Instructions to use scrallex/structural-manifold-compression with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use scrallex/structural-manifold-compression with Transformers:

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

pipe = pipeline("text-generation", model="scrallex/structural-manifold-compression")

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

tokenizer = AutoTokenizer.from_pretrained("scrallex/structural-manifold-compression")
model = AutoModelForCausalLM.from_pretrained("scrallex/structural-manifold-compression", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use scrallex/structural-manifold-compression with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/scrallex/structural-manifold-compression

SGLang

How to use scrallex/structural-manifold-compression 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 "scrallex/structural-manifold-compression" \
    --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": "scrallex/structural-manifold-compression",
		"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 "scrallex/structural-manifold-compression" \
        --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": "scrallex/structural-manifold-compression",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use scrallex/structural-manifold-compression with Docker Model Runner:
```
docker model run hf.co/scrallex/structural-manifold-compression
```

scrallex commited on Nov 6, 2025

Commit

fc4ef52

1 Parent(s): 1a223ca

Highlight structured quick start and upcoming Space

Browse files

Files changed (1) hide show

README.md +18 -0

README.md CHANGED Viewed

@@ -29,6 +29,24 @@ Use this repo if you want to **benchmark manifold LMs** or integrate the encoder
 ---
 ## Latest Benchmarks (2025-11-05)
 All evaluations ran on a single RTX 3080 Ti (12 GB) with the same environment as the training run. The raw artifacts referenced below are stored in `benchmarks/`.

 ---
+## Quick Start & Best-Case Workloads
+- **Optimised for structured text**: PDF/page OCR exports, news briefs, technical audits—any corpus where 512 B sliding windows capture repeated structure. Expect 30–60× token compression with 94–95 % token accuracy (Fox EN/CN/OmniDoc numbers from the main repo).
+- **Reproduce on a sample corpus**:
+  ```bash
+  git clone https://github.com/SepDynamics/structural-manifold-compression.git
+  cd structural-manifold-compression
+  python scripts/experiments/benchmark_eval.py \
+    --dataset briefs=examples/structured_demo/news_sample.jsonl \
+    --json-text-key text \
+    --window-bytes 512 --stride-bytes 384 --precision 3 \
+    --use-native \
+    --output-dir output/benchmark_runs/news_demo
+  ```
+  Inspect `output/benchmark_runs/news_demo/briefs.json` for compression, fidelity, and verification stats, then replace `news_sample.jsonl` with your own JSONL dumps.
+- **Future Hugging Face Space**: a Gradio front-end (planned) will wrap the same workflow so newcomers can upload JSONL/txt, run compression, and view reconstructions/verification without installing CUDA.
+---
 ## Latest Benchmarks (2025-11-05)
 All evaluations ran on a single RTX 3080 Ti (12 GB) with the same environment as the training run. The raw artifacts referenced below are stored in `benchmarks/`.