Update README.md
Browse files
README.md
CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: text-generation
|
|
15 |
|
16 |
## 🎯 Model Overview
|
17 |
|
18 |
-
This is a **specialized language model**
|
19 |
|
20 |
## ⚠️ Important Notice
|
21 |
|
@@ -44,26 +44,7 @@ The model specializes in:
|
|
44 |
|
45 |
### Basic Usage
|
46 |
|
47 |
-
|
48 |
-
from transformers import AutoTokenizer, AutoModelForCausalLM
|
49 |
-
|
50 |
-
# Load your complete DevOps model directly
|
51 |
-
model = AutoModelForCausalLM.from_pretrained("lakhera2023/devops-slm-v1")
|
52 |
-
tokenizer = AutoTokenizer.from_pretrained("lakhera2023/devops-slm-v1")
|
53 |
-
|
54 |
-
# Generate response (model has built-in DevOps filtering)
|
55 |
-
def generate_devops_response(prompt):
|
56 |
-
inputs = tokenizer(prompt, return_tensors="pt")
|
57 |
-
outputs = model.generate(**inputs, max_new_tokens=200, temperature=0.7)
|
58 |
-
return tokenizer.decode(outputs[0], skip_special_tokens=True)
|
59 |
-
|
60 |
-
# Example usage
|
61 |
-
response = generate_devops_response("How do I create a Kubernetes deployment?")
|
62 |
-
print(response)
|
63 |
-
|
64 |
-
# Note: The model automatically filters non-DevOps questions
|
65 |
-
# and redirects them back to DevOps topics
|
66 |
-
```
|
67 |
|
68 |
### Example Queries
|
69 |
|
@@ -88,7 +69,7 @@ print(response)
|
|
88 |
|
89 |
- **Base Model**: lakhera2023/Qwen-model
|
90 |
- **Architecture**: Transformer-based with LoRA fine-tuning
|
91 |
-
- **Training**:
|
92 |
- **Specialization**: Fine-tuned for DevOps tasks only
|
93 |
|
94 |
## 📊 Performance
|
|
|
15 |
|
16 |
## 🎯 Model Overview
|
17 |
|
18 |
+
This is a **specialized language model** specifically for **DevOps tasks and operations only**.
|
19 |
|
20 |
## ⚠️ Important Notice
|
21 |
|
|
|
44 |
|
45 |
### Basic Usage
|
46 |
|
47 |
+
https://colab.research.google.com/drive/1UgTUI6AeVnSlknHoF3cEDhWLHYirghju?usp=sharing
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
|
49 |
### Example Queries
|
50 |
|
|
|
69 |
|
70 |
- **Base Model**: lakhera2023/Qwen-model
|
71 |
- **Architecture**: Transformer-based with LoRA fine-tuning
|
72 |
+
- **Training**: DevOps-specific examples
|
73 |
- **Specialization**: Fine-tuned for DevOps tasks only
|
74 |
|
75 |
## 📊 Performance
|