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
```

OLMo-Bitnet-1B / config.json

emozilla

Update config.json

3f24b12 verified about 2 years ago

raw

history blame contribute delete

1.23 kB

	{
	"activation_type": "swiglu",
	"alibi": false,
	"alibi_bias_max": 8.0,
	"architectures": [
	"OLMoModelForCausalLM"
	],
	"attention_dropout": 0.0,
	"attention_layer_norm": false,
	"attention_layer_norm_with_affine": false,
	"bias_for_layer_norm": false,
	"block_group_size": 1,
	"block_type": "sequential",
	"clip_qkv": null,
	"d_model": 2048,
	"embedding_dropout": 0.0,
	"embedding_size": 50304,
	"eos_token_id": 50279,
	"flash_attention": true,
	"include_bias": false,
	"init_cutoff_factor": null,
	"init_device": "meta",
	"init_fn": "mitchell",
	"init_std": 0.02,
	"layer_norm_type": "rms",
	"layer_norm_with_affine": true,
	"max_sequence_length": 2048,
	"mlp_hidden_size": null,
	"mlp_ratio": 8,
	"model_type": "olmo",
	"multi_query_attention": false,
	"n_heads": 16,
	"n_layers": 16,
	"pad_token_id": 1,
	"precision": "amp_bf16",
	"residual_dropout": 0.0,
	"rope": true,
	"rope_full_precision": true,
	"scale_logits": false,
	"ternary": true,
	"transformers_version": "4.38.2",
	"use_cache": true,
	"vocab_size": 50280,
	"weight_tying": true,
	"auto_map": {
	"AutoConfig": "configuration_olmo.OLMoConfig",
	"AutoModelForCausalLM": "modeling_olmo.OLMoForCausalLM"
	}
	}