README.md

---
base_model: Qwen/Qwen2.5-Math-7B-Instruct
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct/blob/main/LICENSE
model_creator: Qwen
model_name: Qwen2.5-Math-7B-Instruct
quantized_by: Second State Inc.
language:
- en
pipeline_tag: text-generation
library_name: transformers
tags:
- code
- codeqwen
- chat
- qwen
- qwen-coder
---

<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->

# Qwen2.5-Math-7B-Instruct-GGUF

## Original Model

[Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct)

## Run with LlamaEdge

- LlamaEdge version: coming soon

<!-- - LlamaEdge version: [v0.14.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.3) -->

<!-- - Prompt template

  - Prompt type: `qwen-2.5-coder`

  - Prompt string
 
    - File-Level Code Completion (Fill in the middle)

      ```text
      <|fim_prefix|>{prefix_code}<|fim_suffix|>{suffix_code}<|fim_middle|>
      ```
 
      *Reference: https://github.com/QwenLM/Qwen2.5-Coder?tab=readme-ov-file#3-file-level-code-completion-fill-in-the-middle*

    - Repository-Level Code Completion
   
      ```text
      <|repo_name|>{repo_name}
      <|file_sep|>{file_path1} 
      {file_content1}
      <|file_sep|>{file_path2} 
      {file_content2}
      ```

      *Reference: https://github.com/QwenLM/Qwen2.5-Coder?tab=readme-ov-file#4-repository-level-code-completion*

- Context size: `128000`

- Run as LlamaEdge service

  ```bash
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-Math-7B-Instruct-Q5_K_M.gguf \
    llama-api-server.wasm \
    --model-name Qwen2.5-Math-7B-Instruct \
    --prompt-template qwen-2.5-coder \
    --ctx-size 128000
  ```

- Run as LlamaEdge command app

  ```bash
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-Math-7B-Instruct-Q5_K_M.gguf \
    llama-chat.wasm \
    --prompt-template qwen-2.5-coder \
    --ctx-size 128000
  ``` -->

## Quantized GGUF Models

| Name | Quant method | Bits | Size | Use case |
| ---- | ---- | ---- | ---- | ----- |
| [Qwen2.5-Math-7B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q2_K.gguf)     | Q2_K   | 2 | 3.02 GB| smallest, significant quality loss - not recommended for most purposes |
| [Qwen2.5-Math-7B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 4.09 GB| small, substantial quality loss |
| [Qwen2.5-Math-7B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 3.81 GB| very small, high quality loss |
| [Qwen2.5-Math-7B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 3.49 GB| very small, high quality loss |
| [Qwen2.5-Math-7B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q4_0.gguf)     | Q4_0   | 4 | 4.43 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
| [Qwen2.5-Math-7B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 4.68 GB| medium, balanced quality - recommended |
| [Qwen2.5-Math-7B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 4.46 GB| small, greater quality loss |
| [Qwen2.5-Math-7B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q5_0.gguf)     | Q5_0   | 5 | 5.32 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
| [Qwen2.5-Math-7B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 5.44 GB| large, very low quality loss - recommended |
| [Qwen2.5-Math-7B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 5.32 GB| large, low quality loss - recommended |
| [Qwen2.5-Math-7B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q6_K.gguf)     | Q6_K   | 6 | 6.25 GB| very large, extremely low quality loss |
| [Qwen2.5-Math-7B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q8_0.gguf)     | Q8_0   | 8 | 8.21 GB| very large, extremely low quality loss - not recommended |
| [Qwen2.5-Math-7B-Instruct-f16.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-f16.gguf)       | f16    | 16 | 15.2 GB| |

*Quantized with llama.cpp b3751*