update readme
This commit is contained in:
hiyouga
parent
1836c020c5
commit
2618e0b5a7
52
README.md
52
README.md
|
|
@ -18,17 +18,17 @@
|
|||
|
||||
[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.
|
||||
|
||||
|
|
@ -72,6 +72,8 @@
|
|||
| PPO Training | | | ✅ | ✅ |
|
||||
| DPO Training | ✅ | | ✅ | ✅ |
|
||||
|
||||
- Use `--quantization_bit 4/8` argument to enable QLoRA.
|
||||
|
||||
## Provided Datasets
|
||||
|
||||
- For pre-training:
|
||||
|
|
@ -204,8 +206,6 @@ 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
|
||||
|
||||
```bash
|
||||
|
|
@ -280,12 +280,14 @@ 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
|
||||
|
|
@ -313,6 +315,44 @@ 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>
|
||||
|
||||
### Evaluation (BLEU and ROUGE_CHINESE)
|
||||
|
||||
```bash
|
||||
|
|
|
|||
64
README_zh.md
64
README_zh.md
|
|
@ -16,31 +16,31 @@
|
|||
|
||||
[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**一体化浏览器界面**。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。
|
||||
|
||||
|
|
@ -71,6 +71,8 @@
|
|||
| PPO 训练 | | | ✅ | ✅ |
|
||||
| DPO 训练 | ✅ | | ✅ | ✅ |
|
||||
|
||||
- 使用 `--quantization_bit 4/8` 参数来启用 QLoRA 训练。
|
||||
|
||||
## 数据集
|
||||
|
||||
- 用于预训练：
|
||||
|
|
@ -203,8 +205,6 @@ 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
|
||||
|
||||
```bash
|
||||
|
|
@ -279,6 +279,8 @@ 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
|
||||
|
|
@ -312,7 +314,43 @@ use_cpu: false
|
|||
|
||||
</details>
|
||||
|
||||
### 指标评估（BLEU分数和汉语ROUGE分数）
|
||||
#### 使用 DeepSpeed
|
||||
|
||||
```bash
|
||||
deepspeed --num_gpus 8 --master_port=9901 src/train_bash.py --deepspeed ds_config.json ... # 参数同上
|
||||
```
|
||||
|
||||
<details><summary>使用 DeepSpeed ZeRO-2 进行全参数微调的 DeepSpeed 配置示例</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>
|
||||
|
||||
### 指标评估（BLEU 分数和汉语 ROUGE 分数）
|
||||
|
||||
```bash
|
||||
CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
|
||||
|
|
@ -329,7 +367,7 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
|
|||
--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` 参数。
|
||||
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
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue