大模型训练,评估,推理,部署工具
Project description
📌 简介
osc-llm旨在成为一个简单易用的大模型训练、评估、推理、部署工具,支持主流的大模型。
文档地址:
📌 安装
- 安装最新版本pytorch
- 安装osc-llm:
pip install osc-llm
📌 快速开始
# 下面以llama3为例演示如何转换为osc-llm格式,并进行聊天。
# 假设你已经下载好huggingface的llama3模型在checkpoints/meta-llama目录下
# 1. 转换
llm convert --checkpoint_dir checkpoints/meta-llama/Meta-Llama-3-8B-Instruct
# 2. 量化
llm quantize int8 --checkpoint_dir checkpoints/meta-llama/Meta-Llama-3-8B-Instruct --save_dir checkpoints/meta-llama/Meta-Llama-3-8B-Instruct-int8
# 3. 聊天(使用编译功能加速推理速度,需要等待几分钟编译时间)
llm chat --checkpoint_dir checkpoints/meta-llama/Meta-Llama-3-8B-Instruct-int8 --compile true
# 4. 部署
llm serve --checkpoint_dir checkpoints/meta-llama/Meta-Llama-3-8B-Instruct-int8
📌 模型支持
以下huggingface中的模型结构(查看config.json)已经支持转换为osc-llm格式:
- LlamaForCausalLM: llama2, llama3, chinese-alpaca2等。
- Qwen2ForCausalLM: qwen1.5系列。
- Qwen2MoeForCausalLM: qwen2-moe系列(目前无法完成编译,推理速度很慢)。
致敬
本项目参考了大量的开源项目,特别是以下项目:
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
osc_llm-0.1.5.tar.gz
(35.7 kB
view details)
Built Distribution
osc_llm-0.1.5-py3-none-any.whl
(49.7 kB
view details)
File details
Details for the file osc_llm-0.1.5.tar.gz
.
File metadata
- Download URL: osc_llm-0.1.5.tar.gz
- Upload date:
- Size: 35.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.12.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 0c017e2aee2ef05bf9e132dc5f558e84d8dfdcc8194b0df1d2ddf244fb545a7e |
|
MD5 | 017e080a476f7ad6774c886430ddb4dd |
|
BLAKE2b-256 | 51f36861dd00c6af54d1cd99f59c6184b0e48260fc1f3fb36fbb02e29aa05650 |
File details
Details for the file osc_llm-0.1.5-py3-none-any.whl
.
File metadata
- Download URL: osc_llm-0.1.5-py3-none-any.whl
- Upload date:
- Size: 49.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.12.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | b87436b972a9811e47e63c25520c8e338031bd4f9c26a04174a1feff9c5f184d |
|
MD5 | 745aa2785c6bc8745f5fa3292f30db94 |
|
BLAKE2b-256 | caab260be1536d16ca2fd57840bcb3bb23d08e5c04eafc59adb81454b0387670 |