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
```

Possible to run with llama.cpp now?

by BoscoTheDog - opened Jun 26, 2024

Discussion

BoscoTheDog

Jun 26, 2024

Since llama.cpp recently added bitnet support, is it perhaps possible to run this model via llama.cpp by changing the config settings?

dittops

Bud org Jun 27, 2024

I haven't tried the conversion of the model with llama.cpp. But if they are supporting you should be able to run by making necessary changes and do that.

BoscoTheDog

Jun 27, 2024

Thanks. I've tried to change the config.json file to make it seem like a BitnetForCasualLM file, but couldn't get it to work (yet) unfortunately. But cool to know that in theory it could work.

BoscoTheDog changed discussion status to closed Jun 27, 2024

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