Solar Open 100B

temperature=0.8
top_p=0.95
top_k=50

pip install -U "transformers>=5.0" kernels torch accelerate

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

MODEL_ID = "upstage/Solar-Open-100B"

# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)

model = AutoModelForCausalLM.from_pretrained(
    pretrained_model_name_or_path=MODEL_ID,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

# Prepare input
messages = [{"role": "user", "content": "who are you?"}]
inputs = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt",
)
inputs = inputs.to(model.device)

# Generate response
generated_ids = model.generate(
    **inputs,
    max_new_tokens=4096,
    temperature=0.8,
    top_p=0.95,
    top_k=50,
    do_sample=True,
)
generated_text = tokenizer.decode(generated_ids[0][inputs.input_ids.shape[1] :])
print(generated_text)

# For 8 GPUs
docker run --gpus all \
    --ipc=host \
    -p 8000:8000 \
    upstage/vllm-solar-open:latest \
    upstage/Solar-Open-100B \
    --trust-remote-code \
    --enable-auto-tool-choice \
    --tool-call-parser solar_open \
    --reasoning-parser solar_open \
    --logits-processors vllm.model_executor.models.parallel_tool_call_logits_processor:ParallelToolCallLogitsProcessor \
    --logits-processors vllm.model_executor.models.solar_open_logits_processor:SolarOpenTemplateLogitsProcessor \
    --tensor-parallel-size 8

uv venv --python 3.12 --seed
source .venv/bin/activate

VLLM_PRECOMPILED_WHEEL_LOCATION="https://github.com/vllm-project/vllm/releases/download/v0.12.0/vllm-0.12.0-cp38-abi3-manylinux_2_31_x86_64.whl" \
VLLM_USE_PRECOMPILED=1 \
uv pip install git+https://github.com/UpstageAI/[email protected]

vllm serve upstage/Solar-Open-100B \
    --trust-remote-code \
    --enable-auto-tool-choice \
    --tool-call-parser solar_open \
    --reasoning-parser solar_open \
    --logits-processors vllm.model_executor.models.parallel_tool_call_logits_processor:ParallelToolCallLogitsProcessor \
    --logits-processors vllm.model_executor.models.solar_open_logits_processor:SolarOpenTemplateLogitsProcessor \
    --tensor-parallel-size 8

@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}
}