---
license: apache-2.0
model-index:
- name: Yi-1.5-9B
  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: 61.86
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=01-ai/Yi-1.5-9B
      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: 80.37
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=01-ai/Yi-1.5-9B
      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: 70.73
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=01-ai/Yi-1.5-9B
      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: 46.74
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=01-ai/Yi-1.5-9B
      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: 77.98
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=01-ai/Yi-1.5-9B
      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: 62.7
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=01-ai/Yi-1.5-9B
      name: Open LLM Leaderboard
---
<div align="center">

<picture> 
  <img src="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg" width="150px">
</picture>

</div>

<p align="center">
  <a href="https://github.com/01-ai">🐙 GitHub</a> •
  <a href="https://discord.gg/hYUwWddeAu">👾 Discord</a> •
  <a href="https://twitter.com/01ai_yi">🐤 Twitter</a> •
  <a href="https://github.com/01-ai/Yi-1.5/issues/2">💬 WeChat</a> 
  <br/>
  <a href="https://arxiv.org/abs/2403.04652">📝 Paper</a> •
  <a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#faq">🙌 FAQ</a> •
  <a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#learning-hub">📗 Learning Hub</a>
</p>

# Intro

Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples. 

Compared with Yi, Yi-1.5 delivers stronger performance in coding, math, reasoning, and instruction-following capability, while still maintaining excellent capabilities in language understanding, commonsense reasoning, and reading comprehension.

<div align="center">
  
Model | Context Length | Pre-trained Tokens
| :------------: | :------------: | :------------: |
| Yi-1.5 | 4K | 3.6T

</div>

# Models

- Chat models

  <div align="center">
  
  | Name            | Download                                                                                                                                                            |
  | --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
  | Yi-1.5-34B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
  | Yi-1.5-9B-Chat  | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
  | Yi-1.5-6B-Chat  | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
  
  </div>

- Base models

  <div align="center">
  
  | Name       | Download                                                                                                                                                            |
  | ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
  | Yi-1.5-34B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
  | Yi-1.5-9B  | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
  | Yi-1.5-6B  | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
  
  </div>

# Benchmarks

- Chat models

  Yi-1.5-34B-Chat is on par with or excels beyond larger models in most benchmarks.

  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/KcsJ9Oc1VnEmfCDEJc5cd.png)

  Yi-1.5-9B-Chat is the top performer among similarly sized open-source models.

  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/xf6pLg5jqRCwjlh6m3t6_.png)

- Base models

  Yi-1.5-34B is on par with or excels beyond larger models in some benchmarks.

  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/BwU7QM-03dZvZzwdIE1xY.png)

  Yi-1.5-9B is the top performer among similarly sized open-source models.

  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/y-EYSYPT-3aWLJ0x8R94F.png)

# Quick Start

For getting up and running with Yi-1.5 models quickly, see [README](https://github.com/01-ai/Yi-1.5).


# [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_01-ai__Yi-1.5-9B)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |66.73|
|AI2 Reasoning Challenge (25-Shot)|61.86|
|HellaSwag (10-Shot)              |80.37|
|MMLU (5-Shot)                    |70.73|
|TruthfulQA (0-shot)              |46.74|
|Winogrande (5-shot)              |77.98|
|GSM8k (5-shot)                   |62.70|