Text Generation
Transformers
Burmese
English
myanmar
burmese
llm
chat
instruction-following
conversational
autoregressive
Instructions to use amkyawdev/myanmar-ghost with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use amkyawdev/myanmar-ghost with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="amkyawdev/myanmar-ghost") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("amkyawdev/myanmar-ghost", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use amkyawdev/myanmar-ghost with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "amkyawdev/myanmar-ghost" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "amkyawdev/myanmar-ghost", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/amkyawdev/myanmar-ghost
- SGLang
How to use amkyawdev/myanmar-ghost 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 "amkyawdev/myanmar-ghost" \ --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": "amkyawdev/myanmar-ghost", "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 "amkyawdev/myanmar-ghost" \ --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": "amkyawdev/myanmar-ghost", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use amkyawdev/myanmar-ghost with Docker Model Runner:
docker model run hf.co/amkyawdev/myanmar-ghost
Add Burmese README
Browse files- README_my.md +67 -0
README_my.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# π²π² Myanmar Ghost
|
| 2 |
+
|
| 3 |
+
## ααααΊαααΊ
|
| 4 |
+
|
| 5 |
+
Myanmar Ghost αααΊ ααΌααΊαα¬α
α¬αα¬αΈα‘αααΊαα½αα·αΊααα―ααΌααΊαΈ (Sentiment Analysis) α‘αα½ααΊ α‘ααα·αΊααΌαα·αΊ AI Model αα
αΊαα―ααΌα
αΊαα«αααΊα
|
| 6 |
+
|
| 7 |
+
### α‘ααααα―ααΊαα±α¬ααΊαα»ααΊαα»α¬αΈ
|
| 8 |
+
|
| 9 |
+
- **Multi-Modal Fusion** - α‘ααΆ + α
α¬αα¬αΈ αα±α«ααΊαΈα
ααΊααΌααΊαΈ
|
| 10 |
+
- **Active Learning** - αααα±α¬ααΊαα±α¬ α‘αα½αΎααΊαΈαααΊααΎααΊααΌααΊαΈ
|
| 11 |
+
- **Federated Learning** - Privacy-preserving training
|
| 12 |
+
- **Explainable AI** - SHAP/LIME ααΌαα·αΊ ααΎααΊαΈααΌααΌααΊαΈ
|
| 13 |
+
- **Data Augmentation** - Adversarial augmentation
|
| 14 |
+
|
| 15 |
+
## αααΊαααΊααΌααΊαΈ
|
| 16 |
+
|
| 17 |
+
```bash
|
| 18 |
+
pip install -r requirements.txt
|
| 19 |
+
```
|
| 20 |
+
|
| 21 |
+
## α‘αα―αΆαΈααΌα―αα―αΆ
|
| 22 |
+
|
| 23 |
+
### Training
|
| 24 |
+
```bash
|
| 25 |
+
python src/models/train.py \
|
| 26 |
+
--train_data data/processed/splits/train.csv \
|
| 27 |
+
--output_dir outputs/models
|
| 28 |
+
```
|
| 29 |
+
|
| 30 |
+
### Evaluation
|
| 31 |
+
```bash
|
| 32 |
+
python src/models/evaluate.py \
|
| 33 |
+
--model_path outputs/models/best_model.pt \
|
| 34 |
+
--data_path data/processed/splits/test.csv
|
| 35 |
+
```
|
| 36 |
+
|
| 37 |
+
### API Run
|
| 38 |
+
```bash
|
| 39 |
+
uvicorn deployment.api.app:app --host 0.0.0.0 --port 8000
|
| 40 |
+
```
|
| 41 |
+
|
| 42 |
+
## Project Structure
|
| 43 |
+
|
| 44 |
+
```
|
| 45 |
+
Myanmar-Ghost/
|
| 46 |
+
βββ src/
|
| 47 |
+
β βββ data_processing/ # Data processing
|
| 48 |
+
β βββ annotation/ # Annotation tools
|
| 49 |
+
β βββ models/ # Model implementations
|
| 50 |
+
β βββ federated/ # Federated learning
|
| 51 |
+
β βββ xai/ # Explainable AI
|
| 52 |
+
β βββ augmentation/ # Data augmentation
|
| 53 |
+
β βββ utils/ # Utilities
|
| 54 |
+
βββ configs/ # Configuration
|
| 55 |
+
βββ data/ # Data directory
|
| 56 |
+
βββ tests/ # Unit tests
|
| 57 |
+
βββ docs/ # Documentation
|
| 58 |
+
```
|
| 59 |
+
|
| 60 |
+
## License
|
| 61 |
+
|
| 62 |
+
Apache 2.0
|
| 63 |
+
|
| 64 |
+
## Author
|
| 65 |
+
|
| 66 |
+
Aung Myo Kyaw
|
| 67 |
+
https://huggingface.co/amkyawdev
|