Instructions to use zjr2000/SPES-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zjr2000/SPES-7B with Transformers:

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

pipe = pipeline("text-generation", model="zjr2000/SPES-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zjr2000/SPES-7B")
model = AutoModelForCausalLM.from_pretrained("zjr2000/SPES-7B")
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-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zjr2000/SPES-7B"
# 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-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zjr2000/SPES-7B

SGLang

How to use zjr2000/SPES-7B 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-7B" \
    --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-7B",
		"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-7B" \
        --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-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zjr2000/SPES-7B with Docker Model Runner:
```
docker model run hf.co/zjr2000/SPES-7B
```

Add library_name and improve model card

by nielsr HF Staff - opened 22 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+26

-17

Files changed (1) hide show

README.md +26 -17

README.md CHANGED Viewed

@@ -1,5 +1,9 @@
 ---
 license: apache-2.0
 tags:
 - moe
 - mixture-of-experts
@@ -8,46 +12,51 @@ tags:
 - distributed-training
 - decentralized-training
 - sparse-sync
-language:
-- en
-pipeline_tag: text-generation
 ---
 # SPES-7B
-SPES-7B is a pretrained language model released as part of paper:
-**Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm**
 ## Model Details
 - **Model name:** SPES-7B
-- **Model type:** Causal language model
 - **Parameters:** 7B
 - **Framework:** SPES
 - **License:** Apache-2.0
-## 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 MoE training and synchronization
-- experimentation and evaluation of pretrained language models
 ## Citation
-If you use this model, please cite the SPES paper.
 ```bibtex
-@article{zhang2026spes,
   title={Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm},
   author={Zhang, Jinrui and Xiao, Chaodong and Wu, Aoqi and Zhang, Xindong and Zhang, Lei},
   year={2026}
-}

 ---
+language:
+- en
 license: apache-2.0
+pipeline_tag: text-generation
+library_name: transformers
 tags:
 - moe
 - mixture-of-experts
 - distributed-training
 - decentralized-training
 - sparse-sync
 ---
 # SPES-7B
+SPES-7B is a 7B-parameter Mixture-of-Experts (MoE) Large Language Model pretrained using **SPES** (**SP**arse **E**xpert **S**ync), a memory-efficient decentralized training framework.
+This model was introduced in the paper: [Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm](https://huggingface.co/papers/2602.11543).
+**Authors:** Jinrui Zhang, Chaodong Xiao, Aoqi Wu, Xindong Zhang, Lei Zhang.
 ## Model Details
 - **Model name:** SPES-7B
+- **Model type:** Causal language model (MoE)
 - **Parameters:** 7B
+- **Architecture:** Olmoe
 - **Framework:** SPES
 - **License:** Apache-2.0
+## Introduction
+SPES (SParse Expert Sync) is designed for pretraining MoE LLMs across geographically distributed GPU nodes. It addresses memory and bandwidth constraints by training only a subset of experts per node, significantly lowering the individual memory footprint and eliminating the need for full-parameter transmission. SPES-7B achieves competitive performance with centrally trained models under similar computational budgets.
+## Project Links
+- **GitHub:** [zjr2000/SPES](https://github.com/zjr2000/SPES)
+- **Paper (arXiv):** [2602.11543](https://arxiv.org/abs/2602.11543)
+- **Model Collection:** [SPES Collection](https://huggingface.co/collections/zjr2000/spes)
+## Intended Use
+This model is intended for research on:
+- Decentralized LLM pretraining paradigms.
+- Mixture-of-Experts (MoE) training and synchronization.
+- Evaluation of pretrained language models trained under constrained bandwidth conditions.
 ## Citation
+If you use this model, please cite the SPES paper:
 ```bibtex
+@article{zhang2026pretraining,
   title={Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm},
   author={Zhang, Jinrui and Xiao, Chaodong and Wu, Aoqi and Zhang, Xindong and Zhang, Lei},
+  journal={arXiv preprint arXiv:2602.11543},
   year={2026}
+}
+```