Instructions to use ArchSpace-Collection/OLMo3-1B-stage2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArchSpace-Collection/OLMo3-1B-stage2 with Transformers:

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

pipe = pipeline("text-generation", model="ArchSpace-Collection/OLMo3-1B-stage2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ArchSpace-Collection/OLMo3-1B-stage2")
model = AutoModelForCausalLM.from_pretrained("ArchSpace-Collection/OLMo3-1B-stage2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ArchSpace-Collection/OLMo3-1B-stage2 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-stage2"
# 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-stage2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ArchSpace-Collection/OLMo3-1B-stage2

SGLang

How to use ArchSpace-Collection/OLMo3-1B-stage2 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-stage2" \
    --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-stage2",
		"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-stage2" \
        --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-stage2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ArchSpace-Collection/OLMo3-1B-stage2 with Docker Model Runner:
```
docker model run hf.co/ArchSpace-Collection/OLMo3-1B-stage2
```

OLMo3-1B-stage2 / README.md

arch-space

Fix baseline repository ID in model card

ec06653 verified 15 days ago

preview code

Raw

History Blame Contribute Delete

1.42 kB

metadata

library_name: transformers
pipeline_tag: text-generation
tags:
  - olmo3
  - baseline
  - safetensors
  - sliding-window-attention

OLMo 3 1B Baseline — Stage 2 Mid-training

This repository contains the pure OLMo 3 1B baseline checkpoint from o3b1b-s2-s8192-g256-m1-tp1-cp2-dp256-hsdp32-b8-halo-norecomp-lr2p071235e4-save10000-512npu-share-20260801-v1 at iteration 47684. SiameseNorm and Depth-Attention are disabled.

Training sequence length: 8,192
Model context capacity: 8,192
Sliding-window size: 4,096
Attention pattern: [SWA, SWA, SWA, Full]
Vocabulary: 100,278 real tokens; 74 Megatron padding rows removed

Stage 3/4 apply YaRN only to Full-Attention layers. OLMo 3 SWA layers use the original RoPE and retain their 4,096-token local window.

Loading

transformers>=4.57.6,<5 is required.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "ArchSpace-Collection/OLMo3-1B-SiameseNorm-DepthAttention-baseline-stage2"
tokenizer = AutoTokenizer.from_pretrained(
    repo_id,
    use_fast=True,
    fix_mistral_regex=False,
)
model = AutoModelForCausalLM.from_pretrained(
    repo_id,
    dtype=torch.bfloat16,
    attn_implementation="sdpa",
)

fix_mistral_regex=False preserves the tokenizer behavior used for training. The checkpoint uses the official Transformers Olmo3ForCausalLM implementation and does not require remote code.