Instructions to use WYNN747/burmese-coder-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WYNN747/burmese-coder-4b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="WYNN747/burmese-coder-4b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("WYNN747/burmese-coder-4b", dtype="auto")

llama-cpp-python

How to use WYNN747/burmese-coder-4b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="WYNN747/burmese-coder-4b",
	filename="gemma-3n-e4b-it.BF16-mmproj.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use WYNN747/burmese-coder-4b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf WYNN747/burmese-coder-4b:BF16
# Run inference directly in the terminal:
llama-cli -hf WYNN747/burmese-coder-4b:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf WYNN747/burmese-coder-4b:BF16
# Run inference directly in the terminal:
llama-cli -hf WYNN747/burmese-coder-4b:BF16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf WYNN747/burmese-coder-4b:BF16
# Run inference directly in the terminal:
./llama-cli -hf WYNN747/burmese-coder-4b:BF16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf WYNN747/burmese-coder-4b:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf WYNN747/burmese-coder-4b:BF16

Use Docker

docker model run hf.co/WYNN747/burmese-coder-4b:BF16

LM Studio
Jan

vLLM

How to use WYNN747/burmese-coder-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WYNN747/burmese-coder-4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WYNN747/burmese-coder-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/WYNN747/burmese-coder-4b:BF16

SGLang

How to use WYNN747/burmese-coder-4b 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 "WYNN747/burmese-coder-4b" \
    --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": "WYNN747/burmese-coder-4b",
		"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 "WYNN747/burmese-coder-4b" \
        --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": "WYNN747/burmese-coder-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use WYNN747/burmese-coder-4b with Ollama:
```
ollama run hf.co/WYNN747/burmese-coder-4b:BF16
```

Unsloth Studio

How to use WYNN747/burmese-coder-4b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for WYNN747/burmese-coder-4b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for WYNN747/burmese-coder-4b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for WYNN747/burmese-coder-4b to start chatting

Docker Model Runner
How to use WYNN747/burmese-coder-4b with Docker Model Runner:
```
docker model run hf.co/WYNN747/burmese-coder-4b:BF16
```

Lemonade

How to use WYNN747/burmese-coder-4b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull WYNN747/burmese-coder-4b:BF16

Run and chat with the model

lemonade run user.burmese-coder-4b-BF16

List all available models

lemonade list

WYNN747 commited on Mar 30

Commit

6d811fd

verified ·

1 Parent(s): 3e103ff

Upload Modelfile

Browse files

Updated Modelfile with optimized prompt.

Files changed (1) hide show

Modelfile +10 -2

Modelfile CHANGED Viewed

@@ -1,5 +1,13 @@
-FROM .
 TEMPLATE """{{- range $i, $_ := .Messages }}
 {{- $last := eq (len (slice $.Messages $i)) 1 }}
 {{- if or (eq .Role "user") (eq .Role "system") }}<start_of_turn>user

+FROM gemma-3n-e4b-it.Q8_0.gguf
+SYSTEM """You are burmese-coder, a Burmese-first programming assistant.
+Primary response language: Burmese.
+Keep Python syntax, code tokens, library names, commands, filenames, APIs, and standard technical terminology in English.
+Do not output Thai, Japanese, Korean, Chinese, Bengali, Arabic, or romanized Burmese.
+If the user requests code, output exactly one runnable Python code block first, then a concise Burmese explanation.
+If code is not requested, do not force a code block.
+Do not invent files, outputs, API responses, benchmark metrics, or test outcomes.
+If details are missing, state one short Burmese assumption and continue safely.
+Prefer concise, instruction-following, production-usable answers."""
 TEMPLATE """{{- range $i, $_ := .Messages }}
 {{- $last := eq (len (slice $.Messages $i)) 1 }}
 {{- if or (eq .Role "user") (eq .Role "system") }}<start_of_turn>user