Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Documents Updates #2574

Merged
merged 13 commits into from
Dec 7, 2024
Prev Previous commit
Next Next commit
Rename Supported-models-datasets.md to s-m-a-d
  • Loading branch information
yrk111222 committed Dec 6, 2024
commit a17ebf1f33fd678090023acc4ec30b8f02a32db3
4 changes: 2 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -155,7 +155,7 @@ You can contact us and communicate with us by adding our group:
- 🔥2024.04.11: Support Model Evaluation with MMLU/ARC/CEval datasets(also user custom eval datasets) with one command! Check [this documentation](docs/source_en/Instruction/LLM-eval.md) for details. Meanwhile, we support a trick way to do multiple ablation experiments, check [this documentation](docs/source_en/Instruction/LLM-exp.md) to use.
- 🔥2024.04.11: Support **c4ai-command-r** series: c4ai-command-r-plus, c4ai-command-r-v01, use [this script](https://github.com/modelscope/swift/blob/main/examples/pytorch/llm/scripts/c4ai_command_r_plus/lora_mp/sft.sh) to train.
- 2024.04.10: Use SWIFT to fine-tune the qwen-7b-chat model to enhance its function call capabilities, and combine it with [Modelscope-Agent](https://github.com/modelscope/modelscope-agent) for best practices, which can be found [here](https://github.com/modelscope/swift/tree/main/docs/source_en/LLM/Agent-best-practice.md#Usage-with-Modelscope_Agent).
- 🔥2024.04.09: Support ruozhiba dataset. Search `ruozhiba` in [this documentation](docs/source_en/Instruction/Supported-models-datasets.md) to begin training!
- 🔥2024.04.09: Support ruozhiba dataset. Search `ruozhiba` in [this documentation](docs/source_en/Instruction/Supported-models-and-datasets) to begin training!
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

检查链接是否正确

- 2024.04.08: Support the fine-tuning and inference of XVERSE-MoE-A4.2B model, use [this script](https://github.com/modelscope/swift/blob/main/examples/pytorch/llm/scripts/xverse_moe_a4_2b/lora/sft.sh) to start training!
- 2024.04.04: Support **QLoRA+FSDP** to train a 70B model with two 24G memory GPUs, use [this script](https://github.com/modelscope/swift/blob/main/examples/pytorch/llm/scripts/llama2_70b_chat/qlora_fsdp/sft.sh) to train.
- 🔥2024.04.03: Support **Qwen1.5-32B** series: Qwen1.5-32B, Qwen1.5-32B-Chat, Qwen1.5-32B-Chat-GPTQ-Int4.use [this script](https://github.com/modelscope/swift/blob/main/examples/pytorch/llm/scripts/qwen1half_32b_chat/lora_mp/sft.sh) to start training!
Expand Down Expand Up @@ -586,7 +586,7 @@ CUDA_VISIBLE_DEVICES=0 swift deploy \
```

### Supported Models
The complete list of supported models and datasets can be found at [Supported Models and Datasets List](docs/source_en/Instruction/Supported-models-datasets.md).
The complete list of supported models and datasets can be found at [Supported Models and Datasets List](docs/source_en/Instruction/Supported-models-and-datasets.md).

#### LLMs

Expand Down
2 changes: 1 addition & 1 deletion docs/source_en/Instruction/Commend-line-parameters.md
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ The introduction to command line parameters will cover basic parameters, atomic

### Template Parameters

- 🔥template: Template type, default uses the corresponding template type of the model. If it is a custom model, please refer to [Supported Models and Datasets](./Supported-models-datasets.md) and manually input this field.
- 🔥template: Template type, default uses the corresponding template type of the model. If it is a custom model, please refer to [Supported Models and Datasets](./Supported-models-and-datasets) and manually input this field.
- 🔥system: Custom system field, default is None, uses the default system of the template.
- 🔥max_length: Maximum length of tokens for a single sample, default is None (no limit).
- truncation_strategy: How to handle overly long tokens, supports `delete` and `left`, representing deletion and left trimming, default is left.
Expand Down
Original file line number Diff line number Diff line change
@@ -1,4 +1,3 @@
<<<<<<< HEAD:docs/source_en/Instruction/Supported-models-datasets.md
# Supported models and datasets

## Models
Expand Down Expand Up @@ -1155,7 +1154,6 @@ The table below provides information about the datasets integrated with Swift:
- Dataset Size: Size of the subdata set
- Statistic: Statistics of the dataset. We use the number of tokens for statistics, which helps adjust the `max_length` hyperparameter. We concatenate the training and validation sets and then perform statistics. We use Qwen's tokenizer for tokenization. Different tokenizers produce different statistics. If you need token statistics for other models' tokenizers, you can obtain them yourself through [the script](https://github.com/modelscope/swift/tree/main/scripts/utils/run_dataset_info.py).
- Tags: Tags of the dataset
>>>>>>> e0e1aaa0 (Translation):docs/source_en/Instruction/Supported Models and Datasets.md


| Dataset ID | Subset name | Dataset Size | Statistic (token) | Tags | HF Dataset ID |
Expand Down
2 changes: 1 addition & 1 deletion scripts/utils/run_dataset_info.py
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,7 @@ def run_dataset(key, template, cache_mapping):


def write_dataset_info() -> None:
fpaths = ['docs/source/Instruction/支持的模型和数据集.md', 'docs/source_en/Instruction/Supported-models-datasets.md']
fpaths = ['docs/source/Instruction/支持的模型和数据集.md', 'docs/source_en/Instruction/Supported-models-and-datasets.md']
cache_mapping = get_cache_mapping(fpaths[0])
res_text_list = []
res_text_list.append('| Dataset ID | Subset name | Dataset Size | Statistic (token) | Tags | HF Dataset ID |')
Expand Down
2 changes: 1 addition & 1 deletion scripts/utils/run_model_info.py
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@


def get_model_info_table():
fpaths = ['docs/source/Instruction/支持的模型和数据集.md', 'docs/source_en/Instruction/Supported-models-datasets.md']
fpaths = ['docs/source/Instruction/支持的模型和数据集.md', 'docs/source_en/Instruction/Supported-models-and-datasets.md']
end_words = [['### 多模态大模型', '## 数据集'], ['### MLLM', '## Datasets']]
result = [
'| Model ID | Model Type | Default Template | '
Expand Down