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

Libraries

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BananaMind/BananaMind-2-Pro"
# 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-Pro",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

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

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

Final result finally dropped, amazing work!

by Datdanboi25 - opened 2 days ago

Discussion

Datdanboi25

2 days ago

Hi @Banaxi-Tech ,
Just wanted to drop by and say this model is amazing (and too close to gpt-x2.5 for my liking), such awesome work and I look forward to having you as an ongoing worthy rival from now on!
Keep up the great stuff!

Dan
(also btw if its not too much effort to correct, would you mind changing your int index vs training compute chart note about gpt-x2.5 from 2048 context to the correct 8192 context, ty in advance)

Datdanboi25

2 days ago

Also just added it to the leaderboard!

Banaxi-Tech

BananaMind AI org 2 days ago

Yeah the context was accident I'll change

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment