Instructions to use ArchSpace-Collection/NCP_Olmo3_Stage1_Step1100000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArchSpace-Collection/NCP_Olmo3_Stage1_Step1100000 with Transformers:

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

pipe = pipeline("text-generation", model="ArchSpace-Collection/NCP_Olmo3_Stage1_Step1100000", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ArchSpace-Collection/NCP_Olmo3_Stage1_Step1100000", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ArchSpace-Collection/NCP_Olmo3_Stage1_Step1100000 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ArchSpace-Collection/NCP_Olmo3_Stage1_Step1100000"
# 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/NCP_Olmo3_Stage1_Step1100000",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ArchSpace-Collection/NCP_Olmo3_Stage1_Step1100000

SGLang

How to use ArchSpace-Collection/NCP_Olmo3_Stage1_Step1100000 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/NCP_Olmo3_Stage1_Step1100000" \
    --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/NCP_Olmo3_Stage1_Step1100000",
		"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/NCP_Olmo3_Stage1_Step1100000" \
        --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/NCP_Olmo3_Stage1_Step1100000",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ArchSpace-Collection/NCP_Olmo3_Stage1_Step1100000 with Docker Model Runner:
```
docker model run hf.co/ArchSpace-Collection/NCP_Olmo3_Stage1_Step1100000
```

NCP-Olmo3-step-1100000

NCP-Olmo3-step-1100000 is an exported checkpoint from the NCP-Olmo3 training run. It was converted from Megatron iteration 1,100,000 into a Hugging Face-compatible directory with sharded SafeTensors and custom Transformers code.

This is a research checkpoint for the Next-Concept-Prediction (NCP) architecture. Its Transformer layers are aligned with OLMo 3, while NCP adds dense residual connections and discrete concept representations. The model encodes token sequences into discrete concepts, models them at the concept level, and decodes them back into the token space.

Evaluation Results

The final NCP-Olmo3 checkpoint is publicly available as ArchSpace-Collection/NCP_Olmo3_Stage1_StepLast.

The following results compare the final NCP-Olmo3 checkpoint with OLMo-Stage1. On intermediate-checkpoint pages, this table is provided as a reference to the final model rather than as an evaluation of the checkpoint on this page.

Model	GSM8K	HumanEval	MMLU
OLMo-Stage1	39.88	26.94	62.25
NCP-Olmo3-StepLast (ours-hf)	46.78 (+6.90)	31.27 (+4.33)	64.77 (+2.51)

Model Details

Field	Value
Architecture	`NCPOlmo3ForCausalLM`
Backbone layer design	Aligned with OLMo 3
Architecture additions	Dense residual connections and discrete concepts
Source checkpoint	Megatron iteration `1,100,000`
Parameter scale	7B-class
Hidden size	4,096
Transformer layers	32
Attention heads	32
FFN hidden size	11,008
Vocabulary size	100,278
Maximum sequence length	8,192
Concept chunk size	4 tokens
Weight dtype	BF16
Weight format	5 sharded SafeTensors files
Weight key format	Native Megatron state-dict keys
Standalone Transformers backend	Yes
External ConceptLM/Megatron runtime	Not required
Standalone parity status	Candidate (not yet parity-validated)

Requirements

A CUDA-capable NVIDIA GPU with enough memory for this checkpoint.
PyTorch with CUDA and bfloat16 support.
A Transformers version compatible with the bundled remote code (tested target: 5.8.0).
No external ConceptLM or Megatron checkout is required.

Download and Load

The repository bundles its standalone Transformers implementation. Loading requires trust_remote_code=True, but does not require a ConceptLM or Megatron checkout.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "ArchSpace-Collection/NCP_Olmo3_Stage1_Step1100000"

tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(
    repo_id,
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
    device_map="cuda",
)
model.eval()

Generation

prompt = "The role of hierarchical representations in language modeling is"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

with torch.inference_mode():
    output_ids = model.generate(
        **inputs,
        max_new_tokens=128,
        do_sample=True,
        temperature=0.8,
        top_p=0.95,
        use_cache=True,
    )

print(tokenizer.decode(output_ids[0], skip_special_tokens=True))

Downloads last month: -

Safetensors

Model size

9B params

Tensor type

BF16

ArchSpace-Collection
/

NCP_Olmo3_Stage1_Step1100000