Instructions to use upstage/Solar-Open-100B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use upstage/Solar-Open-100B with Transformers:

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

pipe = pipeline("text-generation", model="upstage/Solar-Open-100B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("upstage/Solar-Open-100B")
model = AutoModelForCausalLM.from_pretrained("upstage/Solar-Open-100B")
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 Settings

vLLM

How to use upstage/Solar-Open-100B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "upstage/Solar-Open-100B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "upstage/Solar-Open-100B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/upstage/Solar-Open-100B

SGLang

How to use upstage/Solar-Open-100B 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 "upstage/Solar-Open-100B" \
    --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": "upstage/Solar-Open-100B",
		"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 "upstage/Solar-Open-100B" \
        --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": "upstage/Solar-Open-100B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use upstage/Solar-Open-100B with Docker Model Runner:
```
docker model run hf.co/upstage/Solar-Open-100B
```

Link model card to technical report and project page

#22

by nielsr HF Staff - opened Jan 15

base: refs/heads/main

←

from: refs/pr/22

Discussion Files changed

+12

-8

Files changed (1) hide show

README.md +12 -8

README.md CHANGED Viewed

@@ -2,16 +2,17 @@
 language:
 - en
 - ko
 license: other
 license_name: solar-apache-2.0
 tags:
 - upstage
 - solar
 - moe
 - 100b
 - llm
-library_name: transformers
-pipeline_tag: text-generation
 ---
 <p align="center">
@@ -22,6 +23,8 @@ pipeline_tag: text-generation
 **Solar Open** is Upstage's flagship **102B-parameter** large language model, trained **entirely from scratch** and released under the **Solar-Apache License 2.0** (see [LICENSE](#license) for details). As a **Mixture-of-Experts (MoE)** architecture, it delivers enterprise-grade performance in reasoning, instruction-following, and agentic capabilities—all while prioritizing transparency and customization for the open-source community.
 ## Highlights
 * **MoE Architecture (102B / 12B):** Built on a Mixture-of-Experts architecture with **102B total / 12B active parameters**. This design delivers the knowledge depth of a massive model with the inference speed and cost-efficiency of a much smaller model.
@@ -42,7 +45,7 @@ pipeline_tag: text-generation
 * **Hardware Requirements:**
     * **Minimum:** 4x NVIDIA A100 (80GB)
-For more details, please refer to [Solar Open Technical Report](solar-open-technical-report.pdf).
 ## License
 This repository contains both model weights and code,
@@ -222,10 +225,11 @@ The official API service for Solar Open is scheduled to launch publicly on **Jan
 If you use Solar Open in your research, please cite:
 ```bibtex
-@misc{solar-open-2025,
-    title={Solar Open: Scaling Upstage's LLM Capabilities with MoE},
-    author={Upstage AI},
-    year={2025},
-    url={https://huggingface.co/Upstage/Solar-Open-100B}
 }
 ```

 language:
 - en
 - ko
+library_name: transformers
 license: other
 license_name: solar-apache-2.0
+pipeline_tag: text-generation
 tags:
 - upstage
 - solar
 - moe
 - 100b
 - llm
+arxiv: 2601.07022
 ---
 <p align="center">
 **Solar Open** is Upstage's flagship **102B-parameter** large language model, trained **entirely from scratch** and released under the **Solar-Apache License 2.0** (see [LICENSE](#license) for details). As a **Mixture-of-Experts (MoE)** architecture, it delivers enterprise-grade performance in reasoning, instruction-following, and agentic capabilities—all while prioritizing transparency and customization for the open-source community.
+[**Technical Report**](https://huggingface.co/papers/2601.07022) | [**Project Page**](https://upstage.ai)
 ## Highlights
 * **MoE Architecture (102B / 12B):** Built on a Mixture-of-Experts architecture with **102B total / 12B active parameters**. This design delivers the knowledge depth of a massive model with the inference speed and cost-efficiency of a much smaller model.
 * **Hardware Requirements:**
     * **Minimum:** 4x NVIDIA A100 (80GB)
+For more details, please refer to the [Solar Open Technical Report](https://huggingface.co/papers/2601.07022).
 ## License
 This repository contains both model weights and code,
 If you use Solar Open in your research, please cite:
 ```bibtex
+@article{park2025solar,
+  title={Solar Open Technical Report},
+  author={Sungrae Park and Sanghoon Kim and Jungho Cho and Gyoungjin Gim and Dawoon Jung and Mikyoung Cha and Eunhae Choo and Taekgyu Hong and Minbyul Jeong and SeHwan Joo and Minsoo Khang and Eunwon Kim and Minjeong Kim and Sujeong Kim and Yunsu Kim and Hyeonju Lee and Seunghyun Lee and Sukyung Lee and Siyoung Park and Gyungin Shin and Inseo Song and Wonho Song and Seonghoon Yang and Seungyoun Yi and Sanghoon Yoon and Jeonghyun Ko and Seyoung Song and Keunwoo Choi and Hwalsuk Lee and Sunghun Kim and Du-Seong Chang and Kyunghyun Cho and Junsuk Choe and Hwaran Lee and Jae-Gil Lee and KyungTae Lim and Alice Oh},
+  journal={arXiv preprint arXiv:2601.07022},
+  year={2025},
+  url={https://huggingface.co/papers/2601.07022}
 }
 ```