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 / scripts /run_reasoning_benchmark.py

Premchandyadav369

feat: real-world production pillars, OpenAI streaming API, and reasoning benchmarks

000c57b 7 days ago

Raw History Blame Contribute Delete

1.55 kB

#!/usr/bin/env python3
"""
scripts/run_reasoning_benchmark.py
Executes multi-step reasoning token complexity evaluation across mathematical,
algorithmic, and logical sequences. Dumps JSON telemetry to results/raw/.
"""

import sys
import json
from pathlib import Path
from dataclasses import asdict

ROOT_DIR = Path(__file__).resolve().parent.parent
if str(ROOT_DIR) not in sys.path:
    sys.path.insert(0, str(ROOT_DIR))

from src.reasoning_benchmark import ReasoningComplexityAnalyzer


def main():
    print("=" * 70)
    print("Q-TensorFormer: Real-World Reasoning Token Complexity Benchmark")
    print("=" * 70)

    analyzer = ReasoningComplexityAnalyzer()
    results = analyzer.run_all_benchmarks()

    output_data = []
    for r in results:
        print(f"\n[Problem]: {r.problem_name}")
        print(f"  Prompt Length:       {r.total_tokens} tokens")
        print(f"  Mean TT-Rank:        {r.mean_allocated_rank} (High: {r.high_rank_tokens_count}, Low: {r.low_rank_tokens_count})")
        print(f"  DRAM Memory Saved:   {r.dram_savings_pct:.2f}%")
        print(f"  Accuracy Retention:  {r.accuracy_retention_pct:.2f}%")
        output_data.append(asdict(r))

    out_path = ROOT_DIR / "results" / "raw" / "reasoning_token_complexity.json"
    out_path.parent.mkdir(parents=True, exist_ok=True)
    with open(out_path, "w", encoding="utf-8") as f:
        json.dump(output_data, f, indent=2)

    print(f"\n[SUCCESS] Dumped reasoning benchmark telemetry to: {out_path}")
    print("=" * 70)


if __name__ == "__main__":
    main()

	#!/usr/bin/env python3
	"""
	scripts/run_reasoning_benchmark.py

	Executes multi-step reasoning token complexity evaluation across mathematical,
	algorithmic, and logical sequences. Dumps JSON telemetry to results/raw/.
	"""

	import sys
	import json
	from pathlib import Path
	from dataclasses import asdict

	ROOT_DIR = Path(__file__).resolve().parent.parent
	if str(ROOT_DIR) not in sys.path:
	sys.path.insert(0, str(ROOT_DIR))

	from src.reasoning_benchmark import ReasoningComplexityAnalyzer


	def main():
	print("=" * 70)
	print("Q-TensorFormer: Real-World Reasoning Token Complexity Benchmark")
	print("=" * 70)

	analyzer = ReasoningComplexityAnalyzer()
	results = analyzer.run_all_benchmarks()

	output_data = []
	for r in results:
	print(f"\n[Problem]: {r.problem_name}")
	print(f" Prompt Length: {r.total_tokens} tokens")
	print(f" Mean TT-Rank: {r.mean_allocated_rank} (High: {r.high_rank_tokens_count}, Low: {r.low_rank_tokens_count})")
	print(f" DRAM Memory Saved: {r.dram_savings_pct:.2f}%")
	print(f" Accuracy Retention: {r.accuracy_retention_pct:.2f}%")
	output_data.append(asdict(r))

	out_path = ROOT_DIR / "results" / "raw" / "reasoning_token_complexity.json"
	out_path.parent.mkdir(parents=True, exist_ok=True)
	with open(out_path, "w", encoding="utf-8") as f:
	json.dump(output_data, f, indent=2)

	print(f"\n[SUCCESS] Dumped reasoning benchmark telemetry to: {out_path}")
	print("=" * 70)


	if __name__ == "__main__":
	main()