Instructions to use HA-Siala/Mamba-full-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HA-Siala/Mamba-full-v0.2 with Transformers:

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

pipe = pipeline("text-generation", model="HA-Siala/Mamba-full-v0.2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("HA-Siala/Mamba-full-v0.2")
model = AutoModelForMultimodalLM.from_pretrained("HA-Siala/Mamba-full-v0.2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HA-Siala/Mamba-full-v0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HA-Siala/Mamba-full-v0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HA-Siala/Mamba-full-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HA-Siala/Mamba-full-v0.2

SGLang

How to use HA-Siala/Mamba-full-v0.2 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 "HA-Siala/Mamba-full-v0.2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HA-Siala/Mamba-full-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "HA-Siala/Mamba-full-v0.2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HA-Siala/Mamba-full-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HA-Siala/Mamba-full-v0.2 with Docker Model Runner:
```
docker model run hf.co/HA-Siala/Mamba-full-v0.2
```

HA-Siala/Mamba-full-v0.2

Fine-tuned Mistral model to detect flaws in Mamba code and produce refactored versions of the code. For the dataset and source code used in this study, please refer to the official GitHub repository: https://github.com/Hanan-Abdulwahab-Siala/Mamba

Downloads last month: 225

Safetensors

Model size

7B params

Tensor type

BF16