Instructions to use BananaMind/BananaMind-2-SLMoE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BananaMind/BananaMind-2-SLMoE with Transformers:

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

pipe = pipeline("text-generation", model="BananaMind/BananaMind-2-SLMoE", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("BananaMind/BananaMind-2-SLMoE", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BananaMind/BananaMind-2-SLMoE with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/BananaMind/BananaMind-2-SLMoE

SGLang

How to use BananaMind/BananaMind-2-SLMoE 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 "BananaMind/BananaMind-2-SLMoE" \
    --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": "BananaMind/BananaMind-2-SLMoE",
		"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 "BananaMind/BananaMind-2-SLMoE" \
        --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": "BananaMind/BananaMind-2-SLMoE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BananaMind/BananaMind-2-SLMoE with Docker Model Runner:
```
docker model run hf.co/BananaMind/BananaMind-2-SLMoE
```

BananaMind-2-SLMoE / benchmarks.png

Banaxi-Tech

Upload 11 files

cb8a725 verified 1 day ago

Download

History Blame Contribute Delete

1.85 MB

Xet Pointer Details

( Raw pointer file )

Xet hash:: 119be40e17f16438db5dda8e070bb0738ff949e1d7dfd804ab26bac5e7ba8fdd
Size of remote file:: 1.85 MB
SHA256:: 44f8e431d2a94c3c148e4d5de3673e99db46096fc3fc48716f15f4fce0f3d0bf

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.