Instructions to use heziss666/ScholarNavigator-query-rewriter-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use heziss666/ScholarNavigator-query-rewriter-adapter with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "heziss666/ScholarNavigator-query-rewriter-adapter")

Transformers

How to use heziss666/ScholarNavigator-query-rewriter-adapter with Transformers:

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

pipe = pipeline("text-generation", model="heziss666/ScholarNavigator-query-rewriter-adapter")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("heziss666/ScholarNavigator-query-rewriter-adapter", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use heziss666/ScholarNavigator-query-rewriter-adapter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "heziss666/ScholarNavigator-query-rewriter-adapter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "heziss666/ScholarNavigator-query-rewriter-adapter",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/heziss666/ScholarNavigator-query-rewriter-adapter

SGLang

How to use heziss666/ScholarNavigator-query-rewriter-adapter 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 "heziss666/ScholarNavigator-query-rewriter-adapter" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "heziss666/ScholarNavigator-query-rewriter-adapter",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "heziss666/ScholarNavigator-query-rewriter-adapter" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "heziss666/ScholarNavigator-query-rewriter-adapter",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use heziss666/ScholarNavigator-query-rewriter-adapter with Docker Model Runner:
```
docker model run hf.co/heziss666/ScholarNavigator-query-rewriter-adapter
```

ScholarNavigator Query Rewriter Adapter

该 Adapter 用于把结构化科研需求补充为适合 arXiv/OpenAlex 双源检索的英文查询候选，并与规则查询经过约束校验、预算选择和去重后共同执行。

基本信息

基座模型：Qwen2.5-7B-Instruct；
参数高效方法：LoRA；
冻结检查点：checkpoint-204；
训练配置：Profile B，Seed 2026；
任务类型：因果语言模型文本生成。

下载

hf download heziss666/ScholarNavigator-query-rewriter-adapter \
  --local-dir models/ScholarNavigator-query-rewriter-adapter

基座模型需另行下载到 models/Qwen2.5-7B-Instruct，随后使用 ScholarNavigator 项目入口加载。

权重校验

adapter_model.safetensors
SHA-256: 8763c0dcb675df2b9233e1d07722831f81b1b37da7ee841e43d226105ada6fa6
size: 323014168 bytes

限制

模型只负责生成补充检索式，最终结果仍须经过规则约束、双源检索、融合去重和语义保护重排；生成文本不应直接视为论文事实或检索结果。

Downloads last month: 29

Model tree for heziss666/ScholarNavigator-query-rewriter-adapter

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Adapter

(2610)

this model