sii-research/InnoSpark-HPC-RM-32B

from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained(
    "sii-research/InnoSpark-72B-0710",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("sii-research/InnoSpark-72B-0710")

prompt = "Introduce yourself in detail."
messages = [
    {"role": "system", "content": "You are InnoSpark（启创）, created by Shanghai Innovation Institute （上海创智学院） and East China Normal University(华东师范大学). You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)

generated_ids = model.generate(
    model_inputs.input_ids,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

python -m vllm.entrypoints.openai.api_server --served-model-name InnoSpark --model path/to/InnoSpark --gpu-memory-utilization 0.98 --tensor-parallel-size 4 --port 6000

import requests
import json

def Innospark_stream(inputs,history):
    url = 'http://loaclhost:6000/v1/chat/completions'

    history+=[{"role": "user", "content": inputs},]

    headers = {"User-Agent": "vLLM Client"}

    pload = {
        "model": "InnoSpark",
        "stream": True,
        "messages": history
    }
    response = requests.post(url,
                             headers=headers,
                             json=pload,
                             stream=True)

    for chunk in response.iter_lines(chunk_size=1,
                                     decode_unicode=False,
                                     delimiter=b"\n"):
        if chunk:
            string_data = chunk.decode("utf-8")
            try:
                json_data = json.loads(string_data[6:])
                delta_content = json_data["choices"][0]["delta"]["content"]
                assistant_reply+=delta_content
                yield delta_content
            except KeyError as e:
                delta_content = json_data["choices"][0]["delta"]["role"]
            except json.JSONDecodeError as e:
                history+=[{
                        "role": "assistant",
                        "content": assistant_reply,
                        "tool_calls": []
                    },]
                delta_content='[DONE]'
                assert '[DONE]'==chunk.decode("utf-8")[6:]

inputs='hi'
history=[]
for response_text in Innospark_stream(inputs,history):
    print(response_text,end='')

@misc{song2025cultivatinghelpfulpersonalizedcreative,
      title={Cultivating Helpful, Personalized, and Creative AI Tutors: A Framework for Pedagogical Alignment using Reinforcement Learning}, 
      author={Siyu Song and Wentao Liu and Ye Lu and Ruohua Zhang and Tao Liu and Jinze Lv and Xinyun Wang and Aimin Zhou and Fei Tan and Bo Jiang and Hao Hao},
      year={2025},
      eprint={2507.20335},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2507.20335}, 
}

@misc{wei2025elmesautomatedframeworkevaluating,
      title={ELMES: An Automated Framework for Evaluating Large Language Models in Educational Scenarios}, 
      author={Shou'ang Wei and Xinyun Wang and Shuzhen Bi and Jian Chen and Ruijia Li and Bo Jiang and Xin Lin and Min Zhang and Yu Song and BingDong Li and Aimin Zhou and Hao Hao},
      year={2025},
      eprint={2507.22947},
      archivePrefix={arXiv},
      primaryClass={cs.CY},
      url={https://arxiv.org/abs/2507.22947}, 
}