
-from llmtuner.extras.misc import AverageMeter, count_parameters, get_logits_processor, get_stopping_criteria
+from llmtuner.extras.misc import AverageMeter, count_parameters, get_logits_processor
 from llmtuner.tuner.core.trainer import PeftTrainer
-from llmtuner.tuner.ppo.utils import cast_layernorm_dtype, replace_model
+from llmtuner.tuner.ppo.utils import replace_model
 
 if TYPE_CHECKING:
     from transformers import Seq2SeqTrainingArguments
@@ -35,6 +35,7 @@ class PPOPeftTrainer(PPOTrainer, PeftTrainer):
         finetuning_args: "FinetuningArguments",
         generating_args: "GeneratingArguments",
         callbacks: List["LogCallback"],
+        compute_dtype: torch.dtype,
         **kwargs
     ):
         PPOTrainer.__init__(self, **kwargs)
@@ -42,6 +43,7 @@ class PPOPeftTrainer(PPOTrainer, PeftTrainer):
         self.finetuning_args = finetuning_args
         self.generating_args = generating_args
         self.log_callback = callbacks[0]
+        self.compute_dtype = compute_dtype
         self.state = TrainerState()
         self.control = TrainerControl()
 
@@ -74,8 +76,9 @@ class PPOPeftTrainer(PPOTrainer, PeftTrainer):
 
         # Keyword arguments for `model.generate`
         gen_kwargs = self.generating_args.to_dict()
+        gen_kwargs["eos_token_id"] = list(set([self.tokenizer.eos_token_id] + self.tokenizer.additional_special_tokens_ids))
+        gen_kwargs["pad_token_id"] = self.tokenizer.pad_token_id
         gen_kwargs["logits_processor"] = get_logits_processor()
-        gen_kwargs["stopping_criteria"] = get_stopping_criteria(self.tokenizer.additional_special_tokens_ids)
 
         length_sampler = LengthSampler(max_target_length // 2, max_target_length)
         unwrapped_model: "AutoModelForCausalLMWithValueHead" = self.accelerator.unwrap_model(self.model)
@@ -149,10 +152,8 @@ class PPOPeftTrainer(PPOTrainer, PeftTrainer):
         if length_sampler is not None:
             generation_kwargs["max_new_tokens"] = length_sampler()
 
-        self.model, layer_norm_params = cast_layernorm_dtype(self.model)
         unwrapped_model: "AutoModelForCausalLMWithValueHead" = self.accelerator.unwrap_model(self.model)
         response: torch.Tensor = unwrapped_model.generate(**batch, **generation_kwargs)
-        self.model, _ = cast_layernorm_dtype(self.model, layer_norm_params)
 
         # Temporary hack to ensure the generation config is not initialized for each iteration of the evaluation loop
         # Inspired by: https://github.com/huggingface/transformers/blob/v4.28.1/src/transformers/trainer_seq2seq.py#L273
@@ -181,11 +182,80 @@ class PPOPeftTrainer(PPOTrainer, PeftTrainer):
         """
         replace_model(unwrapped_model, target="reward")
         batch = self.prepare_model_inputs(queries, responses)
+
+        with torch.cuda.amp.autocast(dtype=self.compute_dtype): # support bf16
             _, _, values = self.model(**batch, output_hidden_states=True, return_dict=True)
+
+        if values.size(0) != batch["input_ids"].size(0): # adapt to chatglm2
+            values = torch.transpose(values, 0, 1)
+
         rewards = [reward for reward in values[:, -1].float().detach().cpu()] # use fp32 type
         replace_model(unwrapped_model, target="default")
         return rewards
 
+    @PPODecorators.empty_cuda_cache()
+    def batched_forward_pass(
+        self,
+        model: "AutoModelForCausalLMWithValueHead",
+        queries: torch.Tensor,
+        responses: torch.Tensor,
+        model_inputs: dict,
+        return_logits: Optional[bool] = False
+    ):
+        r"""
+        Calculates model outputs in multiple batches.
+
+        Subclass and override to inject custom behavior.
+        """
+        bs = len(queries)
+        fbs = self.config.mini_batch_size
+        all_logprobs = []
+        all_logits = []
+        all_masks = []
+        all_values = []
+
+        for i in range(math.ceil(bs / fbs)):
+            input_kwargs = {key: value[i * fbs : (i + 1) * fbs] for key, value in model_inputs.items()}
+            query_batch = queries[i * fbs : (i + 1) * fbs]
+            response_batch = responses[i * fbs : (i + 1) * fbs]
+            input_ids = input_kwargs["input_ids"]
+            attention_mask = input_kwargs["attention_mask"]
+
+            with torch.cuda.amp.autocast(dtype=self.compute_dtype): # support bf16
+                logits, _, values = model(**input_kwargs)
+
+            if values.size(0) != input_ids.size(0): # adapt to chatglm2
+                values = torch.transpose(values, 0, 1)
+
+            logprobs = logprobs_from_logits(logits[:, :-1, :], input_ids[:, 1:])
+            masks = torch.zeros_like(attention_mask)
+            masks[:, :-1] = attention_mask[:, 1:]
+
+            for j in range(len(query_batch)):
+                start = len(query_batch[j]) - 1
+                if attention_mask[j, 0] == 0:  # offset left padding
+                    start += attention_mask[j, :].nonzero()[0]
+                end = start + len(response_batch[j])
+
+                masks[j, :start] = 0
+                masks[j, end:] = 0
+
+            if return_logits:
+                all_logits.append(logits)
+            else:
+                del logits
+
+            all_values.append(values)
+            all_logprobs.append(logprobs)
+            all_masks.append(masks)
+
+        return (
+            torch.cat(all_logprobs),
+            torch.cat(all_logits)[:, :-1] if return_logits else None,
+            torch.cat(all_values)[:, :-1],
+            torch.cat(all_masks)[:, :-1],
+        )
+
     def save_model(self, output_dir: Optional[str] = None) -> None:
         r"""
         Saves model checkpoint.

src/llmtuner/tuner/ppo/utils.py

@@ -1,7 +1,4 @@
-import torch
-from typing import TYPE_CHECKING, Dict, List, Literal, Optional, Tuple
-
-from llmtuner.extras.constants import LAYERNORM_NAMES
+from typing import TYPE_CHECKING, Literal
 
 if TYPE_CHECKING:
     from trl import AutoModelForCausalLMWithValueHead
@@ -18,22 +15,3 @@ def replace_model(model: "AutoModelForCausalLMWithValueHead", target: Literal["d
         "summary.weight": getattr(model, "{}_head_weight".format(target)),
         "summary.bias": getattr(model, "{}_head_bias".format(target))
     })
-
-
-def cast_layernorm_dtype(
-    model: "AutoModelForCausalLMWithValueHead",
-    layer_norm_names: List[str] = LAYERNORM_NAMES,
-    layer_norm_params: Optional[Dict[str, torch.Tensor]] = None
-) -> Tuple["AutoModelForCausalLMWithValueHead", Dict[str, torch.Tensor]]:
-
-    layer_norm_state_dict = {}
-
-    for name, param in model.named_parameters():
-        if param.ndim == 1 and any(layer_norm_name in name for layer_norm_name in layer_norm_names):
-            if layer_norm_params is not None:
-                param.data = layer_norm_params[name] # restore float32 weights
-            else:
-                layer_norm_state_dict[name] = param.data.detach().clone() # store float32 weights for stability
-                param.data = param.data.to(torch.float16)
-
-    return model, layer_norm_state_dict

src/llmtuner/tuner/ppo/workflow.py

@@ -6,6 +6,7 @@ from torch.optim import AdamW
 from typing import TYPE_CHECKING, Optional, List
 from transformers import DataCollatorForSeq2Seq
 from transformers.optimization import get_scheduler
+from transformers.utils.versions import require_version
 
 from llmtuner.dsets import get_dataset, preprocess_dataset
 from llmtuner.extras.ploting import plot_loss
@@ -37,9 +38,16 @@ def run_ppo(
         batch_size=training_args.per_device_train_batch_size * training_args.gradient_accumulation_steps,
         gradient_accumulation_steps=training_args.gradient_accumulation_steps,
         ppo_epochs=1,
-        max_grad_norm=training_args.max_grad_norm
+        max_grad_norm=training_args.max_grad_norm,
+        seed=training_args.seed,
+        optimize_cuda_cache=True
     )
 
+    if finetuning_args.ppo_score_norm:
+        require_version("trl>=0.5.1.dev0", "To fix: pip install git+https://github.com/huggingface/trl.git")
+        ppo_config.use_score_scaling = True
+        ppo_config.use_score_norm = True
+
     optimizer = AdamW(filter(lambda p: p.requires_grad, model.parameters()), lr=training_args.learning_rate)
     total_train_batch_size = (
         training_args.per_device_train_batch_size * training_args.gradient_accumulation_steps * training_args.world_size
@@ -58,6 +66,7 @@ def run_ppo(
         finetuning_args=finetuning_args,
         generating_args=generating_args,
         callbacks=callbacks,
+        compute_dtype=model_args.compute_dtype,
         config=ppo_config,
         model=model,
         ref_model=None,

src/llmtuner/tuner/pt/workflow.py

@@ -39,7 +39,7 @@ def run_pt(
 
     # Training
     if training_args.do_train:
-        train_result = trainer.train()
+        train_result = trainer.train(resume_from_checkpoint=training_args.resume_from_checkpoint)
         trainer.log_metrics("train", train_result.metrics)
         trainer.save_metrics("train", train_result.metrics)
         trainer.save_state()
@@ -56,6 +56,5 @@ def run_pt(
             perplexity = float("inf")
 
         metrics["perplexity"] = perplexity
-
         trainer.log_metrics("eval", metrics)
         trainer.save_metrics("eval", metrics)

src/llmtuner/tuner/rm/trainer.py

@@ -42,6 +42,8 @@ class PairwisePeftTrainer(PeftTrainer):
         """
         batch_size = inputs["input_ids"].size(0) // 2
         _, _, values = model(**inputs, output_hidden_states=True, return_dict=True)
+        if values.size(0) != inputs["input_ids"].size(0): # adapt to chatglm2
+            values = torch.transpose(values, 0, 1)
         r_accept, r_reject = values[:, -1].split(batch_size, dim=0)
         loss = -torch.log(torch.sigmoid(r_accept - r_reject)).mean()
         return (loss, [loss, r_accept, r_reject]) if return_outputs else loss

src/llmtuner/tuner/sft/metric.py

@@ -25,7 +25,7 @@ class ComputeMetrics:
         Uses the model predictions to compute metrics.
         """
         preds, labels = eval_preds
-        score_dict = {"accuracy": [], "rouge-1": [], "rouge-2": [], "rouge-l": [], "bleu-4": []}
+        score_dict = {"rouge-1": [], "rouge-2": [], "rouge-l": [], "bleu-4": []}
 
         preds = np.where(preds != IGNORE_INDEX, preds, self.tokenizer.pad_token_id)
         labels = np.where(labels != IGNORE_INDEX, labels, self.tokenizer.pad_token_id)
@@ -49,6 +49,5 @@ class ComputeMetrics:
 
             bleu_score = sentence_bleu([list(label)], list(pred), smoothing_function=SmoothingFunction().method3)
             score_dict["bleu-4"].append(round(bleu_score * 100, 4))
-            score_dict["accuracy"].append(float(len(label) != 0 and pred[:len(label)] == label))
 
         return {k: float(np.mean(v)) for k, v in score_dict.items()}

src/llmtuner/tuner/sft/trainer.py

@@ -50,11 +50,12 @@ class Seq2SeqPeftTrainer(PeftTrainer):
         loss, generated_tokens, labels = super().prediction_step(
             model, inputs, prediction_loss_only=prediction_loss_only, ignore_keys=ignore_keys
         )
-        generated_tokens = (
-            generated_tokens[:, max(prompt_len, label_len):] if generated_tokens is not None else None
+        if generated_tokens is not None:
+            generated_tokens[:, :max(prompt_len, label_len)] = (
+                self.tokenizer.pad_token_id * torch.ones_like(generated_tokens[:, :max(prompt_len, label_len)])
             )
 
-        return (loss, generated_tokens, labels)
+        return loss, generated_tokens, labels
 
     def _pad_tensors_to_target_len(
         self,
@@ -72,10 +73,7 @@ class Seq2SeqPeftTrainer(PeftTrainer):
                 assert self.tokenizer.padding_side == "left", "This method only accepts left-padded tensor."
                 pad_token_id = self.tokenizer.pad_token_id
             else:
-                if self.model.config.pad_token_id is not None:
-                    pad_token_id = self.model.config.pad_token_id
-                else:
-                    raise ValueError("Pad_token_id must be set in the configuration of the model.")
+                raise ValueError("PAD token is required.")
 
         padded_tensor = pad_token_id * torch.ones_like(tgt_tensor)
         padded_tensor[:, -src_tensor.shape[-1]:] = src_tensor # adopt left-padding

src/llmtuner/tuner/sft/workflow.py

@@ -5,7 +5,7 @@ from transformers import DataCollatorForSeq2Seq
 
 from llmtuner.dsets import get_dataset, preprocess_dataset, split_dataset
 from llmtuner.extras.constants import IGNORE_INDEX
-from llmtuner.extras.misc import get_logits_processor, get_stopping_criteria
+from llmtuner.extras.misc import get_logits_processor
 from llmtuner.extras.ploting import plot_loss
 from llmtuner.tuner.core import load_model_and_tokenizer
 from llmtuner.tuner.sft.metric import ComputeMetrics
@@ -52,12 +52,13 @@ def run_sft(
 
     # Keyword arguments for `model.generate`
     gen_kwargs = generating_args.to_dict()
+    gen_kwargs["eos_token_id"] = list(set([tokenizer.eos_token_id] + tokenizer.additional_special_tokens_ids))
+    gen_kwargs["pad_token_id"] = tokenizer.pad_token_id
     gen_kwargs["logits_processor"] = get_logits_processor()
-    gen_kwargs["stopping_criteria"] = get_stopping_criteria(tokenizer.additional_special_tokens_ids)
 
     # Training
     if training_args.do_train:
-        train_result = trainer.train()
+        train_result = trainer.train(resume_from_checkpoint=training_args.resume_from_checkpoint)
         trainer.log_metrics("train", train_result.metrics)
         trainer.save_metrics("train", train_result.metrics)
         trainer.save_state()

src/llmtuner/tuner/tune.py

@@ -35,7 +35,7 @@ def run_exp(args: Optional[Dict[str, Any]] = None, callbacks: Optional[List["Tra
 
 
 def export_model(args: Optional[Dict[str, Any]] = None, max_shard_size: Optional[str] = "10GB"):
-    model_args, _, training_args, finetuning_args, _ = get_train_args(args)
+    model_args, _, training_args, finetuning_args, _, _ = get_train_args(args)
     model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args)
     model.save_pretrained(training_args.output_dir, max_shard_size=max_shard_size)
     try:

src/llmtuner/webui/chat.py

@@ -26,7 +26,7 @@ class WebChatModel(ChatModel):
         finetuning_type: str,
         quantization_bit: str,
         template: str,
-        source_prefix: str
+        system_prompt: str
     ):
         if self.model is not None:
             yield ALERTS["err_exists"][lang]
@@ -53,9 +53,9 @@ class WebChatModel(ChatModel):
             model_name_or_path=model_name_or_path,
             checkpoint_dir=checkpoint_dir,
             finetuning_type=finetuning_type,
-            quantization_bit=int(quantization_bit) if quantization_bit else None,
+            quantization_bit=int(quantization_bit) if quantization_bit != "None" else None,
             template=template,
-            source_prefix=source_prefix
+            system_prompt=system_prompt
         )
         super().__init__(args)
 
@@ -73,7 +73,7 @@ class WebChatModel(ChatModel):
         chatbot: List[Tuple[str, str]],
         query: str,
         history: List[Tuple[str, str]],
-        prefix: str,
+        system: str,
         max_new_tokens: int,
         top_p: float,
         temperature: float
@@ -81,7 +81,7 @@ class WebChatModel(ChatModel):
         chatbot.append([query, ""])
         response = ""
         for new_text in self.stream_chat(
-            query, history, prefix, max_new_tokens=max_new_tokens, top_p=top_p, temperature=temperature
+            query, history, system, max_new_tokens=max_new_tokens, top_p=top_p, temperature=temperature
         ):
             response += new_text
             response = self.postprocess(response)

src/llmtuner/webui/common.py

@@ -6,7 +6,7 @@ import gradio as gr
 from peft.utils import WEIGHTS_NAME as PEFT_WEIGHTS_NAME
 from transformers.trainer import WEIGHTS_NAME, WEIGHTS_INDEX_NAME
 
-from llmtuner.extras.constants import SUPPORTED_MODELS
+from llmtuner.extras.constants import DEFAULT_TEMPLATE, SUPPORTED_MODELS
 
 
 DEFAULT_CACHE_DIR = "cache"
@@ -29,12 +29,14 @@ def load_config() -> Dict[str, Any]:
         with open(get_config_path(), "r", encoding="utf-8") as f:
             return json.load(f)
     except:
-        return {"last_model": "", "path_dict": {}}
+        return {"lang": "", "last_model": "", "path_dict": {}}
 
 
-def save_config(model_name: str, model_path: str) -> None:
+def save_config(lang: str, model_name: str, model_path: str) -> None:
     os.makedirs(DEFAULT_CACHE_DIR, exist_ok=True)
     user_config = load_config()
+    user_config["lang"] = lang or user_config["lang"]
+    if model_name:
         user_config["last_model"] = model_name
         user_config["path_dict"][model_name] = model_path
     with open(get_config_path(), "w", encoding="utf-8") as f:
@@ -46,6 +48,12 @@ def get_model_path(model_name: str) -> str:
     return user_config["path_dict"].get(model_name, SUPPORTED_MODELS.get(model_name, ""))
 
 
+def get_template(model_name: str) -> str:
+    if model_name.endswith("Chat") and model_name.split("-")[0] in DEFAULT_TEMPLATE:
+        return DEFAULT_TEMPLATE[model_name.split("-")[0]]
+    return "default"
+
+
 def list_checkpoint(model_name: str, finetuning_type: str) -> Dict[str, Any]:
     checkpoints = []
     save_dir = os.path.join(get_save_dir(model_name), finetuning_type)

src/llmtuner/webui/components/__init__.py

@@ -1,5 +1,5 @@
 from llmtuner.webui.components.top import create_top
-from llmtuner.webui.components.sft import create_sft_tab
+from llmtuner.webui.components.train import create_train_tab
 from llmtuner.webui.components.eval import create_eval_tab
 from llmtuner.webui.components.infer import create_infer_tab
 from llmtuner.webui.components.export import create_export_tab

src/llmtuner/webui/components/chatbot.py

@@ -17,7 +17,7 @@ def create_chat_box(
 
         with gr.Row():
             with gr.Column(scale=4):
-                prefix = gr.Textbox(show_label=False)
+                system = gr.Textbox(show_label=False)
                 query = gr.Textbox(show_label=False, lines=8)
                 submit_btn = gr.Button(variant="primary")
 
@@ -31,7 +31,7 @@ def create_chat_box(
 
     submit_btn.click(
         chat_model.predict,
-        [chatbot, query, history, prefix, max_new_tokens, top_p, temperature],
+        [chatbot, query, history, system, max_new_tokens, top_p, temperature],
         [chatbot, history],
         show_progress=True
     ).then(
@@ -41,7 +41,7 @@ def create_chat_box(
     clear_btn.click(lambda: ([], []), outputs=[chatbot, history], show_progress=True)
 
     return chat_box, chatbot, history, dict(
-        prefix=prefix,
+        system=system,
         query=query,
         submit_btn=submit_btn,
         clear_btn=clear_btn,

src/llmtuner/webui/components/eval.py

@@ -14,13 +14,13 @@ def create_eval_tab(top_elems: Dict[str, "Component"], runner: "Runner") -> Dict
     with gr.Row():
         dataset_dir = gr.Textbox(value=DEFAULT_DATA_DIR, scale=2)
         dataset = gr.Dropdown(multiselect=True, scale=4)
-        preview_btn = gr.Button(interactive=False, scale=1)
+        data_preview_btn = gr.Button(interactive=False, scale=1)
 
     preview_box, preview_count, preview_samples, close_btn = create_preview_box()
 
     dataset_dir.change(list_dataset, [dataset_dir], [dataset])
-    dataset.change(can_preview, [dataset_dir, dataset], [preview_btn])
-    preview_btn.click(
+    dataset.change(can_preview, [dataset_dir, dataset], [data_preview_btn])
+    data_preview_btn.click(
         get_preview,
         [dataset_dir, dataset],
         [preview_count, preview_samples, preview_box],
@@ -35,6 +35,7 @@ def create_eval_tab(top_elems: Dict[str, "Component"], runner: "Runner") -> Dict
         predict = gr.Checkbox(value=True)
 
     with gr.Row():
+        cmd_preview_btn = gr.Button()
         start_btn = gr.Button()
         stop_btn = gr.Button()
 
@@ -44,16 +45,14 @@ def create_eval_tab(top_elems: Dict[str, "Component"], runner: "Runner") -> Dict
     with gr.Box():
         output_box = gr.Markdown()
 
-    start_btn.click(
-        runner.run_eval,
-        [
+    input_components = [
         top_elems["lang"],
         top_elems["model_name"],
         top_elems["checkpoints"],
         top_elems["finetuning_type"],
         top_elems["quantization_bit"],
         top_elems["template"],
-            top_elems["source_prefix"],
+        top_elems["system_prompt"],
         dataset_dir,
         dataset,
         max_source_length,
@@ -61,18 +60,21 @@ def create_eval_tab(top_elems: Dict[str, "Component"], runner: "Runner") -> Dict
         max_samples,
         batch_size,
         predict
-        ],
-        [
+    ]
+
+    output_components = [
         output_box,
         process_bar
     ]
-    )
+
+    cmd_preview_btn.click(runner.preview_eval, input_components, output_components)
+    start_btn.click(runner.run_eval, input_components, output_components)
     stop_btn.click(runner.set_abort, queue=False)
 
     return dict(
         dataset_dir=dataset_dir,
         dataset=dataset,
-        preview_btn=preview_btn,
+        data_preview_btn=data_preview_btn,
         preview_count=preview_count,
         preview_samples=preview_samples,
         close_btn=close_btn,
@@ -81,6 +83,7 @@ def create_eval_tab(top_elems: Dict[str, "Component"], runner: "Runner") -> Dict
         max_samples=max_samples,
         batch_size=batch_size,
         predict=predict,
+        cmd_preview_btn=cmd_preview_btn,
         start_btn=start_btn,
         stop_btn=stop_btn,
         output_box=output_box

src/llmtuner/webui/components/infer.py

@@ -28,7 +28,7 @@ def create_infer_tab(top_elems: Dict[str, "Component"]) -> Dict[str, "Component"
             top_elems["finetuning_type"],
             top_elems["quantization_bit"],
             top_elems["template"],
-            top_elems["source_prefix"]
+            top_elems["system_prompt"]
         ],
         [info_box]
     ).then(

src/llmtuner/webui/components/top.py

@@ -4,7 +4,7 @@ import gradio as gr
 
 from llmtuner.extras.constants import METHODS, SUPPORTED_MODELS
 from llmtuner.extras.template import templates
-from llmtuner.webui.common import list_checkpoint, get_model_path, save_config
+from llmtuner.webui.common import list_checkpoint, get_model_path, get_template, save_config
 from llmtuner.webui.utils import can_quantize
 
 if TYPE_CHECKING:
@@ -15,27 +15,32 @@ def create_top() -> Dict[str, "Component"]:
     available_models = list(SUPPORTED_MODELS.keys()) + ["Custom"]
 
     with gr.Row():
-        lang = gr.Dropdown(choices=["en", "zh"], value="en", scale=1)
+        lang = gr.Dropdown(choices=["en", "zh"], scale=1)
         model_name = gr.Dropdown(choices=available_models, scale=3)
         model_path = gr.Textbox(scale=3)
 
     with gr.Row():
-        finetuning_type = gr.Dropdown(value="lora", choices=METHODS, scale=1)
+        finetuning_type = gr.Dropdown(choices=METHODS, value="lora", scale=1)
         checkpoints = gr.Dropdown(multiselect=True, scale=5)
         refresh_btn = gr.Button(scale=1)
 
     with gr.Accordion(label="Advanced config", open=False) as advanced_tab:
         with gr.Row():
-            quantization_bit = gr.Dropdown([8, 4], scale=1)
-            template = gr.Dropdown(value="default", choices=list(templates.keys()), scale=1)
-            source_prefix = gr.Textbox(scale=2)
+            quantization_bit = gr.Dropdown(choices=["None", "8", "4"], value="None", scale=1)
+            template = gr.Dropdown(choices=list(templates.keys()), value="default", scale=1)
+            system_prompt = gr.Textbox(scale=2)
+
+    lang.change(save_config, [lang, model_name, model_path])
 
     model_name.change(
         list_checkpoint, [model_name, finetuning_type], [checkpoints]
     ).then(
         get_model_path, [model_name], [model_path]
+    ).then(
+        get_template, [model_name], [template]
     ) # do not save config since the below line will save
-    model_path.change(save_config, [model_name, model_path])
+
+    model_path.change(save_config, [lang, model_name, model_path])
 
     finetuning_type.change(
         list_checkpoint, [model_name, finetuning_type], [checkpoints]
@@ -43,7 +48,9 @@ def create_top() -> Dict[str, "Component"]:
         can_quantize, [finetuning_type], [quantization_bit]
     )
 
-    refresh_btn.click(list_checkpoint, [model_name, finetuning_type], [checkpoints], queue=False)
+    refresh_btn.click(
+        list_checkpoint, [model_name, finetuning_type], [checkpoints], queue=False
+    )
 
     return dict(
         lang=lang,
@@ -55,5 +62,5 @@ def create_top() -> Dict[str, "Component"]:
         advanced_tab=advanced_tab,
         quantization_bit=quantization_bit,
         template=template,
-        source_prefix=source_prefix
+        system_prompt=system_prompt
     )

src/llmtuner/webui/components/train.py

@@ -3,7 +3,8 @@ from transformers.trainer_utils import SchedulerType
 
 import gradio as gr
 
-from llmtuner.webui.common import list_dataset, DEFAULT_DATA_DIR
+from llmtuner.extras.constants import STAGES
+from llmtuner.webui.common import list_checkpoint, list_dataset, DEFAULT_DATA_DIR
 from llmtuner.webui.components.data import create_preview_box
 from llmtuner.webui.utils import can_preview, get_preview, gen_plot
 
@@ -12,17 +13,18 @@ if TYPE_CHECKING:
     from llmtuner.webui.runner import Runner
 
 
-def create_sft_tab(top_elems: Dict[str, "Component"], runner: "Runner") -> Dict[str, "Component"]:
+def create_train_tab(top_elems: Dict[str, "Component"], runner: "Runner") -> Dict[str, "Component"]:
     with gr.Row():
+        training_stage = gr.Dropdown(choices=STAGES, value=STAGES[0], scale=2)
         dataset_dir = gr.Textbox(value=DEFAULT_DATA_DIR, scale=2)
         dataset = gr.Dropdown(multiselect=True, scale=4)
-        preview_btn = gr.Button(interactive=False, scale=1)
+        data_preview_btn = gr.Button(interactive=False, scale=1)
 
     preview_box, preview_count, preview_samples, close_btn = create_preview_box()
 
     dataset_dir.change(list_dataset, [dataset_dir], [dataset])
-    dataset.change(can_preview, [dataset_dir, dataset], [preview_btn])
-    preview_btn.click(
+    dataset.change(can_preview, [dataset_dir, dataset], [data_preview_btn])
+    data_preview_btn.click(
         get_preview,
         [dataset_dir, dataset],
         [preview_count, preview_samples, preview_box],
@@ -40,7 +42,7 @@ def create_sft_tab(top_elems: Dict[str, "Component"], runner: "Runner") -> Dict[
         batch_size = gr.Slider(value=4, minimum=1, maximum=512, step=1)
         gradient_accumulation_steps = gr.Slider(value=4, minimum=1, maximum=512, step=1)
         lr_scheduler_type = gr.Dropdown(
-            value="cosine", choices=[scheduler.value for scheduler in SchedulerType]
+            choices=[scheduler.value for scheduler in SchedulerType], value="cosine"
         )
         max_grad_norm = gr.Textbox(value="1.0")
         val_size = gr.Slider(value=0, minimum=0, maximum=1, step=0.001)
@@ -60,7 +62,21 @@ def create_sft_tab(top_elems: Dict[str, "Component"], runner: "Runner") -> Dict[
             lora_target = gr.Textbox(scale=2)
             resume_lora_training = gr.Checkbox(value=True, scale=1)
 
+    with gr.Accordion(label="RLHF config", open=False) as rlhf_tab:
         with gr.Row():
+            dpo_beta = gr.Slider(value=0.1, minimum=0, maximum=1, step=0.01, scale=2)
+            reward_model = gr.Dropdown(scale=2)
+            refresh_btn = gr.Button(scale=1)
+
+    refresh_btn.click(
+        list_checkpoint,
+        [top_elems["model_name"], top_elems["finetuning_type"]],
+        [reward_model],
+        queue=False
+    )
+
+    with gr.Row():
+        cmd_preview_btn = gr.Button()
         start_btn = gr.Button()
         stop_btn = gr.Button()
 
@@ -78,16 +94,15 @@ def create_sft_tab(top_elems: Dict[str, "Component"], runner: "Runner") -> Dict[
         with gr.Column(scale=1):
             loss_viewer = gr.Plot()
 
-    start_btn.click(
-        runner.run_train,
-        [
+    input_components = [
         top_elems["lang"],
         top_elems["model_name"],
         top_elems["checkpoints"],
         top_elems["finetuning_type"],
         top_elems["quantization_bit"],
         top_elems["template"],
-            top_elems["source_prefix"],
+        top_elems["system_prompt"],
+        training_stage,
         dataset_dir,
         dataset,
         max_source_length,
@@ -109,13 +124,18 @@ def create_sft_tab(top_elems: Dict[str, "Component"], runner: "Runner") -> Dict[
         lora_dropout,
         lora_target,
         resume_lora_training,
+        dpo_beta,
+        reward_model,
         output_dir
-        ],
-        [
+    ]
+
+    output_components = [
         output_box,
         process_bar
     ]
-    )
+
+    cmd_preview_btn.click(runner.preview_train, input_components, output_components)
+    start_btn.click(runner.run_train, input_components, output_components)
     stop_btn.click(runner.set_abort, queue=False)
 
     process_bar.change(
@@ -123,9 +143,10 @@ def create_sft_tab(top_elems: Dict[str, "Component"], runner: "Runner") -> Dict[
     )
 
     return dict(
+        training_stage=training_stage,
         dataset_dir=dataset_dir,
         dataset=dataset,
-        preview_btn=preview_btn,
+        data_preview_btn=data_preview_btn,
         preview_count=preview_count,
         preview_samples=preview_samples,
         close_btn=close_btn,
@@ -150,6 +171,11 @@ def create_sft_tab(top_elems: Dict[str, "Component"], runner: "Runner") -> Dict[
         lora_dropout=lora_dropout,
         lora_target=lora_target,
         resume_lora_training=resume_lora_training,
+        rlhf_tab=rlhf_tab,
+        dpo_beta=dpo_beta,
+        reward_model=reward_model,
+        refresh_btn=refresh_btn,
+        cmd_preview_btn=cmd_preview_btn,
         start_btn=start_btn,
         stop_btn=stop_btn,
         output_dir=output_dir,

src/llmtuner/webui/interface.py

@@ -3,7 +3,7 @@ from transformers.utils.versions import require_version
 
 from llmtuner.webui.components import (
     create_top,
-    create_sft_tab,
+    create_train_tab,
     create_eval_tab,
     create_infer_tab,
     create_export_tab,
@@ -24,8 +24,8 @@ def create_ui() -> gr.Blocks:
     with gr.Blocks(title="Web Tuner", css=CSS) as demo:
         top_elems = create_top()
 
-        with gr.Tab("SFT"):
-            sft_elems = create_sft_tab(top_elems, runner)
+        with gr.Tab("Train"):
+            train_elems = create_train_tab(top_elems, runner)
 
         with gr.Tab("Evaluate"):
             eval_elems = create_eval_tab(top_elems, runner)
@@ -36,7 +36,7 @@ def create_ui() -> gr.Blocks:
         with gr.Tab("Export"):
             export_elems = create_export_tab(top_elems)
 
-        elem_list = [top_elems, sft_elems, eval_elems, infer_elems, export_elems]
+        elem_list = [top_elems, train_elems, eval_elems, infer_elems, export_elems]
         manager = Manager(elem_list)
 
         demo.load(
@@ -59,7 +59,7 @@ def create_web_demo() -> gr.Blocks:
     chat_model = WebChatModel(lazy_init=False)
 
     with gr.Blocks(title="Web Demo", css=CSS) as demo:
-        lang = gr.Dropdown(choices=["en", "zh"], value="en")
+        lang = gr.Dropdown(choices=["en", "zh"])
 
         _, _, _, chat_elems = create_chat_box(chat_model, visible=True)
 
@@ -67,7 +67,7 @@ def create_web_demo() -> gr.Blocks:
 
         demo.load(manager.gen_label, [lang], [lang] + list(chat_elems.values()))
 
-        lang.change(manager.gen_label, [lang], [lang] + list(chat_elems.values()), queue=False)
+        lang.select(manager.gen_label, [lang], [lang] + list(chat_elems.values()), queue=False)
 
     return demo
 

src/llmtuner/webui/locales.py

@@ -77,7 +77,7 @@ LOCALES = {
             "info": "构建提示词时使用的模板"
         }
     },
-    "source_prefix": {
+    "system_prompt": {
         "en": {
             "label": "System prompt (optional)",
             "info": "A sequence used as the default system prompt."
@@ -87,6 +87,16 @@ LOCALES = {
             "info": "默认使用的系统提示词"
         }
     },
+    "training_stage": {
+        "en": {
+            "label": "Stage",
+            "info": "The stage to perform in training."
+        },
+        "zh": {
+            "label": "训练阶段",
+            "info": "目前采用的训练方式。"
+        }
+    },
     "dataset_dir": {
         "en": {
             "label": "Data dir",
@@ -105,12 +115,12 @@ LOCALES = {
             "label": "数据集"
         }
     },
-    "preview_btn": {
+    "data_preview_btn": {
         "en": {
-            "value": "Preview"
+            "value": "Preview dataset"
         },
         "zh": {
-            "value": "预览"
+            "value": "预览数据集"
         }
     },
     "preview_count": {
@@ -335,6 +345,42 @@ LOCALES = {
             "info": "接着上次的 LoRA 权重训练或创建一个新的 LoRA 权重。"
         }
     },
+    "rlhf_tab": {
+        "en": {
+            "label": "RLHF configurations"
+        },
+        "zh": {
+            "label": "RLHF 参数设置"
+        }
+    },
+    "dpo_beta": {
+        "en": {
+            "label": "DPO beta",
+            "info": "Value of the beta parameter in the DPO loss."
+        },
+        "zh": {
+            "label": "DPO beta 参数",
+            "info": "DPO 损失函数中 beta 超参数大小。"
+        }
+    },
+    "reward_model": {
+        "en": {
+            "label": "Reward model",
+            "info": "Checkpoint of the reward model for PPO training."
+        },
+        "zh": {
+            "label": "奖励模型",
+            "info": "PPO 训练中奖励模型的断点路径。"
+        }
+    },
+    "cmd_preview_btn": {
+        "en": {
+            "value": "Preview command"
+        },
+        "zh": {
+            "value": "预览命令"
+        }
+    },
     "start_btn": {
         "en": {
             "value": "Start"
@@ -409,7 +455,7 @@ LOCALES = {
             "value": "模型未加载，请先加载模型。"
         }
     },
-    "prefix": {
+    "system": {
         "en": {
             "placeholder": "System prompt (optional)"
         },

src/llmtuner/webui/manager.py

@@ -12,12 +12,18 @@ class Manager:
     def __init__(self, elem_list: List[Dict[str, Component]]):
         self.elem_list = elem_list
 
-    def gen_refresh(self) -> Dict[str, Any]:
+    def gen_refresh(self, lang: str) -> Dict[str, Any]:
         refresh_dict = {
             "dataset": {"choices": list_dataset()["choices"]},
             "output_dir": {"value": get_time()}
         }
+
         user_config = load_config()
+        if lang:
+            refresh_dict["lang"] = {"value": lang}
+        else:
+            refresh_dict["lang"] = {"value": user_config["lang"] if user_config["lang"] else "en"}
+
         if user_config["last_model"]:
             refresh_dict["model_name"] = {"value": user_config["last_model"]}
             refresh_dict["model_path"] = {"value": get_model_path(user_config["last_model"])}
@@ -26,10 +32,12 @@ class Manager:
 
     def gen_label(self, lang: str) -> Dict[Component, Dict[str, Any]]: # cannot use TYPE_CHECKING
         update_dict = {}
-        refresh_dict = self.gen_refresh()
+        refresh_dict = self.gen_refresh(lang)
 
         for elems in self.elem_list:
             for name, component in elems.items():
-                update_dict[component] = gr.update(**LOCALES[name][lang], **refresh_dict.get(name, {}))
+                update_dict[component] = gr.update(
+                    **LOCALES[name][refresh_dict["lang"]["value"]], **refresh_dict.get(name, {})
+                )
 
         return update_dict

src/llmtuner/webui/runner.py

@@ -5,7 +5,7 @@ import threading
 import time
 import transformers
 from transformers.trainer import TRAINING_ARGS_NAME
-from typing import Generator, List, Tuple
+from typing import Any, Dict, Generator, List, Tuple
 
 from llmtuner.extras.callbacks import LogCallback
 from llmtuner.extras.constants import DEFAULT_MODULE
@@ -14,7 +14,7 @@ from llmtuner.extras.misc import torch_gc
 from llmtuner.tuner import run_exp
 from llmtuner.webui.common import get_model_path, get_save_dir
 from llmtuner.webui.locales import ALERTS
-from llmtuner.webui.utils import get_eval_results, update_process_bar
+from llmtuner.webui.utils import gen_cmd, get_eval_results, update_process_bar
 
 
 class Runner:
@@ -22,39 +22,36 @@ class Runner:
     def __init__(self):
         self.aborted = False
         self.running = False
+        self.logger_handler = LoggerHandler()
+        self.logger_handler.setLevel(logging.INFO)
+        logging.root.addHandler(self.logger_handler)
+        transformers.logging.add_handler(self.logger_handler)
 
     def set_abort(self):
         self.aborted = True
         self.running = False
 
-    def initialize(
+    def _initialize(
         self, lang: str, model_name: str, dataset: List[str]
-    ) -> Tuple[str, str, LoggerHandler, LogCallback]:
+    ) -> str:
         if self.running:
-            return None, ALERTS["err_conflict"][lang], None, None
+            return ALERTS["err_conflict"][lang]
 
         if not model_name:
-            return None, ALERTS["err_no_model"][lang], None, None
+            return ALERTS["err_no_model"][lang]
 
-        model_name_or_path = get_model_path(model_name)
-        if not model_name_or_path:
-            return None, ALERTS["err_no_path"][lang], None, None
+        if not get_model_path(model_name):
+            return ALERTS["err_no_path"][lang]
 
         if len(dataset) == 0:
-            return None, ALERTS["err_no_dataset"][lang], None, None
+            return ALERTS["err_no_dataset"][lang]
 
         self.aborted = False
-        self.running = True
+        self.logger_handler.reset()
+        self.trainer_callback = LogCallback(self)
+        return ""
 
-        logger_handler = LoggerHandler()
-        logger_handler.setLevel(logging.INFO)
-        logging.root.addHandler(logger_handler)
-        transformers.logging.add_handler(logger_handler)
-        trainer_callback = LogCallback(self)
-
-        return model_name_or_path, "", logger_handler, trainer_callback
-
-    def finalize(
+    def _finalize(
         self, lang: str, finish_info: str
     ) -> str:
         self.running = False
@@ -64,7 +61,7 @@ class Runner:
         else:
             return finish_info
 
-    def run_train(
+    def _parse_train_args(
         self,
         lang: str,
         model_name: str,
@@ -72,7 +69,8 @@ class Runner:
         finetuning_type: str,
         quantization_bit: str,
         template: str,
-        source_prefix: str,
+        system_prompt: str,
+        training_stage: str,
         dataset_dir: str,
         dataset: List[str],
         max_source_length: int,
@@ -94,16 +92,13 @@ class Runner:
         lora_dropout: float,
         lora_target: str,
         resume_lora_training: bool,
+        dpo_beta: float,
+        reward_model: str,
         output_dir: str
-    ) -> Generator[str, None, None]:
-        model_name_or_path, error, logger_handler, trainer_callback = self.initialize(lang, model_name, dataset)
-        if error:
-            yield error, gr.update(visible=False)
-            return
-
+    ) -> Tuple[str, str, List[str], str, Dict[str, Any]]:
         if checkpoints:
             checkpoint_dir = ",".join(
-                [os.path.join(get_save_dir(model_name), finetuning_type, checkpoint) for checkpoint in checkpoints]
+                [os.path.join(get_save_dir(model_name), finetuning_type, ckpt) for ckpt in checkpoints]
             )
         else:
             checkpoint_dir = None
@@ -112,14 +107,14 @@ class Runner:
 
         args = dict(
             stage="sft",
-            model_name_or_path=model_name_or_path,
+            model_name_or_path=get_model_path(model_name),
             do_train=True,
             overwrite_cache=True,
             checkpoint_dir=checkpoint_dir,
             finetuning_type=finetuning_type,
-            quantization_bit=int(quantization_bit) if quantization_bit else None,
+            quantization_bit=int(quantization_bit) if quantization_bit != "None" else None,
             template=template,
-            source_prefix=source_prefix,
+            system_prompt=system_prompt,
             dataset_dir=dataset_dir,
             dataset=",".join(dataset),
             max_source_length=max_source_length,
@@ -134,8 +129,6 @@ class Runner:
             logging_steps=logging_steps,
             save_steps=save_steps,
             warmup_steps=warmup_steps,
-            fp16=(compute_type == "fp16"),
-            bf16=(compute_type == "bf16"),
             padding_side=padding_side,
             lora_rank=lora_rank,
             lora_dropout=lora_dropout,
@@ -143,6 +136,23 @@ class Runner:
             resume_lora_training=resume_lora_training,
             output_dir=output_dir
         )
+        args[compute_type] = True
+
+        if training_stage == "Reward Modeling":
+            args["stage"] = "rm"
+            args["resume_lora_training"] = False
+        elif training_stage == "PPO":
+            args["stage"] = "ppo"
+            args["resume_lora_training"] = False
+            args["reward_model"] = reward_model
+            args["padding_side"] = "left"
+            val_size = 0
+        elif training_stage == "DPO":
+            args["stage"] = "dpo"
+            args["resume_lora_training"] = False
+            args["dpo_beta"] = dpo_beta
+        elif training_stage == "Pre-Training":
+            args["stage"] = "pt"
 
         if val_size > 1e-6:
             args["val_size"] = val_size
@@ -150,25 +160,9 @@ class Runner:
             args["eval_steps"] = save_steps
             args["load_best_model_at_end"] = True
 
-        run_kwargs = dict(args=args, callbacks=[trainer_callback])
-        thread = threading.Thread(target=run_exp, kwargs=run_kwargs)
-        thread.start()
+        return lang, model_name, dataset, output_dir, args
 
-        while thread.is_alive():
-            time.sleep(2)
-            if self.aborted:
-                yield ALERTS["info_aborting"][lang], gr.update(visible=False)
-            else:
-                yield logger_handler.log, update_process_bar(trainer_callback)
-
-        if os.path.exists(os.path.join(output_dir, TRAINING_ARGS_NAME)):
-            finish_info = ALERTS["info_finished"][lang]
-        else:
-            finish_info = ALERTS["err_failed"][lang]
-
-        yield self.finalize(lang, finish_info), gr.update(visible=False)
-
-    def run_eval(
+    def _parse_eval_args(
         self,
         lang: str,
         model_name: str,
@@ -176,7 +170,7 @@ class Runner:
         finetuning_type: str,
         quantization_bit: str,
         template: str,
-        source_prefix: str,
+        system_prompt: str,
         dataset_dir: str,
         dataset: List[str],
         max_source_length: int,
@@ -184,12 +178,7 @@ class Runner:
         max_samples: str,
         batch_size: int,
         predict: bool
-    ) -> Generator[str, None, None]:
-        model_name_or_path, error, logger_handler, trainer_callback = self.initialize(lang, model_name, dataset)
-        if error:
-            yield error, gr.update(visible=False)
-            return
-
+    ) -> Tuple[str, str, List[str], str, Dict[str, Any]]:
         if checkpoints:
             checkpoint_dir = ",".join(
                 [os.path.join(get_save_dir(model_name), finetuning_type, checkpoint) for checkpoint in checkpoints]
@@ -201,15 +190,15 @@ class Runner:
 
         args = dict(
             stage="sft",
-            model_name_or_path=model_name_or_path,
+            model_name_or_path=get_model_path(model_name),
             do_eval=True,
             overwrite_cache=True,
             predict_with_generate=True,
             checkpoint_dir=checkpoint_dir,
             finetuning_type=finetuning_type,
-            quantization_bit=int(quantization_bit) if quantization_bit else None,
+            quantization_bit=int(quantization_bit) if quantization_bit != "None" else None,
             template=template,
-            source_prefix=source_prefix,
+            system_prompt=system_prompt,
             dataset_dir=dataset_dir,
             dataset=",".join(dataset),
             max_source_length=max_source_length,
@@ -223,7 +212,33 @@ class Runner:
             args.pop("do_eval", None)
             args["do_predict"] = True
 
-        run_kwargs = dict(args=args, callbacks=[trainer_callback])
+        return lang, model_name, dataset, output_dir, args
+
+    def preview_train(self, *args) -> Generator[Tuple[str, Dict[str, Any]], None, None]:
+        lang, model_name, dataset, _, args = self._parse_train_args(*args)
+        error = self._initialize(lang, model_name, dataset)
+        if error:
+            yield error, gr.update(visible=False)
+        else:
+            yield gen_cmd(args), gr.update(visible=False)
+
+    def preview_eval(self, *args) -> Generator[Tuple[str, Dict[str, Any]], None, None]:
+        lang, model_name, dataset, _, args = self._parse_eval_args(*args)
+        error = self._initialize(lang, model_name, dataset)
+        if error:
+            yield error, gr.update(visible=False)
+        else:
+            yield gen_cmd(args), gr.update(visible=False)
+
+    def run_train(self, *args) -> Generator[Tuple[str, Dict[str, Any]], None, None]:
+        lang, model_name, dataset, output_dir, args = self._parse_train_args(*args)
+        error = self._initialize(lang, model_name, dataset)
+        if error:
+            yield error, gr.update(visible=False)
+            return
+
+        self.running = True
+        run_kwargs = dict(args=args, callbacks=[self.trainer_callback])
         thread = threading.Thread(target=run_exp, kwargs=run_kwargs)
         thread.start()
 
@@ -232,11 +247,37 @@ class Runner:
             if self.aborted:
                 yield ALERTS["info_aborting"][lang], gr.update(visible=False)
             else:
-                yield logger_handler.log, update_process_bar(trainer_callback)
+                yield self.logger_handler.log, update_process_bar(self.trainer_callback)
+
+        if os.path.exists(os.path.join(output_dir, TRAINING_ARGS_NAME)):
+            finish_info = ALERTS["info_finished"][lang]
+        else:
+            finish_info = ALERTS["err_failed"][lang]
+
+        yield self._finalize(lang, finish_info), gr.update(visible=False)
+
+    def run_eval(self, *args) -> Generator[str, None, None]:
+        lang, model_name, dataset, output_dir, args = self._parse_eval_args(*args)
+        error = self._initialize(lang, model_name, dataset)
+        if error:
+            yield error, gr.update(visible=False)
+            return
+
+        self.running = True
+        run_kwargs = dict(args=args, callbacks=[self.trainer_callback])
+        thread = threading.Thread(target=run_exp, kwargs=run_kwargs)
+        thread.start()
+
+        while thread.is_alive():
+            time.sleep(2)
+            if self.aborted:
+                yield ALERTS["info_aborting"][lang], gr.update(visible=False)
+            else:
+                yield self.logger_handler.log, update_process_bar(self.trainer_callback)
 
         if os.path.exists(os.path.join(output_dir, "all_results.json")):
             finish_info = get_eval_results(os.path.join(output_dir, "all_results.json"))
         else:
             finish_info = ALERTS["err_failed"][lang]
 
-        yield self.finalize(lang, finish_info), gr.update(visible=False)
+        yield self._finalize(lang, finish_info), gr.update(visible=False)

src/llmtuner/webui/utils.py

@@ -62,6 +62,18 @@ def can_quantize(finetuning_type: str) -> Dict[str, Any]:
         return gr.update(interactive=True)
 
 
+def gen_cmd(args: Dict[str, Any]) -> str:
+    if args.get("do_train", None):
+        args["plot_loss"] = True
+    cmd_lines = ["CUDA_VISIBLE_DEVICES=0 python "]
+    for k, v in args.items():
+        if v is not None and v != "":
+            cmd_lines.append("    --{} {} ".format(k, str(v)))
+    cmd_text = "\\\n".join(cmd_lines)
+    cmd_text = "```bash\n{}\n```".format(cmd_text)
+    return cmd_text
+
+
 def get_eval_results(path: os.PathLike) -> str:
     with open(path, "r", encoding="utf-8") as f:
         result = json.dumps(json.load(f), indent=4)