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
```

Is it bitnet {-1,0,1}?

by Remek - opened Apr 9, 2024

Discussion

Remek

Apr 9, 2024

I looked through many bitnet1.58 implementations and noticed that they all use the method suggested in "The Era from 1-bit LLMs: Training Tips, Code and FAQ". The weights of the models that are currently trained according to this recipe are not numbers in the set {-1, 0, 1} and values in the interval (0,1). Is this the way it should be?

The formula describing the quanztization of weights ("The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits").
Implementation proposal ("The Era of 1-bit LLMs: Training Tips, Code and FAQ").
Weights quantization test.
Model during training.

supercharge19

Apr 21, 2024

Sadly no. Its fp16, honestly I don't understand reason for training on fp16, why is research not carried forward from where the paper left? Why not train another 1bit model but either with more parameters or with more trainign data or for longer, even better yet for a good combination of these! It was already shown in paper that 1bit is a good contender to all other fp models (or int quants) so why even bother other things? Anyway, I hope someone can carry forward research from here without needing google resources (pun intended).

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