Instructions to use GGUFGuy/hyperdex-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GGUFGuy/hyperdex-test with Transformers:

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

pipe = pipeline("text-generation", model="GGUFGuy/hyperdex-test")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GGUFGuy/hyperdex-test")
model = AutoModelForCausalLM.from_pretrained("GGUFGuy/hyperdex-test", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GGUFGuy/hyperdex-test with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/GGUFGuy/hyperdex-test

SGLang

How to use GGUFGuy/hyperdex-test 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 "GGUFGuy/hyperdex-test" \
    --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": "GGUFGuy/hyperdex-test",
		"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 "GGUFGuy/hyperdex-test" \
        --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": "GGUFGuy/hyperdex-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use GGUFGuy/hyperdex-test with Docker Model Runner:
```
docker model run hf.co/GGUFGuy/hyperdex-test
```

hyperdex-test

File size: 2,003 Bytes

da3d0c4

---
license: odc-by
datasets:
  - HuggingFaceFW/fineweb-edu
language:
  - en
library_name: transformers
pipeline_tag: text-generation
tags:
  - nanodex
  - tiny-lm
  - pretrained-from-scratch
---

# hyperdex-test

A **1,000,224-parameter** decoder-only language model pre-trained
**from scratch** on [fineweb-edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu),
using the [NanoDex Trainer](https://huggingface.co/spaces/hugging-science/nanodex-trainer) Space.

## Architecture

A standard `LlamaForCausalLM` decoder-only transformer — SiLU MLP, RMSNorm,
rotary position embeddings, grouped-query attention, tied embeddings, no biases —
scaled down in width and depth to fit the parameter budget.

| | |
|---|---|
| Parameters | 1,000,224 |
| Hidden size | 96 |
| Layers | 5 |
| Attention heads | 6 (KV: 2) |
| FFN size | 472 |
| Context length | 512 |
| Vocab | 2,048 (custom BPE trained on fineweb-edu) |

## Training

| | |
|---|---|
| Tokens seen | 299,892,736 |
| Steps | 2,288 |
| Tokens / step | 131,072 |
| Optimizer | AdamW(0.9, 0.95) wd=0.1 clip=1.0 |
| LR schedule | warmup 2% + cosine to 10% (peak 3e-03) |
| Final loss | 3.5412 (ppl 34.5) |
| Wall time | 14.7 min |
| Trained by | [@GGUFGuy](https://huggingface.co/GGUFGuy) |

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("GGUFGuy/hyperdex-test")
model = AutoModelForCausalLM.from_pretrained("GGUFGuy/hyperdex-test")

ids = tok("The mitochondria is", return_tensors="pt").input_ids
print(tok.decode(model.generate(ids, max_new_tokens=60, do_sample=True,
                                temperature=0.8, top_k=50)[0]))
```

## Caveats

This is a **nano-scale research artifact**. At this parameter count and token
budget the model learns word shapes, common collocations and a little syntax —
it is not a useful assistant and its output is not factual. It exists to make
"pre-train a transformer from scratch" something you can actually watch happen.