---
language:
- zh
- en
license: apache-2.0
model-index:
- name: chinese-alpaca-2-7b
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 49.57
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ziqingyang/chinese-alpaca-2-7b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 72.62
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ziqingyang/chinese-alpaca-2-7b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 46.5
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ziqingyang/chinese-alpaca-2-7b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 48.63
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ziqingyang/chinese-alpaca-2-7b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 70.01
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ziqingyang/chinese-alpaca-2-7b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 5.76
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ziqingyang/chinese-alpaca-2-7b
      name: Open LLM Leaderboard
---

# Chinese-Alpaca-2-7B

**This is the full Chinese-Alpaca-2-7B model，which can be loaded directly for inference and full-parameter training.**

**Related models👇**
* Long context base models
  * [Chinese-LLaMA-2-7B-16K (full model)](https://huggingface.co/hfl/chinese-llama-2-7b-16k)
  * [Chinese-LLaMA-2-LoRA-7B-16K (LoRA model)](https://huggingface.co/hfl/chinese-llama-2-lora-7b-16k)
  * [Chinese-LLaMA-2-13B-16K (full model)](https://huggingface.co/hfl/chinese-llama-2-13b-16k)
  * [Chinese-LLaMA-2-LoRA-13B-16K (LoRA model)](https://huggingface.co/hfl/chinese-llama-2-lora-13b-16k)
* Base models
  * [Chinese-LLaMA-2-7B (full model)](https://huggingface.co/hfl/chinese-llama-2-7b)
  * [Chinese-LLaMA-2-LoRA-7B (LoRA model)](https://huggingface.co/hfl/chinese-llama-2-lora-7b)
  * [Chinese-LLaMA-2-13B (full model)](https://huggingface.co/hfl/chinese-llama-2-13b)
  * [Chinese-LLaMA-2-LoRA-13B (LoRA model)](https://huggingface.co/hfl/chinese-llama-2-lora-13b)
* Instruction/Chat models
  * [Chinese-Alpaca-2-7B (full model)](https://huggingface.co/hfl/chinese-alpaca-2-7b)
  * [Chinese-Alpaca-2-LoRA-7B (LoRA model)](https://huggingface.co/hfl/chinese-alpaca-2-lora-7b)
  * [Chinese-Alpaca-2-13B (full model)](https://huggingface.co/hfl/chinese-alpaca-2-13b)
  * [Chinese-Alpaca-2-LoRA-13B (LoRA model)](https://huggingface.co/hfl/chinese-alpaca-2-lora-13b)


# Description of Chinese-LLaMA-Alpaca-2 
This project is based on the Llama-2, released by Meta, and it is the second generation of the Chinese LLaMA & Alpaca LLM project. We open-source Chinese LLaMA-2 (foundation model) and Alpaca-2 (instruction-following model). These models have been expanded and optimized with Chinese vocabulary beyond the original Llama-2. We used large-scale Chinese data for incremental pre-training, which further improved the fundamental semantic understanding of the Chinese language, resulting in a significant performance improvement compared to the first-generation models. The relevant models support a 4K context and can be expanded up to 18K+ using the NTK method.

The main contents of this project include:

* 🚀 New extended Chinese vocabulary beyond Llama-2, open-sourcing the Chinese LLaMA-2 and Alpaca-2 LLMs.
* 🚀 Open-sourced the pre-training and instruction finetuning (SFT) scripts for further tuning on user's data
* 🚀 Quickly deploy and experience the quantized LLMs on CPU/GPU of personal PC
* 🚀 Support for LLaMA ecosystems like 🤗transformers, llama.cpp, text-generation-webui, LangChain, vLLM etc.

Please refer to [https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/) for details.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ziqingyang__chinese-alpaca-2-7b)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |48.85|
|AI2 Reasoning Challenge (25-Shot)|49.57|
|HellaSwag (10-Shot)              |72.62|
|MMLU (5-Shot)                    |46.50|
|TruthfulQA (0-shot)              |48.63|
|Winogrande (5-shot)              |70.01|
|GSM8k (5-shot)                   | 5.76|