Instructions to use ArchSpace-Collection/OLMo3-1B-stage3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArchSpace-Collection/OLMo3-1B-stage3 with Transformers:

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

pipe = pipeline("text-generation", model="ArchSpace-Collection/OLMo3-1B-stage3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ArchSpace-Collection/OLMo3-1B-stage3")
model = AutoModelForCausalLM.from_pretrained("ArchSpace-Collection/OLMo3-1B-stage3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ArchSpace-Collection/OLMo3-1B-stage3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ArchSpace-Collection/OLMo3-1B-stage3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArchSpace-Collection/OLMo3-1B-stage3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ArchSpace-Collection/OLMo3-1B-stage3

SGLang

How to use ArchSpace-Collection/OLMo3-1B-stage3 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 "ArchSpace-Collection/OLMo3-1B-stage3" \
    --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": "ArchSpace-Collection/OLMo3-1B-stage3",
		"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 "ArchSpace-Collection/OLMo3-1B-stage3" \
        --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": "ArchSpace-Collection/OLMo3-1B-stage3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ArchSpace-Collection/OLMo3-1B-stage3 with Docker Model Runner:
```
docker model run hf.co/ArchSpace-Collection/OLMo3-1B-stage3
```

arch-space commited on 16 days ago

Commit

cc612e9

verified ·

1 Parent(s): 0454e9f

Fix baseline repository ID in model card

Browse files

Files changed (2) hide show

README.md +1 -1
SHA256SUMS +1 -1

README.md CHANGED Viewed

@@ -31,7 +31,7 @@ original RoPE and retain their 4,096-token local window.
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
-repo_id = "ArchSpace-Collection/OLMo3-1B-SiameseNorm-DepthAttention--baseline-stage3"
 tokenizer = AutoTokenizer.from_pretrained(
     repo_id,
     use_fast=True,

 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
+repo_id = "ArchSpace-Collection/OLMo3-1B-SiameseNorm-DepthAttention-baseline-stage3"
 tokenizer = AutoTokenizer.from_pretrained(
     repo_id,
     use_fast=True,

SHA256SUMS CHANGED Viewed

@@ -1,4 +1,4 @@
-ee4e133cd814cf50530202f800a9d79df885dfe97fa5e540e4c9ca431b12d1e6  README.md
 0dbc55ce09a6ce495d6889efa2d31ef01cd14a1f4b70262fe4612b94ec57f99c  config.json
 775219d4e613a55e6f052b0e92ee1e0880eb3dd0a8a00cb690e435f2628c82be  conversion_manifest.json
 dbd4aa5dc6f7f1bdc0c181d9e5582f6571e1d2a22878dfcd98149324b9f5c4a2  generation_config.json

+2a88b9360f4e3f524dca6e90f767201010c944efccbdd1f6174fc6cdec4d48f4  README.md
 0dbc55ce09a6ce495d6889efa2d31ef01cd14a1f4b70262fe4612b94ec57f99c  config.json
 775219d4e613a55e6f052b0e92ee1e0880eb3dd0a8a00cb690e435f2628c82be  conversion_manifest.json
 dbd4aa5dc6f7f1bdc0c181d9e5582f6571e1d2a22878dfcd98149324b9f5c4a2  generation_config.json