SQ

sqlite lembed model examples

SqliteGGUF by asg017Updated 2024-08-25
Download on Hugging Face
Parameters23M
Context512
Layers6
Architecturebert
Smallest quant0.0 GB
Quick answer

sqlite lembed model examples needs about 0.7 GB of memory at F32 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 0.0 GB (Q8_0) to 0.4 GB (F32).

Lightweight BERT embedding model for quick inference

The sqlite lembed model examples is a 0.0226B BERT-based embedding model. It supports a 512 token context window and is optimized for low memory usage. The model is released under the MIT license.

Good at

  • Embedding generation
  • Lightweight inference
  • Low VRAM usage

Limits

  • 512 token context only
  • No vision support
  • MIT license only

Best for

  • Text similarity tasks
  • Semantic search
  • Embedding-based clustering

Who it’s for. Developers needing quick embedding generation on limited hardware. Suitable for edge devices or small servers.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.0 GB 0.5 GB
Fits Get file →
BF160.0 GB 0.6 GB
Fits Get file →
F160.0 GB 0.6 GB
Fits Get file →
F320.1 GB 0.6 GB
Fits Get file →
Q8_00.1 GB 0.6 GB
Fits Get file →
BF160.2 GB 0.7 GB
Fits Get file →
F160.2 GB 0.7 GB
Fits Get file →
F320.4 GB 0.9 GB
Fits Get file →

For 0.5 GB VRAM, use Q8_0 (0.03 GB file, ~0.6 GB memory). For 1 GB VRAM, F32 (0.09 GB file, ~0.7 GB memory) is a good choice. Larger VRAM allows any quant, but smaller files reduce load time.

What GPU do you need for sqlite lembed model examples?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is F32 (0.4 GB file, about 1.0 GB in use).

Which sqlite lembed model examples quant should you choose?

F32 (0.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is Q8_0 at 0.0 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturebert
Parameters23M
Layers6
Trained context512 tokens
KV cache (fp16)9 KB per token

Source

Quantized byasg017
FamilySqlite
Licensemit
Downloads (HF)604
Last updated2024-08-25

Frequently asked questions about sqlite lembed model examples

How much VRAM does sqlite lembed model examples need?

About 0.7 GB at F32 with an 8K context window. That is the 0.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run sqlite lembed model examples on an 8 GB GPU?

Yes, with F32: the 0.4 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of sqlite lembed model examples GGUF?

It depends on the quant: Q8_0 is 0.0 GB, BF16 is 0.0 GB, F16 is 0.0 GB, F32 is 0.1 GB, Q8_0 is 0.1 GB, BF16 is 0.2 GB and 2 more.

What context length does sqlite lembed model examples support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 512.

Where can I download sqlite lembed model examples GGUF?

The files are on Hugging Face in the asg017/sqlite-lembed-model-examples repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does sqlite lembed model examples use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 0.5 GB VRAM?

Yes, the Q8_0 quant uses 0.03 GB file size and requires about 0.6 GB memory at 8k context.

Does it support multilingual embeddings?

No languages are listed, so multilingual support is not guaranteed.

Is it compatible with llama.cpp?

Yes, the model is available in GGUF format for llama.cpp.

Similar models

Browse all →

More Sqlite models

All Sqlite →

Other tiny models

All tiny models →