Update README.md
Browse files
README.md
CHANGED
|
@@ -12,4 +12,38 @@ library_name: transformers
|
|
| 12 |
tags:
|
| 13 |
- code
|
| 14 |
- text-generation-inference
|
| 15 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
tags:
|
| 13 |
- code
|
| 14 |
- text-generation-inference
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# DevOps Mastermind Model
|
| 18 |
+
|
| 19 |
+
This repository hosts the **DevOps Mastermind** model, a pre-trained model based on `microsoft/phi-2` with modifications tailored for specialized DevOps knowledge tasks. The model is designed to support various downstream tasks, such as code generation, documentation assistance, and knowledge inference in DevOps domains.
|
| 20 |
+
|
| 21 |
+
## Model Details
|
| 22 |
+
|
| 23 |
+
- **Base Model**: `microsoft/phi-2`
|
| 24 |
+
- **Purpose**: Enhanced with additional training and modifications for DevOps and software engineering contexts.
|
| 25 |
+
- **Files Included**:
|
| 26 |
+
- `config.json`: Model configuration.
|
| 27 |
+
- `pytorch_model.bin`: The primary model file containing weights.
|
| 28 |
+
- `tokenizer.json`: Tokenizer for processing text inputs.
|
| 29 |
+
- `added_tokens.json`: Additional tokens specific to DevOps vocabulary.
|
| 30 |
+
- `generation_config.json`: Generation configuration for text generation tasks.
|
| 31 |
+
- Other auxiliary files required for model usage and compatibility.
|
| 32 |
+
|
| 33 |
+
## Usage
|
| 34 |
+
|
| 35 |
+
To load and use this model in your code, run the following commands:
|
| 36 |
+
|
| 37 |
+
```python
|
| 38 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 39 |
+
|
| 40 |
+
# Load the model and tokenizer
|
| 41 |
+
model = AutoModelForCausalLM.from_pretrained("kavinduc/devops-mastermind")
|
| 42 |
+
tokenizer = AutoTokenizer.from_pretrained("kavinduc/devops-mastermind")
|
| 43 |
+
|
| 44 |
+
# Example usage
|
| 45 |
+
input_text = "Explain how to set up a CI/CD pipeline"
|
| 46 |
+
inputs = tokenizer(input_text, return_tensors="pt")
|
| 47 |
+
outputs = model.generate(**inputs)
|
| 48 |
+
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
| 49 |
+
print(generated_text)
|