Instructions to use NousResearch/OLMo-Bitnet-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NousResearch/OLMo-Bitnet-1B with Transformers:

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

pipe = pipeline("text-generation", model="NousResearch/OLMo-Bitnet-1B", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NousResearch/OLMo-Bitnet-1B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("NousResearch/OLMo-Bitnet-1B", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use NousResearch/OLMo-Bitnet-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NousResearch/OLMo-Bitnet-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NousResearch/OLMo-Bitnet-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NousResearch/OLMo-Bitnet-1B

SGLang

How to use NousResearch/OLMo-Bitnet-1B 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 "NousResearch/OLMo-Bitnet-1B" \
    --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": "NousResearch/OLMo-Bitnet-1B",
		"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 "NousResearch/OLMo-Bitnet-1B" \
        --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": "NousResearch/OLMo-Bitnet-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NousResearch/OLMo-Bitnet-1B with Docker Model Runner:
```
docker model run hf.co/NousResearch/OLMo-Bitnet-1B
```

ModuleNotFoundError: No module named 'transformers_modules.NousResearch.OLMo-Bitnet

by fahdmirzac - opened Mar 31, 2024

Discussion

fahdmirzac

Mar 31, 2024

Hi,
While running it on Ubuntu , getting following error. I have built transformers from the source:

pip install git+https://github.com/huggingface/transformers

and my transformers version is Version: 4.40.0.dev0

and when I run following:
model = AutoModelForCausalLM.from_pretrained("NousResearch/OLMo-Bitnet-1B",
torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")

I get following error:

File "/home/ubuntu/.cache/huggingface/modules/transformers_modules/NousResearch/OLMo-Bitnet-1B/9c9783f0983e51c6dfe84e22c054611ba4eae27f/optim.py", line 13, in
from .model import LayerNormBase, BitLinear158
ModuleNotFoundError: No module named 'transformers_modules.NousResearch.OLMo-Bitnet-1B.9c9783f0983e51c6dfe84e22c054611ba4eae27f.model'

namtran

Apr 3, 2024

Hi @fahdmirzac , have you resolved the problem yet?
I got the same error when trying the transformer (ver 4.38.2).
Here is the error:
File "OLMo-Bitnet-1B/optim.py", line 13, in
from .model import LayerNormBase, BitLinear158
ModuleNotFoundError: No module named 'transformers_modules.OLMo-Bitnet-1B.model

namtran

Apr 3, 2024

I found a way to bypass this, only need to copy file bị thiếu từ model directory into the cache path (somehow the model.py file is not included)

cd model
cp *.py /.cache/huggingface/modules/transformers_modules/OLMo-Bitnet-1B/

fahdmirzac

Apr 4, 2024

@namtran where exactly is this model directly. I don't see it on my Ubuntu system, and still getting the same error.

namtran

Apr 4, 2024

The model folder is the huggingface model folder after you install. In your case, I think you can try:
cd OLMo-Bitnet-1B
cp *.py /home/ubuntu/.cache/huggingface/modules/transformers_modules/NousResearch/OLMo-Bitnet-1B/9c9783f0983e51c6dfe84e22c054611ba4eae27f/

fahdmirzac

Apr 4, 2024

@namtran thanks for reply. Could you please share all the commands you are using so that I could reproduce?

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