Flora_7B-GGUF / README.md
bartowski's picture
Llamacpp quants
615bb8a verified
metadata
base_model:
  - jeiku/FloraBase
  - jeiku/Synthetic_Soul_1k_Mistral_128
library_name: transformers
tags:
  - finetune
license: cc-by-sa-4.0
datasets:
  - ResplendentAI/Synthetic_Soul_1k
language:
  - en
quantized_by: bartowski
pipeline_tag: text-generation

Llamacpp Quantizations of Flora_7B

Using llama.cpp release b2334 for quantization.

Original model: https://huggingface.co/ResplendentAI/Flora_7B

Download a file (not the whole branch) from below:

Filename Quant type File Size Description
Flora_7B-Q8_0.gguf Q8_0 7.69GB Extremely high quality, generally unneeded but max available quant.
Flora_7B-Q6_K.gguf Q6_K 5.94GB Very high quality, near perfect, recommended.
Flora_7B-Q5_K_M.gguf Q5_K_M 5.13GB High quality, very usable.
Flora_7B-Q5_K_S.gguf Q5_K_S 4.99GB High quality, very usable.
Flora_7B-Q5_0.gguf Q5_0 4.99GB High quality, older format, generally not recommended.
Flora_7B-Q4_K_M.gguf Q4_K_M 4.36GB Good quality, similar to 4.25 bpw.
Flora_7B-Q4_K_S.gguf Q4_K_S 4.14GB Slightly lower quality with small space savings.
Flora_7B-Q4_0.gguf Q4_0 4.10GB Decent quality, older format, generally not recommended.
Flora_7B-Q3_K_L.gguf Q3_K_L 3.82GB Lower quality but usable, good for low RAM availability.
Flora_7B-Q3_K_M.gguf Q3_K_M 3.51GB Even lower quality.
Flora_7B-Q3_K_S.gguf Q3_K_S 3.16GB Low quality, not recommended.
Flora_7B-Q2_K.gguf Q2_K 2.71GB Extremely low quality, not recommended.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski