Instructions to use akahoush/dhdna-profiler-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use akahoush/dhdna-profiler-v2 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-v2")

Transformers

How to use akahoush/dhdna-profiler-v2 with Transformers:

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

pipe = pipeline("text-generation", model="akahoush/dhdna-profiler-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("akahoush/dhdna-profiler-v2", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use akahoush/dhdna-profiler-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "akahoush/dhdna-profiler-v2"
# 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-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/akahoush/dhdna-profiler-v2

SGLang

How to use akahoush/dhdna-profiler-v2 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-v2" \
    --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-v2",
		"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-v2" \
        --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-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use akahoush/dhdna-profiler-v2 with Docker Model Runner:
```
docker model run hf.co/akahoush/dhdna-profiler-v2
```

DHDNA Profiler v2 — Cognitive Profiling LoRA

A LoRA adapter fine-tuned on the Digital Human DNA (DHDNA) framework for cognitive profiling of historical figures and text analysis across 12 cognitive dimensions.

Model Details

Base Model: Qwen/Qwen2.5-3B-Instruct (3B params, Apache 2.0)
Adapter: LoRA r=16, alpha=16, dropout=0.05
Training: 95 examples (65 genius profiles + 30 scoring examples), 3 epochs, 36 steps
GPU: Kaggle T4 x2 (free tier), float16, 6.4 GB VRAM
Training Time: 525s (~9 min)
Training Loss: 2.41 → 1.22 (final step)
Cost: $0

v2 Improvements over v1

Metric	v1	v2
Training examples	53	95 (+79%)
Dimensions parsed	12/60	58/60 (97%)
Shakespeare MAE	inf (POOR)	0.79 (EXCELLENT)
Final step loss	1.46	1.22
Domains covered	5	8+

Ground Truth Evaluation (5 Subjects)

Subject	Domain	MAE	Grade
Tesla	STEM/Engineering	1.58	FAIR
Shakespeare	Arts/Literature	0.79	EXCELLENT
Lincoln	Politics/Leadership	2.60	POOR
Confucius	Philosophy/Ethics	1.92	FAIR
Napoleon	Military/Strategy	1.42	GOOD
GLOBAL	5 domains	1.63	FAIR

The 12 DHDNA Dimensions

Analytical Depth — Systematic, proof-oriented reasoning
Creative Range — Paradigm-breaking creative bandwidth
Emotional Processing — Emotional richness and expression
Linguistic Precision — Architecturally complex communication
Ethical Reasoning — Principle-driven moral framework
Strategic Thinking — Multi-move, game-theoretic planning
Memory Integration — Deep historical awareness and synthesis
Social Intelligence — Coalition-building and social navigation
Domain Expertise — Deep specialist knowledge
Intuitive Reasoning — Insight-driven pattern recognition
Temporal Orientation — Time-spanning awareness
Metacognition — Thinking about thinking

Research

DHDNA Framework: DOI 10.5281/zenodo.18736629
What-If Oracle: DOI 10.5281/zenodo.18736841
IP Portfolio: DOI 10.5281/zenodo.19076505

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct", torch_dtype="float16")
model = PeftModel.from_pretrained(base, "akahoush/dhdna-profiler-v2")
tokenizer = AutoTokenizer.from_pretrained("akahoush/dhdna-profiler-v2")

Developed by

AHK Strategies — ahkstrategies.net | themindbook.app

Built by ERIC (Empire Research & Intelligence Commander) for Commander Ashraf H. Kahoush.

License: CC-BY-NC-4.0

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-v2

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Adapter

(1285)

this model

Paper for akahoush/dhdna-profiler-v2

Quantifying the Carbon Emissions of Machine Learning

Paper • 1910.09700 • Published Oct 21, 2019 • 50