Instructions to use akahoush/dhdna-profiler-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use akahoush/dhdna-profiler-v1 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "akahoush/dhdna-profiler-v1")

Transformers

How to use akahoush/dhdna-profiler-v1 with Transformers:

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

pipe = pipeline("text-generation", model="akahoush/dhdna-profiler-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("akahoush/dhdna-profiler-v1", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use akahoush/dhdna-profiler-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/akahoush/dhdna-profiler-v1

SGLang

How to use akahoush/dhdna-profiler-v1 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 "akahoush/dhdna-profiler-v1" \
    --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": "akahoush/dhdna-profiler-v1",
		"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 "akahoush/dhdna-profiler-v1" \
        --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": "akahoush/dhdna-profiler-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use akahoush/dhdna-profiler-v1 with Docker Model Runner:
```
docker model run hf.co/akahoush/dhdna-profiler-v1
```

DHDNA Profiler v1 — LoRA Adapter

The first cognitive profiling model trained on the Digital Human DNA (DHDNA) framework.

This is a LoRA adapter fine-tuned on Qwen 2.5-3B-Instruct to generate 12-dimensional cognitive profiles of historical figures using the DHDNA framework.

Model Details

Base model: Qwen/Qwen2.5-3B-Instruct (3B params, Apache 2.0)
Fine-tuning: LoRA (r=16, alpha=16, dropout=0.05)
Training data: 53 examples (40 genius profiles + 13 scoring examples) across 8 domains
Training: 3 epochs, 21 steps, ~5 min on Kaggle T4 GPU
Loss: 2.44 → 1.46 (40% drop)
Evaluation: Global MAE 1.38 (GOOD) across 5 ground truth subjects
Developed by: AHK Strategies (ERIC)
License: CC-BY-NC-4.0

The 12 DHDNA Dimensions

#	Dimension	Low (1-3)	High (8-10)
1	Analytical Depth	Intuitive, holistic	Systematic, proof-oriented
2	Creative Range	Conventional	Paradigm-breaking
3	Emotional Processing	Detached, clinical	Emotionally rich
4	Linguistic Precision	Simple, direct	Architecturally complex
5	Ethical Reasoning	Pragmatic	Principle-driven
6	Strategic Thinking	Tactical, reactive	Multi-move, game-theoretic
7	Memory Integration	Present-focused	Deep historical awareness
8	Social Intelligence	Self-referential	Coalition-building
9	Domain Expertise	Generalist	Deep specialist
10	Intuitive Reasoning	Methodical	Insight-driven
11	Temporal Orientation	Present-anchored	Time-spanning
12	Metacognition	Unreflective	Thinks about thinking

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

base_model = "Qwen/Qwen2.5-3B-Instruct"
adapter = "akahoush/dhdna-profiler-v1"

tokenizer = AutoTokenizer.from_pretrained(base_model)
model = AutoModelForCausalLM.from_pretrained(base_model, device_map="auto", torch_dtype="auto")
model = PeftModel.from_pretrained(model, adapter)

messages = [
    {"role": "system", "content": "You are a DHDNA cognitive profiler. You analyze historical figures using the Digital Human DNA (DHDNA) framework — 12 cognitive dimensions scored 1.0 to 10.0."},
    {"role": "user", "content": "Profile Nikola Tesla on all 12 DHDNA cognitive dimensions."},
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=2048, temperature=0.7, top_p=0.9)

print(tokenizer.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))

Evaluation Results (v1)

Subject	Domain	MAE	Grade
Tesla	STEM/Engineering	1.62	FAIR
Lincoln	Politics/Leadership	1.00	GOOD
Confucius	Philosophy/Ethics	0.00	EXCELLENT
Napoleon	Military/Strategy	1.75	FAIR
Global	All domains	1.38	GOOD

Training Domains

STEM, Arts/Literature, Politics/Leadership, Philosophy/Ethics, Military/Strategy, Business/Innovation, Civil Rights, History/Governance

Limitations

v1 is trained on only 53 examples — scores may be approximate
Model sometimes uses variant dimension names (e.g., "Creative Flexibility" instead of "Creative Range")
Best for well-documented historical figures; less reliable for living people or obscure figures
English only

Next Steps (v2)

95+ training examples (Wave 3 data ready)
Improved regex score extraction
More diverse cultural representation
Target: Global MAE < 1.0

Citation

@misc{kahoush2025dhdna,
  title={Digital Human DNA (DHDNA): A 12-Dimensional Cognitive Profiling Framework},
  author={Kahoush, Ashraf H.},
  year={2025},
  doi={10.5281/zenodo.18736629},
  publisher={Zenodo}
}

base_model: Qwen/Qwen2.5-3B-Instruct library_name: peft pipeline_tag: text-generation tags: - base_model:adapter:Qwen/Qwen2.5-3B-Instruct - lora - sft - transformers - trl

Model Card for Model ID

Model Details

Model Description

Developed by: [More Information Needed]
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Model type: [More Information Needed]
Language(s) (NLP): [More Information Needed]
License: [More Information Needed]
Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

Repository: [More Information Needed]
Paper [optional]: [More Information Needed]
Demo [optional]: [More Information Needed]

Uses

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: [More Information Needed]
Hours used: [More Information Needed]
Cloud Provider: [More Information Needed]
Compute Region: [More Information Needed]
Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Framework versions

PEFT 0.18.1

Downloads last month: -

Model tree for akahoush/dhdna-profiler-v1

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Adapter

(1284)

this model

Paper for akahoush/dhdna-profiler-v1

Quantifying the Carbon Emissions of Machine Learning

Paper • 1910.09700 • Published Oct 21, 2019 • 50

DHDNA Profiler v1 — LoRA Adapter

Model Details

The 12 DHDNA Dimensions

Usage

Evaluation Results (v1)

Training Domains

Limitations

Next Steps (v2)

Citation

Links

base_model: Qwen/Qwen2.5-3B-Instruct library_name: peft pipeline_tag: text-generation tags: - base_model:adapter:Qwen/Qwen2.5-3B-Instruct - lora - sft - transformers - trl

Model Card for Model ID

Model Details

Model Description

Model Sources [optional]

Uses

Direct Use

Downstream Use [optional]

Out-of-Scope Use

Bias, Risks, and Limitations

Recommendations

How to Get Started with the Model

Training Details

Training Data

Training Procedure

Preprocessing [optional]

Training Hyperparameters

Speeds, Sizes, Times [optional]

Evaluation

Testing Data, Factors & Metrics

Testing Data

Factors

Metrics

Results

Summary

Model Examination [optional]

Environmental Impact

Technical Specifications [optional]

Model Architecture and Objective

Compute Infrastructure

Hardware

Software

Citation [optional]

Glossary [optional]

More Information [optional]

Model Card Authors [optional]

Model Card Contact

Framework versions

Model tree for akahoush/dhdna-profiler-v1

Paper for akahoush/dhdna-profiler-v1