Instructions to use md-nishat-008/Mojo-Coder-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use md-nishat-008/Mojo-Coder-it with Transformers:

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

pipe = pipeline("text-generation", model="md-nishat-008/Mojo-Coder-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("md-nishat-008/Mojo-Coder-it")
model = AutoModelForCausalLM.from_pretrained("md-nishat-008/Mojo-Coder-it", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use md-nishat-008/Mojo-Coder-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "md-nishat-008/Mojo-Coder-it"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "md-nishat-008/Mojo-Coder-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/md-nishat-008/Mojo-Coder-it

SGLang

How to use md-nishat-008/Mojo-Coder-it 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 "md-nishat-008/Mojo-Coder-it" \
    --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": "md-nishat-008/Mojo-Coder-it",
		"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 "md-nishat-008/Mojo-Coder-it" \
        --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": "md-nishat-008/Mojo-Coder-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use md-nishat-008/Mojo-Coder-it with Docker Model Runner:
```
docker model run hf.co/md-nishat-008/Mojo-Coder-it
```

md-nishat-008 commited on Oct 25, 2024

Commit

c3d478e

verified ·

1 Parent(s): 44930f6

Update README.md

Browse files

Files changed (1) hide show

README.md +21 -2

README.md CHANGED Viewed

@@ -23,7 +23,6 @@ pipeline_tag: text-generation
 <div align="center">
 <h2>🎯 Background and Motivation</h2>
 </div>
@@ -218,4 +217,24 @@ The model is designed for:
 - Open-source contribution to Mojo ecosystem
 - Supporting multilingual access to Mojo programming
-Code should be reviewed and tested before production use, especially for performance-critical applications.

 <div align="center">
 <h2>🎯 Background and Motivation</h2>
 </div>
 - Open-source contribution to Mojo ecosystem
 - Supporting multilingual access to Mojo programming
+Code should be reviewed and tested before production use, especially for performance-critical applications.
+<div align="center">
+<h2>📚 Citation</h2>
+</div>
+If you find our work helpful, please consider citing our paper:
+<div style="background-color: #f6f8fa; padding: 20px; border-radius: 5px; margin: 10px 0;">
+<p style="margin-bottom: 10px;"><strong>MojoBench: Language Modeling and Benchmarks for Mojo</strong></p>
+```bibtex
+@inproceedings{Raihan2024MojoBenchLM,
+   title     = {MojoBench: Language Modeling and Benchmarks for Mojo},
+   author    = {Raihan, Nishat and Santos, Joanna C. S. and Zampieri, Marcos},
+   year      = {2024},
+   url       = {https://api.semanticscholar.org/CorpusID:273532552}
+}
+```