Instructions to use ArchSpace-Collection/OLMo3-3B-stage4-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArchSpace-Collection/OLMo3-3B-stage4-instruct with Transformers:

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

pipe = pipeline("text-generation", model="ArchSpace-Collection/OLMo3-3B-stage4-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ArchSpace-Collection/OLMo3-3B-stage4-instruct")
model = AutoModelForCausalLM.from_pretrained("ArchSpace-Collection/OLMo3-3B-stage4-instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ArchSpace-Collection/OLMo3-3B-stage4-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ArchSpace-Collection/OLMo3-3B-stage4-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArchSpace-Collection/OLMo3-3B-stage4-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ArchSpace-Collection/OLMo3-3B-stage4-instruct

SGLang

How to use ArchSpace-Collection/OLMo3-3B-stage4-instruct 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/OLMo3-3B-stage4-instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArchSpace-Collection/OLMo3-3B-stage4-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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/OLMo3-3B-stage4-instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArchSpace-Collection/OLMo3-3B-stage4-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ArchSpace-Collection/OLMo3-3B-stage4-instruct with Docker Model Runner:
```
docker model run hf.co/ArchSpace-Collection/OLMo3-3B-stage4-instruct
```

OLMo3-3B-stage4-instruct / README.md

arch-space

Add files using upload-large-folder tool

da5c8be verified about 2 months ago

preview code

Raw History Blame Contribute Delete

1.56 kB

---
library_name: transformers
pipeline_tag: text-generation
tags:
- olmo3
- safetensors
- sliding-window-attention
- baseline
---
# OLMo 3 3B Baseline — Stage 4 Instruct SFT

This repository is the Hugging Face export of `o3b3b-instruct-sft-dolci-s32768-g32-m1-ga1-tp2-cp8-dp32-h32-b2-lr3e5-min0-wd5e2-wu10pct-2ep-512npu-share-20260906t095032z-s4v2` at
iteration `3252`. This is the matched pure OLMo 3 baseline. It uses Transformers' official `Olmo3ForCausalLM` implementation and does not require remote code.

- Training sequence length: 32,768
- Model context capacity: 65,536
- Sliding-window size: 4,096
- Attention pattern: `[SWA, SWA, SWA, Full]`
- Vocabulary: 100,278 real tokens; 74 Megatron padding-only rows removed

Stage 3/4 use the frozen 65,536-token configuration. YaRN applies to the Full
Attention layers; SWA layers retain their original RoPE and 4,096-token local
window.

## Loading

Use `transformers>=4.57.6,<5`.

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
repo_id = "ArchSpace-Collection/OLMo3-3B-stage4-instruct"
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 exact tokenizer behavior used during
training. Conversion provenance, per-tensor hashes, and CPU validation results
are included in `conversion_manifest.json`, `SHA256SUMS`, and
`hf_validation_report.json`.

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

	# OLMo 3 3B Baseline — Stage 4 Instruct SFT

	This repository is the Hugging Face export of `o3b3b-instruct-sft-dolci-s32768-g32-m1-ga1-tp2-cp8-dp32-h32-b2-lr3e5-min0-wd5e2-wu10pct-2ep-512npu-share-20260906t095032z-s4v2` at
	iteration `3252`. This is the matched pure OLMo 3 baseline. It uses Transformers' official `Olmo3ForCausalLM` implementation and does not require remote code.

	- Training sequence length: 32,768
	- Model context capacity: 65,536
	- Sliding-window size: 4,096
	- Attention pattern: `[SWA, SWA, SWA, Full]`
	- Vocabulary: 100,278 real tokens; 74 Megatron padding-only rows removed

	Stage 3/4 use the frozen 65,536-token configuration. YaRN applies to the Full
	Attention layers; SWA layers retain their original RoPE and 4,096-token local
	window.

	## Loading

	Use `transformers>=4.57.6,<5`.

	```python
	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer

	repo_id = "ArchSpace-Collection/OLMo3-3B-stage4-instruct"
	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 exact tokenizer behavior used during
	training. Conversion provenance, per-tensor hashes, and CPU validation results
	are included in `conversion_manifest.json`, `SHA256SUMS`, and
	`hf_validation_report.json`.