Instructions to use FFZwai/leyoai-flow-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FFZwai/leyoai-flow-medium with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "FFZwai/leyoai-flow-medium")

Transformers

How to use FFZwai/leyoai-flow-medium with Transformers:

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

pipe = pipeline("text-generation", model="FFZwai/leyoai-flow-medium")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("FFZwai/leyoai-flow-medium", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FFZwai/leyoai-flow-medium with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/FFZwai/leyoai-flow-medium

SGLang

How to use FFZwai/leyoai-flow-medium 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 "FFZwai/leyoai-flow-medium" \
    --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": "FFZwai/leyoai-flow-medium",
		"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 "FFZwai/leyoai-flow-medium" \
        --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": "FFZwai/leyoai-flow-medium",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FFZwai/leyoai-flow-medium with Docker Model Runner:
```
docker model run hf.co/FFZwai/leyoai-flow-medium
```

FFZwai commited on Apr 28

Commit

fe9dffe

verified ·

1 Parent(s): 7efabd2

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +94 -18

README.md CHANGED Viewed

@@ -1,33 +1,109 @@
 ---
 license: apache-2.0
 tags:
-  - leyoai
-  - qwen2.5
-  - lora
-  - flow
-base_model: Qwen/Qwen2.5-1.5B-Instruct
 ---
-# leyoai-flow-medium
-LeyoAI Flow 中规模模型 - 流程自动化助手 - Workflow Automation AI Assistant
-Base: Qwen2.5-1.5B-Instruct + LoRA (LoRA r=16, ~3K samples)
-## About LeyoAI
-LeyoAI is a vertical AI MaaS platform by 杭州市上城区乐友信息服务工作室, providing four AI assistants:
-- **Cyber Model**: AI Security Assistant
-- **Video Model**: Video Safety Assistant
-- **Flow Model**: Workflow Automation Assistant
-- **Analytics Model**: Data Analytics Assistant
-## Usage
 ```python
 from peft import PeftModel
 from transformers import AutoModelForCausalLM, AutoTokenizer
-base = AutoModelForCausalLM.from_pretrained('Qwen/Qwen2.5-1.5B-Instruct')
-tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen2.5-1.5B-Instruct')
-model = PeftModel.from_pretrained(base, 'FFZwai/leyoai-flow-medium')
 ```

 ---
 license: apache-2.0
+language:
+- en
+- zh
 tags:
+- workflow-automation
+- process-automation
+- qwen2.5
+- lora
+- leyoai
+base_model: Qwen/Qwen2.5-3B-Instruct
 ---
+# LeyoAI Flow Automation Assistant (Medium)
+English | [中文](#中文)
+## English
+### Model Description
+Enhanced workflow automation and classification assistant
+### Installation
+```bash
+pip install transformers peft torch
+```
+### Usage Scenarios
+- Workflow classification
+- Process automation
+- Task routing
+### How to Use
 ```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
 from peft import PeftModel
+# Load base model
+base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
+# Load LoRA adapter
+model = PeftModel.from_pretrained(base_model, "FFZwai/leyoai-flow-medium")
+# Generate response
+input_text = "Your question here"
+inputs = tokenizer(input_text, return_tensors="pt")
+outputs = model.generate(**inputs, max_length=512)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+### Training Details
+- **Base Model**: Qwen/Qwen2.5-3B-Instruct
+- **LoRA Rank**: 16
+- **Training Data**: 3,500 samples
+- **Validation Data**: 175 samples
+- **Framework**: QLoRA + SFTTrainer
+---
+## 中文
+### 模型描述
+增强版流程自动化和分类助手
+### 安装方法
+```bash
+pip install transformers peft torch
+```
+### 使用场景
+- 工作流分类
+- 流程自动化
+- 任务路由
+### 使用方法
+```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+# 加载基座模型
+base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
+# 加载 LoRA 适配器
+model = PeftModel.from_pretrained(base_model, "FFZwai/leyoai-flow-medium")
+# 生成回复
+input_text = "你的问题"
+inputs = tokenizer(input_text, return_tensors="pt")
+outputs = model.generate(**inputs, max_length=512)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
+### 训练细节
+- **基座模型**: Qwen/Qwen2.5-3B-Instruct
+- **LoRA Rank**: 16
+- **训练数据**: 3,500 samples
+- **验证数据**: 175 samples
+- **训练框架**: QLoRA + SFTTrainer
+---
+## About LeyoAI
+LeyoAI is an AI MaaS platform by 杭州市上城区乐友信息服务工作室, providing specialized AI assistants for cybersecurity, video safety, workflow automation, and data analytics.
+**Website**: https://leyoai.vercel.app