Instructions to use budecosystem/boomer-bitnet-634m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use budecosystem/boomer-bitnet-634m with Transformers:

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

pipe = pipeline("text-generation", model="budecosystem/boomer-bitnet-634m", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("budecosystem/boomer-bitnet-634m", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use budecosystem/boomer-bitnet-634m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "budecosystem/boomer-bitnet-634m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "budecosystem/boomer-bitnet-634m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/budecosystem/boomer-bitnet-634m

SGLang

How to use budecosystem/boomer-bitnet-634m 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 "budecosystem/boomer-bitnet-634m" \
    --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": "budecosystem/boomer-bitnet-634m",
		"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 "budecosystem/boomer-bitnet-634m" \
        --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": "budecosystem/boomer-bitnet-634m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use budecosystem/boomer-bitnet-634m with Docker Model Runner:
```
docker model run hf.co/budecosystem/boomer-bitnet-634m
```

Democratizing access to LLMs for the open-source community.
Let's advance AI, together.

Introduction 🎉

We are open-sourcing one of our early experiments of BitNet b1.58 paper. This 634m parameter model is pre-trained from scratch using a custom synthetic dataset of 5B tokens. The model's architecture experiments contain the modification of using higher depth and shallow configuration

Run the model

Please note that, at the moment, trust_remote_code=True is required for running the model.

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("budecosystem/boomer-bitnet-634m",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("budecosystem/boomer-bitnet-634m")

input_ids = tokenizer("In the recent Super Bowl LVIII,", return_tensors='pt').to(model.device)["input_ids"]

outputs = model.generate(input_ids, max_new_tokens=216)

print(tokenizer.batch_decode(outputs))

Evaluations

We have evaluated the pre-trained model on few of the benchmarks

Model Name	ARC	MMLU	Winogrande	Hellaswag	MathQA	GSM8K
boomer-bitnet-634m	26.19	25.23	51.07	34.08	23.38	0.91

Final thought on Boomer!

This isn't the end. It's just the beginning of a journey towards creating more advanced, more efficient, and more accessible language models. We invite you to join us on this exciting journey.

Aknowledgements

We'd like to thank the open-source community and the researchers whose foundational work laid the path for BOOMER. Special shoutout to team who published BitNet b1.58 paper.

Downloads last month: 6

Safetensors

Model size

0.6B params

Tensor type

F16

Dataset used to train budecosystem/boomer-bitnet-634m

Paper for budecosystem/boomer-bitnet-634m

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 629