Instructions to use MonolithFoundation/Bumblebee with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MonolithFoundation/Bumblebee with Transformers:

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

pipe = pipeline("text-generation", model="MonolithFoundation/Bumblebee")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("MonolithFoundation/Bumblebee", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MonolithFoundation/Bumblebee with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MonolithFoundation/Bumblebee"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MonolithFoundation/Bumblebee",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MonolithFoundation/Bumblebee

SGLang

How to use MonolithFoundation/Bumblebee 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 "MonolithFoundation/Bumblebee" \
    --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": "MonolithFoundation/Bumblebee",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "MonolithFoundation/Bumblebee" \
        --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": "MonolithFoundation/Bumblebee",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MonolithFoundation/Bumblebee with Docker Model Runner:
```
docker model run hf.co/MonolithFoundation/Bumblebee
```

MonolithFoundation commited on Apr 26, 2024

Commit

aba1922

verified ·

1 Parent(s): 173ba04

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -1

README.md CHANGED Viewed

@@ -1,3 +1,15 @@
 <div align="center">
 <img src="assets/a.png" />
 <h1>Bumblebee</h1>
@@ -81,4 +93,4 @@ In our pursuit of advancement, we are currently developing even more advanced te
 - The development of a specialized model that works exclusively with documents, incorporating some innovative techniques.
 - Hopefully we can make a new **Optimus Prime** model in the near future.
-If you were interested in the new progress, please **star and watch** this repo!

+---
+license: apache-2.0
+datasets:
+- HuggingFaceFW/fineweb
+- YanweiLi/MGM-Instruction
+language:
+- zh
+tags:
+- vlm
+- MLLM
+- Multi-Modal LLM
+---
 <div align="center">
 <img src="assets/a.png" />
 <h1>Bumblebee</h1>
 - The development of a specialized model that works exclusively with documents, incorporating some innovative techniques.
 - Hopefully we can make a new **Optimus Prime** model in the near future.
+If you were interested in the new progress, please **star and watch** this repo!