Instructions to use Invalid-Null/PeiYangMe-0.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Invalid-Null/PeiYangMe-0.6 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Invalid-Null/PeiYangMe-0.6")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Invalid-Null/PeiYangMe-0.6")
model = AutoModelForCausalLM.from_pretrained("Invalid-Null/PeiYangMe-0.6")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Invalid-Null/PeiYangMe-0.6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Invalid-Null/PeiYangMe-0.6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Invalid-Null/PeiYangMe-0.6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Invalid-Null/PeiYangMe-0.6

SGLang

How to use Invalid-Null/PeiYangMe-0.6 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Invalid-Null/PeiYangMe-0.6" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Invalid-Null/PeiYangMe-0.6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Invalid-Null/PeiYangMe-0.6" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Invalid-Null/PeiYangMe-0.6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Invalid-Null/PeiYangMe-0.6 with Docker Model Runner:
```
docker model run hf.co/Invalid-Null/PeiYangMe-0.6
```

A newer version of this model is available: Invalid-Null/PeiYangMe

北洋微衍V0.6/PeiYang MicroEmergence-0.6

模型曾用名 / Model Name History

此模型在开发过程中经历了以下命名阶段： This model has gone through the following naming stages during development:

早期阶段 / Initial Stage:
Invalid-Null/Non-Null
发展阶段 / Development Stage:
天津大学/北洋微衍 (Tianjin University/Peiyang MicroDerivation)
当前版本 / Current Release:
天津大学/北洋微衍 (Tianjin University/Peiyang MicroEmergence)

模型概述 / Model Overview

本模型专注于计算催化领域，特别是丙烷脱氢(PDH)过程。 This model focuses on computational catalysis, specifically designed for propane dehydrogenation (PDH) processes.

技术基础 / Technical Foundation

基础框架 / Base Framework:
基于ModelScope的ms-swift框架开发 Developed using ModelScope's ms-swift framework
基础模型 / Base Model:
基于零一万物的Yi系列6B模型训练，包括yi-6B、yi-6B-chat、yi-1.5-6B、yi-1.5-6B-chat Fine-tuned on 01.AI's Yi-6B series model, including yi-6B, yi-6B-chat, yi-1.5-6B and yi-1.5-6B-chat

当前状态 / Current Status

详细的技术规格和性能指标将在相关研究论文发表后提供。 Detailed technical specifications and performance metrics will be available upon publication of our research paper.

致谢 / Acknowledgments

特别感谢以下开源项目的贡献： We would like to acknowledge the contributions of the following open-source projects:

ModelScope的ms-swift框架 / ModelScope's ms-swift framework
零一万物的Yi系列模型 / 01.AI's Yi series models

Downloads last month: 6

Safetensors

Model size

6B params

Tensor type

F16

Model tree for Invalid-Null/PeiYangMe-0.6

Base model

01-ai/Yi-1.5-6B-Chat

Finetuned

(4)

this model

Collection including Invalid-Null/PeiYangMe-0.6

PeiYangMe

Collection

北洋微衍/PeiYang MicroEmergence • 11 items • Updated May 22, 2025