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")

# 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
```

structural-manifold-compression / benchmarks /wikitext_structural_20k.json

scrallex

Add wikitext structural/perplexity benchmarks

1a223ca 10 months ago

Raw

History Blame Contribute Delete

1.17 kB

	{
	"source": "structural-manifold-compression/output/benchmark_runs/wikitext_quick_20k/wikitext.json",
	"generated_at": "2025-11-06T06:05:39.483192+00:00",
	"documents": 12894,
	"records": 21234,
	"window_bytes": 512,
	"stride_bytes": 384,
	"precision": 3,
	"byte_metrics": {
	"original_size_bytes": 5880678,
	"compressed_size_bytes": 191034,
	"compression_ratio": 30.783410282986274
	},
	"token_metrics": {
	"token_accuracy": 0.8367166332748543,
	"token_precision": 0.8367166332748543,
	"token_recall": 0.8048828140142499,
	"token_f1": 0.8204910636817365,
	"token_compression_stream": 60.743618724686826,
	"token_compression_unique": 60.76651276736079,
	"text_tokens_total": 1289830,
	"reconstructed_tokens_total": 1541296
	},
	"character_metrics": {
	"character_accuracy": 0.8354988184380605,
	"normalized_edit_distance": 0.16450118156193946
	},
	"verification": {
	"precision": 0.17765469696462635,
	"false_positive_rate": 0.00023145642541616578,
	"recall": 1.0
	},
	"shared_signatures": 3737,
	"notes": {
	"non_empty_documents": 12894,
	"negatives_evaluated": 424658766,
	"use_native": true
	}
	}