Instructions to use amkyawdev/myanmar-ghost with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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", device_map="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
```

amkyawdev commited on Jul 10

Commit

9574bbb

verified ·

1 Parent(s): fdb7961

Update to LLM model - text-generation

Browse files

Files changed (1) hide show

README.md +39 -59

README.md CHANGED Viewed

@@ -1,79 +1,59 @@
 ---
 language:
-- my
-- en
-license: apache-2.0
-library_name: transformers
-pipeline_tag: text-classification
-tags:
-- myanmar
-- burmese
-- nlp
-- text-classification
-- sentiment-analysis
-- news-classification
-- xlm-roberta
----
-# Myanmar Ghost 🐉
-Advanced Myanmar Language Understanding Model
-## 🎯 Overview
-Myanmar Ghost is a transformer-based language model designed for Myanmar (Burmese) language understanding tasks.
-### Features
-- **Multi-task Learning**: Supports classification, translation, and NLI
-- **Pre-trained on Myanmar corpus**: 10.6M Myanmar text samples
-- **Fine-tuned datasets**: News classification, translation, instruction tuning
-- **Multi-modal Ready**: Audio + text fusion for sentiment analysis
-## 📊 Training Data
-| Dataset | Size | Purpose |
-|---------|------|---------|
-| Myanmar Written Corpus | 10.6M | Pre-training |
-| Myanmar News Classification | 29K | Fine-tuning |
-| Myanmar-English Translation | 22K | Translation |
-| Instruction Tuning | 91K | Chat/QA |
-## 🚀 Quick Start
 ```python
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
-# Load model
-model_name = "amkyawdev/myanmar-ghost"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForSequenceClassification.from_pretrained(model_name)
-# Predict
-text = "မြန်မာစာသတင်း"
-inputs = tokenizer(text, return_tensors="pt")
-outputs = model(**inputs)
-prediction = outputs.logits.argmax(dim=-1)
 ```
-## 📁 Project Structure
-```
-Myanmar-Ghost/
-├── configs/           # Model & training configs
-├── data/             # Datasets
-├── src/
-│   ├── models/       # Model implementations
-│   ├── data_processing/
-│   ├── training/     # Training pipeline
-│   └── evaluation/   # Metrics & benchmarking
-└── docs/             # Documentation
-```
-## 📜 License
 Apache 2.0
-## 👤 Author
 Aung Myo Kyaw (amkyawdev)

 ---
 language:
+    - my
+    - en
+    license: apache-2.0
+    library_name: transformers
+    pipeline_tag: text-generation
+    tags:
+        - myanmar
+        - burmese
+        - llm
+        - chat
+        - instruction-following
+        ---
+# Myanmar Ghost
+**Advanced Myanmar Language Model (LLM)**
+## Overview
+Myanmar Ghost is a Large Language Model for Myanmar language instruction following and conversation.
+- Based on: MiniMax-M2.7 Architecture
+- Fine-tuned with: QLoRA on Myanmar datasets
+- Supports: Chat, Code, Translation, QA
+## Quick Start
 ```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+model = AutoModelForCausalLM.from_pretrained("amkyawdev/myanmar-ghost", load_in_4bit=True)
+tokenizer = AutoTokenizer.from_pretrained("amkyawdev/myanmar-ghost")
+prompt = "### Instruction:
+မြန်မာစာမေးပွဲအကြောင်း ရှင်းပါ
+### Response:
+"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=256)
+print(tokenizer.decode(outputs[0]))
 ```
+## Training Data
+- myanmar-v3-clean: 877K
+- burme-coder-max: 1M
+- mm-llm-coder-agent: 4M
+- alpaca-myanmar: 91K
+## License
 Apache 2.0
+## Author
 Aung Myo Kyaw (amkyawdev)