Instructions to use embedme/lightonai-denseon-Q8_0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use embedme/lightonai-denseon-Q8_0 with sentence-transformers:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("embedme/lightonai-denseon-Q8_0")

sentences = [
    "That is a happy person",
    "That is a happy dog",
    "That is a very happy person",
    "Today is a sunny day"
]
embeddings = model.encode(sentences)

similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4]

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use embedme/lightonai-denseon-Q8_0 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf embedme/lightonai-denseon-Q8_0:Q8_0
# Run inference directly in the terminal:
llama cli -hf embedme/lightonai-denseon-Q8_0:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf embedme/lightonai-denseon-Q8_0:Q8_0
# Run inference directly in the terminal:
llama cli -hf embedme/lightonai-denseon-Q8_0:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf embedme/lightonai-denseon-Q8_0:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf embedme/lightonai-denseon-Q8_0:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf embedme/lightonai-denseon-Q8_0:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf embedme/lightonai-denseon-Q8_0:Q8_0

Use Docker

docker model run hf.co/embedme/lightonai-denseon-Q8_0:Q8_0

LM Studio
Jan
Ollama
How to use embedme/lightonai-denseon-Q8_0 with Ollama:
```
ollama run hf.co/embedme/lightonai-denseon-Q8_0:Q8_0
```

Unsloth Studio

How to use embedme/lightonai-denseon-Q8_0 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for embedme/lightonai-denseon-Q8_0 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for embedme/lightonai-denseon-Q8_0 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for embedme/lightonai-denseon-Q8_0 to start chatting

Docker Model Runner
How to use embedme/lightonai-denseon-Q8_0 with Docker Model Runner:
```
docker model run hf.co/embedme/lightonai-denseon-Q8_0:Q8_0
```

Lemonade

How to use embedme/lightonai-denseon-Q8_0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull embedme/lightonai-denseon-Q8_0:Q8_0

Run and chat with the model

lemonade run user.lightonai-denseon-Q8_0-Q8_0

List all available models

lemonade list

Atomic Chat

ctrltokyo commited on 24 days ago

Commit

febe768

verified ·

1 Parent(s): 9da2632

Publish DenseOn Q8_0 from cb9947e

Browse files

Converted with llama.cpp 6eddde0; preserves native CLS pooling and verified litembeddings usage.

Files changed (3) hide show

.gitattributes +1 -0
DenseOn-Q8_0.gguf +3 -0
README.md +58 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+DenseOn-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

DenseOn-Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:506d5bab02a4adf7c00a71fef2bb58bfa54f769e15670886e212af7c16b4ccff
+size 160208288

README.md ADDED Viewed

	@@ -0,0 +1,58 @@

+---
+base_model: lightonai/DenseOn
+library_name: litembeddings
+license: apache-2.0
+language:
+- en
+pipeline_tag: sentence-similarity
+tags:
+- gguf
+- litembeddings
+- modernbert
+- sentence-transformers
+- dense-retrieval
+- feature-extraction
+- quantized
+---
+# DenseOn Q8_0 for litembeddings
+A Q8_0 GGUF conversion of [lightonai/DenseOn](https://huggingface.co/lightonai/DenseOn), a 149M-parameter ModernBERT dense retrieval model. DenseOn emits one 768-dimensional, L2-normalized vector using CLS pooling and was trained with asymmetric query/document prefixes.
+## Files
+| File | Purpose | SHA-256 |
+|---|---|---|
+| `DenseOn-Q8_0.gguf` | Q8_0 ModernBERT encoder with native CLS pooling metadata | `506d5bab02a4adf7c00a71fef2bb58bfa54f769e15670886e212af7c16b4ccff` |
+## litembeddings usage
+```sql
+.load ./litembeddings
+SELECT lembed_model(
+  '/path/to/DenseOn-Q8_0.gguf',
+  json_object('ctx_size', 512, 'batch_size', 512)
+);
+-- Prefixes are required by DenseOn's training contract.
+SELECT lembed('query: best database indexing strategy');
+SELECT lembed('document: covering indexes can avoid table lookups');
+```
+Use `query: ` for queries and `document: ` for corpus passages. Omitting or swapping these prefixes can reduce retrieval quality. The source model's maximum sequence length is 512 tokens.
+## Conversion provenance
+- Source: [`lightonai/DenseOn`](https://huggingface.co/lightonai/DenseOn)
+- Source revision: `cb9947ebccb33862d24e3c7ca2edb25e51acd887`
+- Converted: 2026-07-14
+- llama.cpp revision: `6eddde06a4f25d55d538b5d15628dcc2b6882147`
+- Quantization: Q8_0
+- Pooling: native CLS pooling from sentence-transformers metadata
+An end-to-end parity check against the source FP32 Transformers pipeline produced cosine similarity `0.999389` for the validation query. Small differences are expected from Q8_0 quantization.
+## License and attribution
+The source model is released under Apache 2.0. See the [DenseOn model card](https://huggingface.co/lightonai/DenseOn) for training details, evaluation results, intended use, limitations, and citation information. This repository is an independent conversion and is not affiliated with LightOn.