|
|
--- |
|
|
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B |
|
|
library_name: peft |
|
|
pipeline_tag: text-generation |
|
|
language: en |
|
|
tags: |
|
|
- deepseek |
|
|
- text-generation |
|
|
- conversational |
|
|
--- |
|
|
|
|
|
# Microsoft 365 Data Management Expert |
|
|
|
|
|
This model is fine-tuned from deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B for answering questions about Microsoft 365 data management, |
|
|
specifically focusing on SharePoint, OneDrive, and Teams. It provides detailed responses about: |
|
|
|
|
|
- Data governance |
|
|
- Retention policies |
|
|
- Permissions management |
|
|
- Version control |
|
|
- Sensitivity labels |
|
|
- Document lifecycle |
|
|
- Compliance features |
|
|
- And more |
|
|
|
|
|
## Model Details |
|
|
|
|
|
- **Base Model**: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B |
|
|
- **Training**: Fine-tuned using LoRA |
|
|
- **Task**: Question-answering about Microsoft 365 data management |
|
|
- **Language**: English |
|
|
- **License**: Same as base model |
|
|
|
|
|
## Usage |
|
|
|
|
|
```python |
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
|
|
model = AutoModelForCausalLM.from_pretrained("YOUR_USERNAME/microsoft365_expert") |
|
|
tokenizer = AutoTokenizer.from_pretrained("YOUR_USERNAME/microsoft365_expert") |
|
|
|
|
|
# Example usage |
|
|
question = "What is data governance in Microsoft 365?" |
|
|
inputs = tokenizer(question, return_tensors="pt") |
|
|
outputs = model.generate(**inputs, max_new_tokens=2048) |
|
|
response = tokenizer.decode(outputs[0], skip_special_tokens=True) |
|
|
print(response) |
|
|
``` |
|
|
|
|
|
## Limitations |
|
|
|
|
|
- Responses are based on training data and may not reflect the latest Microsoft 365 updates |
|
|
- Should be used as a reference, not as the sole source for compliance decisions |
|
|
- May require fact-checking against official Microsoft documentation |
|
|
|
