Instructions to use Banaxi-Tech/waterfall-alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Banaxi-Tech/waterfall-alpha with Transformers:

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

pipe = pipeline("text-generation", model="Banaxi-Tech/waterfall-alpha", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Banaxi-Tech/waterfall-alpha", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Banaxi-Tech/waterfall-alpha with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Banaxi-Tech/waterfall-alpha

SGLang

How to use Banaxi-Tech/waterfall-alpha 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 "Banaxi-Tech/waterfall-alpha" \
    --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": "Banaxi-Tech/waterfall-alpha",
		"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 "Banaxi-Tech/waterfall-alpha" \
        --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": "Banaxi-Tech/waterfall-alpha",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Banaxi-Tech/waterfall-alpha with Docker Model Runner:
```
docker model run hf.co/Banaxi-Tech/waterfall-alpha
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Cascade Alpha

BananaMind 2 Mini checkpoint exported as a Hugging Face Transformers model folder.

Source checkpoint: step_022999.pt
Training step: 22,999
Tokens seen: 12,435,456,000
Parameters: ~25.2M
Context length: 4096
Tokenizer vocab: 8192

Load with:

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Banaxi-Tech/waterfall-alpha", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("Banaxi-Tech/waterfall-alpha")

Downloads last month: -

Safetensors

Model size

28.3M params

Tensor type

F32