Instructions to use Premchan369/Q-TensorFormer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Premchan369/Q-TensorFormer with Transformers:

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

pipe = pipeline("text-generation", model="Premchan369/Q-TensorFormer", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Premchan369/Q-TensorFormer", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Premchan369/Q-TensorFormer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Premchan369/Q-TensorFormer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Premchan369/Q-TensorFormer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Premchan369/Q-TensorFormer

SGLang

How to use Premchan369/Q-TensorFormer 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 "Premchan369/Q-TensorFormer" \
    --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": "Premchan369/Q-TensorFormer",
		"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 "Premchan369/Q-TensorFormer" \
        --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": "Premchan369/Q-TensorFormer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Premchan369/Q-TensorFormer with Docker Model Runner:
```
docker model run hf.co/Premchan369/Q-TensorFormer
```

Q-TensorFormer / site /documentation.html

Premchandyadav369

feat(seo): maximize discoverability, Google Scholar metadata, interactive HF widget, LLM crawler schemas, zero em dashes, and one-click quickstart downloads

5175adb 10 days ago

Raw History Blame Contribute Delete

6.41 kB

<!DOCTYPE html>
<html lang="en">
<head>
  <meta charset="UTF-8">
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
  <title>Documentation, Setup &amp; API Reference - Q-TensorFormer</title>
  <meta name="description" content="Complete documentation, installation guide, and API reference for Q-TensorFormer across PyTorch, Hugging Face, GGUF, and ONNX.">
  <link rel="canonical" href="https://premchan369.github.io/Q-TensorFormer/documentation.html">
  
  <meta property="og:type" content="article">
  <meta property="og:site_name" content="Q-TensorFormer Research Project">
  <meta property="og:title" content="Documentation, Setup &amp; API Reference - Q-TensorFormer">
  <meta property="og:description" content="Turnkey installation, research API usage, and Hugging Face integration examples.">
  <meta property="og:url" content="https://premchan369.github.io/Q-TensorFormer/documentation.html">

  <script type="application/ld+json">
  {
    "@context": "https://schema.org",
    "@type": "TechArticle",
    "headline": "Q-TensorFormer API Reference and Usage Documentation",
    "description": "Comprehensive guide for PyTorch research API, Hugging Face AutoModel integration, and deployment tools.",
    "url": "https://premchan369.github.io/Q-TensorFormer/documentation.html",
    "author": { "@type": "Person", "name": "Premchand Yadav" },
    "datePublished": "2026-10-13"
  }
  </script>
  <link rel="stylesheet" href="assets/style.css">
</head>
<body>
  <header>
    <div class="header-container">
      <div class="logo">
        <a href="index.html"><span>Q-TensorFormer</span> Research</a>
      </div>
      <nav>
        <a href="index.html">Overview</a>
        <a href="architecture.html">Architecture</a>
        <a href="methodology.html">Methodology</a>
        <a href="benchmarks.html">Benchmarks</a>
        <a href="edge-inference.html">Edge Inference</a>
        <a href="training.html">Training</a>
        <a href="documentation.html" class="active">Docs & API</a>
        <a href="research.html">Research</a>
        <a href="limitations.html">Limitations</a>
        <a href="contributing.html">Contributing</a>
      </nav>
    </div>
  </header>

  <main class="container">
    <h1>Documentation &amp; API Reference</h1>
    <p class="lead">
      Q-TensorFormer provides two first-class API interfaces: the <strong>Research API</strong> in <code>src/</code> for closed-loop dynamic systems experiments, and the <strong>Hugging Face API</strong> for standard <code>AutoModelForCausalLM</code> pipelines.
    </p>

    <section>
      <h2>1. Installation</h2>
      <p>Clone the repository and install dependencies:</p>
      <pre><code>git clone https://huggingface.co/Premchan369/Q-TensorFormer
cd Q-TensorFormer
pip install -r requirements.txt</code></pre>
      <p>Dependencies: <code>torch >= 2.0.0</code>, <code>transformers >= 4.35.0</code>, <code>numpy >= 1.24.0</code>, <code>pytest >= 7.0.0</code>.</p>
    </section>

    <section>
      <h2>2. PyTorch Research API (src/)</h2>
      <p>Load the verified canonical checkpoint and perform inference:</p>
      <pre><code>import torch
from src.checkpoint import load_canonical_checkpoint
from src.tokenizer import QTensorFormerTokenizer

# 1. Load canonical tokenizer
tokenizer = QTensorFormerTokenizer.load("checkpoints/tokenizer/tokenizer.json")

# 2. Load canonical checkpoint with strict verification
model, info = load_canonical_checkpoint(
    "checkpoints/qtensorformer_canonical_trained.pt",
    strict=True,
    require_trained=True,
    tokenizer=tokenizer
)

# 3. Tokenize input text
prompt = "Transformer attention"
input_ids = torch.tensor([tokenizer.encode(prompt, add_bos=True)])

# 4. Generate with KV cache and deterministic greedy decoding
output_ids = model.generate(
    input_ids,
    max_new_tokens=15,
    do_sample=False,
    use_cache=True,
    eos_token_id=tokenizer.eos_token_id,
    pad_token_id=tokenizer.pad_token_id
)

print("Decoded Output:", tokenizer.decode(output_ids[0]))</code></pre>
    </section>

    <section>
      <h2>3. Hugging Face Transformers API</h2>
      <p>Use Q-TensorFormer with the standard Hugging Face pipeline:</p>
      <pre><code>from transformers import AutoConfig, AutoModelForCausalLM

# Load model from the canonical checkpoint directory
model_path = "checkpoints/hf_canonical_trained"
config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True)

# Generate using Hugging Face .generate()
import torch
prompt_ids = torch.tensor([[1, 25, 42, 10]])
generated = model.generate(prompt_ids, max_new_tokens=10, do_sample=False)
print("Generated Token IDs:", generated)</code></pre>
    </section>

    <section>
      <h2>4. Deployment &amp; Export Tools</h2>
      <div class="grid">
        <div class="card">
          <h3>GGUF v3 Binary Export</h3>
          <p>Export the model to Ollama / llama.cpp compatible GGUF format:</p>
          <pre><code>python qtensorformer_to_gguf.py \
  --checkpoint checkpoints/qtensorformer_canonical_trained.pt \
  --output qtensorformer.gguf \
  --strict</code></pre>
        </div>
        <div class="card">
          <h3>ONNX Graph Export</h3>
          <p>Export Tensor-Train linear layers to ONNX for edge runtime acceleration:</p>
          <pre><code>python export_onnx.py \
  --output qtensorformer.onnx \
  --batch_size 1 \
  --seq_len 32</code></pre>
        </div>
      </div>
    </section>

    <section>
      <h2>5. Running Unit Tests &amp; Smoke Tests</h2>
      <p>Verify that your environment matches our benchmark findings:</p>
      <pre><code># Run full pytest suite (94 passing tests)
pytest -v

# Run deterministic smoke test
python scripts/smoke_test.py</code></pre>
    </section>
  </main>

  <footer>
    <div class="footer-links">
      <a href="index.html">Home</a>
      <a href="architecture.html">Architecture</a>
      <a href="methodology.html">Methodology</a>
      <a href="benchmarks.html">Benchmarks</a>
      <a href="documentation.html">Docs</a>
      <a href="limitations.html">Limitations</a>
      <a href="sitemap.xml">Sitemap</a>
      <a href="llms.txt">llms.txt</a>
      <a href="https://huggingface.co/Premchan369/Q-TensorFormer">Hugging Face</a>
    </div>
    <p>&copy; 2026 Premchand Yadav. Licensed under Apache-2.0.</p>
  </footer>
</body>
</html>

	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="UTF-8">
	<meta name="viewport" content="width=device-width, initial-scale=1.0">
	<title>Documentation, Setup & API Reference - Q-TensorFormer</title>
	<meta name="description" content="Complete documentation, installation guide, and API reference for Q-TensorFormer across PyTorch, Hugging Face, GGUF, and ONNX.">
	<link rel="canonical" href="https://premchan369.github.io/Q-TensorFormer/documentation.html">

	<meta property="og:type" content="article">
	<meta property="og:site_name" content="Q-TensorFormer Research Project">
	<meta property="og:title" content="Documentation, Setup & API Reference - Q-TensorFormer">
	<meta property="og:description" content="Turnkey installation, research API usage, and Hugging Face integration examples.">
	<meta property="og:url" content="https://premchan369.github.io/Q-TensorFormer/documentation.html">

	<script type="application/ld+json">
	{
	"@context": "https://schema.org",
	"@type": "TechArticle",
	"headline": "Q-TensorFormer API Reference and Usage Documentation",
	"description": "Comprehensive guide for PyTorch research API, Hugging Face AutoModel integration, and deployment tools.",
	"url": "https://premchan369.github.io/Q-TensorFormer/documentation.html",
	"author": { "@type": "Person", "name": "Premchand Yadav" },
	"datePublished": "2026-10-13"
	}
	</script>
	<link rel="stylesheet" href="assets/style.css">
	</head>
	<body>
	<header>
	<div class="header-container">
	<div class="logo">
	<a href="index.html"><span>Q-TensorFormer</span> Research</a>
	</div>
	<nav>
	<a href="index.html">Overview</a>
	<a href="architecture.html">Architecture</a>
	<a href="methodology.html">Methodology</a>
	<a href="benchmarks.html">Benchmarks</a>
	<a href="edge-inference.html">Edge Inference</a>
	<a href="training.html">Training</a>
	<a href="documentation.html" class="active">Docs & API</a>
	<a href="research.html">Research</a>
	<a href="limitations.html">Limitations</a>
	<a href="contributing.html">Contributing</a>
	</nav>
	</div>
	</header>

	<main class="container">
	<h1>Documentation & API Reference</h1>
	<p class="lead">
	Q-TensorFormer provides two first-class API interfaces: the <strong>Research API</strong> in <code>src/</code> for closed-loop dynamic systems experiments, and the <strong>Hugging Face API</strong> for standard <code>AutoModelForCausalLM</code> pipelines.
	</p>

	<section>
	<h2>1. Installation</h2>
	<p>Clone the repository and install dependencies:</p>
	<pre><code>git clone https://huggingface.co/Premchan369/Q-TensorFormer
	cd Q-TensorFormer
	pip install -r requirements.txt</code></pre>
	<p>Dependencies: <code>torch >= 2.0.0</code>, <code>transformers >= 4.35.0</code>, <code>numpy >= 1.24.0</code>, <code>pytest >= 7.0.0</code>.</p>
	</section>

	<section>
	<h2>2. PyTorch Research API (src/)</h2>
	<p>Load the verified canonical checkpoint and perform inference:</p>
	<pre><code>import torch
	from src.checkpoint import load_canonical_checkpoint
	from src.tokenizer import QTensorFormerTokenizer

	# 1. Load canonical tokenizer
	tokenizer = QTensorFormerTokenizer.load("checkpoints/tokenizer/tokenizer.json")

	# 2. Load canonical checkpoint with strict verification
	model, info = load_canonical_checkpoint(
	"checkpoints/qtensorformer_canonical_trained.pt",
	strict=True,
	require_trained=True,
	tokenizer=tokenizer
	)

	# 3. Tokenize input text
	prompt = "Transformer attention"
	input_ids = torch.tensor([tokenizer.encode(prompt, add_bos=True)])

	# 4. Generate with KV cache and deterministic greedy decoding
	output_ids = model.generate(
	input_ids,
	max_new_tokens=15,
	do_sample=False,
	use_cache=True,
	eos_token_id=tokenizer.eos_token_id,
	pad_token_id=tokenizer.pad_token_id
	)

	print("Decoded Output:", tokenizer.decode(output_ids[0]))</code></pre>
	</section>

	<section>
	<h2>3. Hugging Face Transformers API</h2>
	<p>Use Q-TensorFormer with the standard Hugging Face pipeline:</p>
	<pre><code>from transformers import AutoConfig, AutoModelForCausalLM

	# Load model from the canonical checkpoint directory
	model_path = "checkpoints/hf_canonical_trained"
	config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
	model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True)

	# Generate using Hugging Face .generate()
	import torch
	prompt_ids = torch.tensor([[1, 25, 42, 10]])
	generated = model.generate(prompt_ids, max_new_tokens=10, do_sample=False)
	print("Generated Token IDs:", generated)</code></pre>
	</section>

	<section>
	<h2>4. Deployment & Export Tools</h2>
	<div class="grid">
	<div class="card">
	<h3>GGUF v3 Binary Export</h3>
	<p>Export the model to Ollama / llama.cpp compatible GGUF format:</p>
	<pre><code>python qtensorformer_to_gguf.py \
	--checkpoint checkpoints/qtensorformer_canonical_trained.pt \
	--output qtensorformer.gguf \
	--strict</code></pre>
	</div>
	<div class="card">
	<h3>ONNX Graph Export</h3>
	<p>Export Tensor-Train linear layers to ONNX for edge runtime acceleration:</p>
	<pre><code>python export_onnx.py \
	--output qtensorformer.onnx \
	--batch_size 1 \
	--seq_len 32</code></pre>
	</div>
	</div>
	</section>

	<section>
	<h2>5. Running Unit Tests & Smoke Tests</h2>
	<p>Verify that your environment matches our benchmark findings:</p>
	<pre><code># Run full pytest suite (94 passing tests)
	pytest -v

	# Run deterministic smoke test
	python scripts/smoke_test.py</code></pre>
	</section>
	</main>

	<footer>
	<div class="footer-links">
	<a href="index.html">Home</a>
	<a href="architecture.html">Architecture</a>
	<a href="methodology.html">Methodology</a>
	<a href="benchmarks.html">Benchmarks</a>
	<a href="documentation.html">Docs</a>
	<a href="limitations.html">Limitations</a>
	<a href="sitemap.xml">Sitemap</a>
	<a href="llms.txt">llms.txt</a>
	<a href="https://huggingface.co/Premchan369/Q-TensorFormer">Hugging Face</a>
	</div>
	<p>© 2026 Premchand Yadav. Licensed under Apache-2.0.</p>
	</footer>
	</body>
	</html>