Instructions to use Banaxi-Tech/unified-2.1-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Banaxi-Tech/unified-2.1-test with Transformers:

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

pipe = pipeline("text-generation", model="Banaxi-Tech/unified-2.1-test", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Banaxi-Tech/unified-2.1-test", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Banaxi-Tech/unified-2.1-test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Banaxi-Tech/unified-2.1-test"
# 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/unified-2.1-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Banaxi-Tech/unified-2.1-test

SGLang

How to use Banaxi-Tech/unified-2.1-test 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/unified-2.1-test" \
    --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/unified-2.1-test",
		"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/unified-2.1-test" \
        --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/unified-2.1-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Banaxi-Tech/unified-2.1-test with Docker Model Runner:
```
docker model run hf.co/Banaxi-Tech/unified-2.1-test
```

unified-2.1-test / checkpoint_metadata.json

Banaxi-Tech

Upload BananaMind 2.1 Unified 100% preview at 37,999,869,952 tokens

09d0f9d verified 3 days ago

Raw

History Blame Contribute Delete

1.03 kB

	{
	"parameters": 34999041,
	"matmul_parameters": 34975744,
	"training_percent": 100,
	"step": 72479,
	"total_steps": 72479,
	"tokens_seen": 37999869952,
	"target_tokens": 38000000000,
	"trained_token_target": 37999869952,
	"tokens_per_step": 524288,
	"world_size": 8,
	"gpu_name": "NVIDIA RTX PRO 6000 Blackwell Server Edition",
	"peak_lr": 0.0023,
	"solo_lambda": 0.3,
	"architecture_revision": "a0f30efc480e2c298dc7e779d714338ecf031eaa",
	"dataset_revisions": {
	"fineweb_hq": "e58199cdd52438d94405df1a4d8630cc5f13bf84",
	"dclm": "a3b142c183aebe5af344955ae20836eb34dcf69b",
	"cosmopedia_v2": "3ba9d605774198c5868892d7a8deda78031a781f",
	"finemath": "e92b25a616738fe95dc186b64dfb19f9c8525594"
	},
	"source_tokens": {
	"fineweb_hq": 19363528704,
	"dclm": 7891058688,
	"cosmopedia_v2": 7616331776,
	"finemath": 3128950784
	},
	"mix": {
	"fineweb_hq": 0.50957,
	"dclm": 0.20766,
	"cosmopedia_v2": 0.20043,
	"finemath": 0.08234
	},
	"elapsed_seconds": 27405.331552505493
	}