Instructions to use zjr2000/SPES-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zjr2000/SPES-2B with Transformers:

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

pipe = pipeline("text-generation", model="zjr2000/SPES-2B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zjr2000/SPES-2B")
model = AutoModelForCausalLM.from_pretrained("zjr2000/SPES-2B")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use zjr2000/SPES-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zjr2000/SPES-2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zjr2000/SPES-2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zjr2000/SPES-2B

SGLang

How to use zjr2000/SPES-2B 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 "zjr2000/SPES-2B" \
    --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": "zjr2000/SPES-2B",
		"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 "zjr2000/SPES-2B" \
        --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": "zjr2000/SPES-2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zjr2000/SPES-2B with Docker Model Runner:
```
docker model run hf.co/zjr2000/SPES-2B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

SPES-2B

SPES-2B is a 2B-parameter Mixture-of-Experts (MoE) pretrained language model introduced in the paper:

Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm

Model Details

Model name: SPES-2B
Model type: Causal language model (MoE)
Architecture: OLMoE
Parameters: 2B
Framework: SPES (SParse Expert Synchronization)
License: Apache-2.0

Description

SPES-2B was trained using SPES, a memory-efficient decentralized framework. Unlike traditional centralized training that requires high-bandwidth interconnects, SPES enables pretraining across geographically distributed GPU nodes by training only a subset of experts per node and periodically synchronizing them. This model was trained using 16 standalone 48GB GPUs over standard internet connections.

Project Links

GitHub: https://github.com/zjr2000/SPES
Paper: https://huggingface.co/papers/2602.11543

Intended Use

This model is intended for:

Research on decentralized LLM pretraining.
Research on Mixture-of-Experts (MoE) training and synchronization.
Experimentation and evaluation of pretrained language models.

Citation

If you use this model, please cite the SPES paper:

@article{zhang2026pretraining,
  title={Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm},
  author={Zhang, Jinrui icon and Xiao, Chaodong and Wu, Aoqi and Zhang, Xindong and Zhang, Lei},
  journal={arXiv preprint arXiv:2602.11543},
  year={2026}
}

Downloads last month: 29

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for zjr2000/SPES-2B

Quantizations

2 models

Collection including zjr2000/SPES-2B

SPES

Collection

Pretrained models for paper "Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm" • 3 items • Updated Mar 9

Paper for zjr2000/SPES-2B

Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm

Paper • 2602.11543 • Published Feb 12 • 6