/LLMBox

A comprehensive library for implementing LLMs, including a unified training pipeline and comprehensive model evaluation.

Primary LanguagePythonMIT LicenseMIT

LLMBox | Training | Utilization

LLMBox

LLMBox is a comprehensive library for implementing LLMs, including a unified training pipeline and comprehensive model evaluation. LLMBox is designed to be a one-stop solution for training and utilizing LLMs. Through a pratical library design, we achieve a high-level of flexibility and efficiency in both training and utilization stages.

Key Features

Training

  • Diverse training strategies: We support multiple training strategies, including Supervised Fine-tuning (SFT), Pre-training (PT), PPO and DPO.
  • Comprehensive SFT datasets: We support 9 SFT datasets as the inputs for training.
  • Tokenizer Vocabulary Merging: We support the tokenizer merging function to expand the vocabulary.
  • Data Construction Strategies: We currently support merging multiple datasets for training. Self-Instruct and Evol-Instruct are also available to process the dataset.
  • Parameter Efficient Fine-Tuning: LoRA and QLoRA are supported in SFT or PT.
  • Efficient Training: We support Flash Attention and Deepspeed for efficient training.

Utilization

  • Comprehensive Evaluation: 56+ commonly used datasets and benchmarks in evaluating LLMs.
  • Evaluation Methods: Accurately reproduce results from original papers of OpenAI, LLaMA, Mistral, and other models.
  • In-Context Learning: We support various ICL strategies, including KATE, GlobalE, and APE.
  • Chain-of-Thought: For some datasets, we support three types of CoT evaluation: base, least-to-most, and pal.
  • Prefix Caching: By managing the KV Cache of prefixes, we can speed up local inference by up to 6x.
  • vLLM and Flash Attention Support: We also support vLLM and Flash Attention for efficient inference.
  • Quantization: BitsAndBytes and GPTQ quantization are supported.

Quick Start

Install

git clone https://github.com/RUCAIBox/LLMBox.git && cd LLMBox
pip install -r requirements.txt

If you are only evaluating the OpenAI (or OpenAI compatible like DeepSeek, Perplexity) models, you can install the minimal requirements requirements-openai.txt.

For installation problem, see trouble shooting.

Quick Start with Training

You can start with training a SFT model based on LLaMA-2 (7B) with deepspeed3:

cd training
bash download.sh
bash bash/run_7b_ds3.sh

Quick Start with Utilization

To utilize your model, or evaluate an existing model, you can run the following command:

python inference.py -m gpt-3.5-turbo -d copa  # --num_shot 0 --model_type chat

This is default to run the OpenAI GPT 3.5 turbo model on the CoPA dataset in a zero-shot manner.

Training

LLMBox Training supports various training strategies and dataset construction strategies, along with some efficiency-improving modules. You can train your model with the following command:

python train.py \
    --model_name_or_path meta-llama/Llama-2-7b-hf \
    --data_path data/ \
    --dataset alpaca_data_1k.json \
    --output_dir $OUTPUT_DIR \
    --num_train_epochs 2 \
    --per_device_train_batch_size 8 \
    --gradient_accumulation_steps 2 \
    --save_strategy "epoch" \
    --save_steps 2 \
    --save_total_limit 2 \
    --learning_rate 1e-5 \
    --lr_scheduler_type "constant"

Alternatively, you can use the following preset bash scripts to train your model:

Merging Tokenizer

If you want to pre-train your models on corpora with languages or tokens not well-supported in original language mdoels(e.g., LLaMA), we provide the tokenizer merging function to expand the vocabulary based on the corpora by using sentencepiece. You can check merge_tokenizer.py for detailed information. Please follow the guide in Pre-train.

bash bash/run_7b_pt.sh

Merging Datasets

If you want to train your models with a mix of multiple datasets, you can pass a list of dataset files or names to LLMBox. LLMBox will transfer each file or name into a PTDataset or SFTDataset, and merge them together to construct a combined dataset. You can also set the merging ratio of each dataset by passing a list of floats to LLMBox. Please follow the guide in Merge Dataset.

bash bash/run_7b_hybrid.sh

Self-Instruct and Evol-Instruct

Since manually creating instruction data of high qualities to train the model is very time-consuming and labor-intensive, Self-Instruct and Evol-Instruct are proposed to create large amounts of instruction data with varying levels of complexity using LLM instead of humans. LLMBox support both Self-Instruct and Evol-Instruct to augment or enhance the input data files. Please follow the guide in Self-Insturct and Evol-Instruct

python self_instruct/self_instruct.py --seed_tasks_path=seed_tasks.jsonl

For more details, view the training documentation.

Utilization

We provide a broad support on Huggingface models (e.g. LLaMA-3, Mistral, or the model you are building on), OpenAI, Anthropic, QWen and other OpenAI-compatible models for further utilization.

Currently a total of 56+ commonly used datasets are supported, including: HellaSwag, MMLU, GSM8K, GPQA, AGIEval, CEval, and CMMLU. For a full list of supported models and datasets, view the utilization documentation.

CUDA_VISIBLE_DEVICES=0 python inference.py \
  -m llama-2-7b-hf \
  -d mmlu agieval:[English] \
  --model_type chat \
  --num_shot 5 \
  --ranking_type ppl_no_option
Performance
Model get_ppl get_prob generation
Hellaswag (0-shot) MMLU (5-shot) GSM (8-shot)
GPT-3.5 Turbo 79.98 69.25 75.13
LLaMA-2 (7B) 76 45.95 14.63

Efficient Evaluation

We by default enable prefix caching for efficient evaluation. vLLM is also supported.

Time
Model Efficient Method get_ppl get_prob generation
Hellaswag (0-shot) MMLU (5-shot) GSM (8-shot)
LLaMA-2 (7B) Vanilla 0:05:32 0:18:30 2:10:27
vLLM 0:06:37 0:14:55 0:03:36
Prefix Caching 0:05:48 0:05:51 0:17:13

You can also use the following command to use vllm:

python inference.py -m ../Llama-2-7b-hf -d mmlu:abstract_algebra,anatomy --vllm True  # --prefix_caching False --flash_attention False

To evaluate with quantization, you can use the following command:

python inference.py -m model -d dataset --load_in_4bits  # --load_in_8_bits or --gptq

Evaluation Method

Various types of evaluation methods are supported:

Dataset Evaluation Method Variants (Ranking Type)
GenerationDataset generation
MultipleChoiceDataset get_ppl ppl_no_option, ppl
get_prob prob

By default, we use the get_ppl method with ppl_no_option ranking type for MultipleChoiceDataset and the generation method for GenerationDataset. You can also use the following command to use the get_prob method or ppl variant of get_ppl for MultipleChoiceDataset:

python inference.py -m model -d dataset --ranking_type prob  # or ppl

We also support In-Context Learning and Chain-of-Thought evaluation for some datasets:

python inference.py -m model -d dataset --kate  # --globale or --ape
python inference.py -m model -d dataset --cot least_to_most  # --base or --pal

For a more detailed instruction on model utilization, view the utilization documentation.

Contributing

Please let us know if you encounter a bug or have any suggestions by filing an issue.

We welcome all contributions from bug fixes to new features and extensions.

We expect all contributions discussed in the issue tracker and going through PRs.

You can follow model customization and dataset customization to add new model provider or dataset.

Make sure to format your code with yapf --style .style.cfg and isort before submitting a PR.

The Team

LLMBox is developed and maintained by AI Box. See more details in change log

License

LLMBox uses MIT License.

Reference

If you find LLMBox useful for your research or development, please cite the following papers: