43 lines
895 B
Markdown
43 lines
895 B
Markdown
|
---
|
|||
|
|
base_model:
|
|||
|
|
- Qwen/Qwen2.5-7B-Instruct
|
|||
|
|
base_model_relation: finetune
|
|||
|
|
datasets:
|
|||
|
|
evaluation: null
|
|||
|
|
test: null
|
|||
|
|
train: null
|
|||
|
|
domain: null
|
|||
|
|
frameworks: other
|
|||
|
|
language:
|
|||
|
|
- zh
|
|||
|
|
- en
|
|||
|
|
license: Apache License 2.0
|
|||
|
|
models: null
|
|||
|
|
tags:
|
|||
|
|
- null
|
|||
|
|
tasks:
|
|||
|
|
- text-generation
|
|||
|
|
---
|
|||
|
|
#### Clone with HTTP
|
|||
|
|
```bash
|
|||
|
|
git clone https://www.modelscope.cn/studios/ysqlian/YZH_Model.git
|
|||
|
|
```
|
|||
|
|
#YZH-完整模型-Q4_K_M
|
|||
|
|
|
|||
|
|
这是一个使用 Qwen 架构，由我收集数据并从头训练（Pre-trained from Scratch）的语言模型。
|
|||
|
|
|
|||
|
|
本仓库提供的是经过 Q4_K_M 量化的 GGUF 版本，专为使用 llama.cpp 进行本地推理而设计。
|
|||
|
|
|
|||
|
|
“##模型详情”
|
|||
|
|
|
|||
|
|
量化格式：GGUF (Q4_K_M)
|
|||
|
|
参数量：8B
|
|||
|
|
语言：中文、英文
|
|||
|
|
##如何使用
|
|||
|
|
|
|||
|
|
你可以使用 llama.cpp 在本地运行此模型。
|
|||
|
|
|
|||
|
|
###命令行推理
|
|||
|
|
|
|||
|
|
./main -m YZH-Full-Model-Q4_K_M.gguf -p "你好，请介绍一下你自己。" -n 512 -c 8192
|