Instructions to use endless-frontier/BigBang-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use endless-frontier/BigBang-v1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="endless-frontier/BigBang-v1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("endless-frontier/BigBang-v1")
model = AutoModelForMultimodalLM.from_pretrained("endless-frontier/BigBang-v1", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use endless-frontier/BigBang-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "endless-frontier/BigBang-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "endless-frontier/BigBang-v1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/endless-frontier/BigBang-v1

SGLang

How to use endless-frontier/BigBang-v1 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 "endless-frontier/BigBang-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "endless-frontier/BigBang-v1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "endless-frontier/BigBang-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "endless-frontier/BigBang-v1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use endless-frontier/BigBang-v1 with Docker Model Runner:
```
docker model run hf.co/endless-frontier/BigBang-v1
```

One of the better finetunes

by zviratko - opened 2 days ago

Discussion

zviratko

2 days ago

Thank you

Intelligence Benchmark Comparison

              Mode    Sampled                      BigBang-v1-oQ4e-mtp               BigBang-v1-oQ5e-mtp               BigBang-v1-oQ6e-mtp               BigBang-v1-oQ8e-mtp  Qwopus3.6-35B-A3B-Coder-oQ8e-mtp
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
MMLU          Sample  300/14042                                  82.0%                             80.7%                             81.3%                             81.0%                             82.0%
MMLU_PRO      Sample  300/12032                                  61.3%                             59.3%                             63.3%                             63.7%                             66.7%
HUMANEVAL     Full    164                                        86.6%                             87.2%                             85.4%                             89.0%                             91.5%

--- Detail ---

Model: BigBang-v1-oQ4e-mtp
Benchmark         Accuracy   Correct   Total   Time(s)   Think
--------------------------------------------------------------
MMLU                 82.0%       246     300     105.5      No
MMLU_PRO             61.3%       184     300     209.5      No
HUMANEVAL            86.6%       142     164     137.1      No

Model: BigBang-v1-oQ5e-mtp
Benchmark         Accuracy   Correct   Total   Time(s)   Think
--------------------------------------------------------------
MMLU                 80.7%       242     300     111.6      No
MMLU_PRO             59.3%       178     300     285.7      No
HUMANEVAL            87.2%       143     164     138.5      No

Model: BigBang-v1-oQ6e-mtp
Benchmark         Accuracy   Correct   Total   Time(s)   Think
--------------------------------------------------------------
MMLU                 81.3%       244     300     117.4      No
MMLU_PRO             63.3%       190     300       374      No
HUMANEVAL            85.4%       140     164     182.6      No

Model: BigBang-v1-oQ8e-mtp
Benchmark         Accuracy   Correct   Total   Time(s)   Think
--------------------------------------------------------------
MMLU                 81.0%       243     300     123.3      No
MMLU_PRO             63.7%       191     300     397.3      No
HUMANEVAL            89.0%       146     164     170.6      No

Model: Qwopus3.6-35B-A3B-Coder-oQ8e-mtp
Benchmark         Accuracy   Correct   Total   Time(s)   Think
--------------------------------------------------------------
MMLU                 82.0%       246     300     136.2      No
MMLU_PRO             66.7%       200     300     450.4      No
HUMANEVAL            91.5%       150     164     265.1      No

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