SE

sea-lion-7b-instruct-research

SeaGGUF by RichardErkhovUpdated 2024-05-31
Download on Hugging Face
Parameters7.5B
Context2K
Layers32
Architecturempt
Smallest quant3.3 GB
Quick answer

sea-lion-7b-instruct-research needs about 8.8 GB of memory at IQ3_M (a 4.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 10 quants, from 3.3 GB (Q2_K) to 4.6 GB (Q3_K_L).

sea-lion-7b-instruct-research is a 7.5B-parameter Sea model in GGUF format, quantized by RichardErkhov. Its trained context length is 2K tokens. The repository has 10 quant files, from 3.3 GB (Q2_K) to 4.6 GB (Q3_K_L).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.3 GB 4.9 GB
Fits Get file →
IQ3_XS3.6 GB 5.2 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
Q3_K_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M4.0 GB 5.6 GB
Fits Get file →
Q3_K4.3 GB 5.8 GB
Fits Get file →
Q3_K_M4.3 GB 5.8 GB
Fits Get file →
IQ4_XS4.4 GB 5.9 GB
Fits Get file →
Q4_04.5 GB 6.1 GB
Fits Get file →
Q3_K_L4.6 GB 6.2 GB
Fits Get file →

What GPU do you need for sea-lion-7b-instruct-research?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q3_K_L (4.6 GB file, about 9.4 GB in use).

Which sea-lion-7b-instruct-research quant should you choose?

IQ3_M (4.0 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is Q2_K at 3.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturempt
Parameters7.5B
Layers32
Trained context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized byRichardErkhov
FamilySea
Downloads (HF)134
Last updated2024-05-31

Frequently asked questions about sea-lion-7b-instruct-research

How much VRAM does sea-lion-7b-instruct-research need?

About 8.8 GB at IQ3_M with an 8K context window. That is the 4.0 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 sea-lion-7b-instruct-research on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of sea-lion-7b-instruct-research GGUF?

It depends on the quant: Q2_K is 3.3 GB, IQ3_XS is 3.6 GB, IQ3_S is 3.7 GB, Q3_K_S is 3.7 GB, IQ3_M is 4.0 GB, Q3_K is 4.3 GB and 4 more.

What context length does sea-lion-7b-instruct-research support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.

Where can I download sea-lion-7b-instruct-research GGUF?

The files are on Hugging Face in the RichardErkhov/aisingapore_-_sea-lion-7b-instruct-research-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Sea models

All Sea →

Other small models

All small models →