Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language: en
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
base_model: Qwen/Qwen2-3B
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
# Commgpt‑3B
|
| 9 |
+
|
| 10 |
+
**Commgpt‑3B** is a conversational language model fine-tuned from [Qwen2-3B](https://huggingface.co/Qwen/Qwen2-3B).
|
| 11 |
+
It was specifically adapted for **Engineering Communications** topics.
|
| 12 |
+
|
| 13 |
+
For more information, visit the GitHub repository:
|
| 14 |
+
🔗 [https://github.com/DavidA00/Commgpt-final-year-project](https://github.com/DavidA00/Commgpt-final-year-project)
|
| 15 |
+
|
| 16 |
+
## Usage
|
| 17 |
+
|
| 18 |
+
```python
|
| 19 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
|
| 20 |
+
|
| 21 |
+
model = AutoModelForCausalLM.from_pretrained("dabboud/Commgpt-3B")
|
| 22 |
+
tokenizer = AutoTokenizer.from_pretrained("dabboud/Commgpt-3B")
|
| 23 |
+
|
| 24 |
+
generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
|
| 25 |
+
output = generator("Hello, how can I help you today?", max_new_tokens=100)
|
| 26 |
+
print(output[0]["generated_text"])
|