Instructions to use bhxdianzhang/ParaDesigner-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bhxdianzhang/ParaDesigner-SFT with Transformers:

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

pipe = pipeline("text-generation", model="bhxdianzhang/ParaDesigner-SFT")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("bhxdianzhang/ParaDesigner-SFT")
model = AutoModelForMultimodalLM.from_pretrained("bhxdianzhang/ParaDesigner-SFT", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bhxdianzhang/ParaDesigner-SFT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/bhxdianzhang/ParaDesigner-SFT

SGLang

How to use bhxdianzhang/ParaDesigner-SFT 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 "bhxdianzhang/ParaDesigner-SFT" \
    --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": "bhxdianzhang/ParaDesigner-SFT",
		"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 "bhxdianzhang/ParaDesigner-SFT" \
        --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": "bhxdianzhang/ParaDesigner-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bhxdianzhang/ParaDesigner-SFT with Docker Model Runner:
```
docker model run hf.co/bhxdianzhang/ParaDesigner-SFT
```

ParaDesigner-SFT / README.md

bhxdianzhang

Upload ParaDesigner-SFT model card and final weights

ea420d1 verified 3 months ago

preview code

Raw History Blame

6.74 kB

metadata

license: other
library_name: transformers
base_model: Qwen/Qwen3.5-4B
language:
  - zh
  - en
tags:
  - paradoxgpt
  - designer
  - sft
  - supervised-fine-tuning
  - scientific-writing
  - research-agents
  - qwen
pipeline_tag: text-generation
model-index:
  - name: ParaDesigner-SFT
    results:
      - task:
          type: text-generation
          name: Designer specialist modeling
        dataset:
          name: ParaSFT-designer
          type: bhxdianzhang/ParaSFT-designer
        metrics:
          - type: loss
            value: 0.9128507972
            name: eval_loss

ParaDesigner-SFT

English | 中文

Overview

ParaDesigner-SFT is a private ParadoxGPT Designer specialist model fine-tuned from a Qwen 4B base model. It is designed for research-paper workflows rather than general chat.

Intended Use

Use ParaDesigner-SFT for:

paper-level scientific writing and review-support workflows;
converting paper context into structured reasoning traces;
internal ParadoxGPT research-agent training and evaluation;
assisting human researchers with evidence, argumentation, and risk analysis.

Outputs should be checked against the original paper context. This model is not a substitute for human scientific judgment.

Training Data

The model was supervised-fine-tuned on private dataset bhxdianzhang/ParaSFT-designer.

Split	Samples
Train	35,389
Dev	2,062
Test	2,296
Total	39,747

Task distribution:

Task type	Samples
`D1_claim_to_evidence`	7,954
`D2_experiment_argument_plan`	7,951
`D3_ablation_analysis_design`	7,942
`D4_sufficiency_critique`	7,944
`D5_interpretation_boundary`	7,956

Quality filter: each target answer contains exactly one balanced <think>...</think> reasoning block followed by the final answer.

Training Summary

Base model: Qwen 4B local base model.

Field	Value
Epochs	3.0
Learning rate	3e-6
Scheduler	cosine
Distributed devices	2
Gradient accumulation	8
Total train batch size	16
Final train loss	0.8653310693
Final eval loss	0.9128507972

Qualitative Behavior

Local side-by-side checks show strong task alignment across D1-D5. Compared with the same 4B backbone before SFT, ParaDesigner-SFT is much more concise, more Chinese-final-answer focused, and better at turning claims into evidence plans, experiment argumentation, ablation/mechanism needs, sufficiency critiques, and interpretation boundaries.

ParaDesigner-SFT is best used with rich paper context matching the training shape, such as title, abstract, introduction, selected body sections, figure/table captions, claims, reviews, or task-specific paper context depending on the skill.

Example Prompt Shape

你是顶会论文分析专家。给定论文上下文，请按指定任务做中文分析。

论文标题: ...

摘要: ...

引言: ...

正文关键片段: ...

图表/实验/claim 信息: ...

任务: ...

Limitations

The model is optimized for a narrow ParadoxGPT specialist workflow, not general chat.
It may inherit teacher-model annotation errors from the SFT data.
It should not be used as an authority on paper correctness without source verification.

License and Use Restrictions

This repository is marked with license: other.

The model was trained on private ParadoxGPT SFT data derived from parsed academic papers, reviews, and teacher annotations. Rights to original papers and reviews remain with their respective authors, reviewers, venues, and publishers. This private model is provided for internal research and engineering use only. Redistribution or public release should be reviewed separately against source venue policies and applicable copyright rules.

Citation

@model{zhang2026paradesignersft,
  title        = {ParaDesigner-SFT: A ParadoxGPT Designer Specialist Model},
  author       = {Heng Zhang},
  year         = {2026},
  publisher    = {Hugging Face},
  howpublished = {https://huggingface.co/bhxdianzhang/ParaDesigner-SFT},
  note         = {Private ParadoxGPT supervised fine-tuned Designer model}
}

中文

概述

ParaDesigner-SFT 是 ParadoxGPT 的 Designer 专家模型，由 Qwen 4B 基座监督微调而来。它面向科研论文工作流，不是通用聊天模型。

适用场景

ParaDesigner-SFT 适合用于：

论文级科研写作与 review-support 工作流；
将论文上下文转成结构化 reasoning trace；
ParadoxGPT 内部 research-agent 训练与评测；
辅助研究者做证据、论证和风险分析。

输出应结合原论文上下文复核，不能替代人类科研判断。

训练数据

模型使用私有数据集 bhxdianzhang/ParaSFT-designer 进行监督微调。

Split	样本数
Train	35,389
Dev	2,062
Test	2,296
Total	39,747

任务分布：

Task type	Samples
`D1_claim_to_evidence`	7,954
`D2_experiment_argument_plan`	7,951
`D3_ablation_analysis_design`	7,942
`D4_sufficiency_critique`	7,944
`D5_interpretation_boundary`	7,956

质量过滤：每条目标答案都包含且只包含一个配平的 <think>...</think> 思考块，后接最终答案。

训练摘要

基座模型：本地 Qwen 4B base model。

字段	数值
Epochs	3.0
Learning rate	3e-6
Scheduler	cosine
分布式设备数	2
Gradient accumulation	8
Total train batch size	16
Final train loss	0.8653310693
Final eval loss	0.9128507972

定性行为

本地 side-by-side 检查显示，ParaDesigner-SFT 在 D1-D5 上任务对齐稳定。相比同一 4B backbone 的 SFT 前模型，它更收敛、更聚焦中文最终答案，也更擅长把 claim 转成证据规划、实验论证、消融/机制分析需求、充分性批判和解释边界。

为了获得最佳效果，请使用与训练数据一致的丰富论文上下文，例如 title、abstract、introduction、正文关键片段、figure/table captions、claims、reviews 或具体任务所需的 paper context。

局限

模型针对 ParadoxGPT 窄域专家工作流优化，不是通用聊天模型。
模型可能继承 SFT 数据中的 teacher-model 标注误差。
不应在未检查原论文上下文的情况下，把输出当成科研事实。

引用

@model{zhang2026paradesignersft,
  title        = {ParaDesigner-SFT: A ParadoxGPT Designer Specialist Model},
  author       = {Heng Zhang},
  year         = {2026},
  publisher    = {Hugging Face},
  howpublished = {https://huggingface.co/bhxdianzhang/ParaDesigner-SFT},
  note         = {Private ParadoxGPT supervised fine-tuned Designer model}
}