LL

llama 2 7b chat tagalog v0.3a

LlamaGGUF by 922-NarraUpdated 2023-09-02
Download on Hugging Face
Parameters6.74B
Context2K
Layers—
Architecturellama
Smallest quant4.2 GB
Quick answer

llama 2 7b chat tagalog v0.3a needs about 6.2 GB of memory at Q5_1 (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 4.2 GB (Q4_1) to 7.1 GB (Q8_0).

llama 2 7b chat tagalog v0.3a is a 6.74B-parameter Llama model in GGUF format, quantized by 922-Narra. Its trained context length is 2K tokens. The repository has 3 quant files, from 4.2 GB (Q4_1) to 7.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_14.2 GB 4.9 GB
Fits Get file →
Q5_15.1 GB 5.7 GB
Fits Get file →
Q8_07.1 GB 7.8 GB
Tight Get file →

What GPU do you need for llama 2 7b chat tagalog v0.3a?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q4_1 (4.2 GB file, about 5.2 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_1 (5.1 GB file, about 6.2 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.1 GB file, about 8.5 GB in use).

Which llama 2 7b chat tagalog v0.3a quant should you choose?

Q5_1 (5.1 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q4_1 at 4.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Trained context2,048 tokens

Source

Quantized by922-Narra
FamilyLlama
Licensellama2
Downloads (HF)106
Last updated2023-09-02

Frequently asked questions about llama 2 7b chat tagalog v0.3a

How much VRAM does llama 2 7b chat tagalog v0.3a need?

About 6.2 GB at Q5_1 with an 8K context window. That is the 5.1 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 llama 2 7b chat tagalog v0.3a on an 8 GB GPU?

Yes, with Q5_1: the 5.1 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of llama 2 7b chat tagalog v0.3a GGUF?

It depends on the quant: Q4_1 is 4.2 GB, Q5_1 is 5.1 GB, Q8_0 is 7.1 GB.

What context length does llama 2 7b chat tagalog v0.3a support?

The GGUF header lists a trained context length of 2,048 tokens (2K).

Where can I download llama 2 7b chat tagalog v0.3a GGUF?

The files are on Hugging Face in the 922-Narra/llama-2-7b-chat-tagalog-v0.3a-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does llama 2 7b chat tagalog v0.3a use?

Hugging Face lists the license as llama2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from 922-Narra

All by 922-Narra →

More Llama models

All Llama →

Other small models

All small models →