bartowski's picture
Llamacpp quants
6ec3134 verified
metadata
language:
  - en
license: apache-2.0
tags:
  - open-source
  - code
  - math
  - chemistry
  - biology
  - text-generation
  - question-answering
datasets:
  - Locutusque/OpenCerebrum-dpo
pipeline_tag: text-generation
quantized_by: bartowski

Llamacpp Quantizations of OpenCerebrum-1.0-7b-DPO

Using llama.cpp release b2536 for quantization.

Original model: https://huggingface.co./Locutusque/OpenCerebrum-1.0-7b-DPO

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

Filename Quant type File Size Description
OpenCerebrum-1.0-7b-DPO-Q8_0.gguf Q8_0 7.69GB Extremely high quality, generally unneeded but max available quant.
OpenCerebrum-1.0-7b-DPO-Q6_K.gguf Q6_K 5.94GB Very high quality, near perfect, recommended.
OpenCerebrum-1.0-7b-DPO-Q5_K_M.gguf Q5_K_M 5.13GB High quality, very usable.
OpenCerebrum-1.0-7b-DPO-Q5_K_S.gguf Q5_K_S 4.99GB High quality, very usable.
OpenCerebrum-1.0-7b-DPO-Q5_0.gguf Q5_0 4.99GB High quality, older format, generally not recommended.
OpenCerebrum-1.0-7b-DPO-Q4_K_M.gguf Q4_K_M 4.36GB Good quality, uses about 4.83 bits per weight.
OpenCerebrum-1.0-7b-DPO-Q4_K_S.gguf Q4_K_S 4.14GB Slightly lower quality with small space savings.
OpenCerebrum-1.0-7b-DPO-IQ4_NL.gguf IQ4_NL 4.15GB Decent quality, similar to Q4_K_S, new method of quanting,
OpenCerebrum-1.0-7b-DPO-IQ4_XS.gguf IQ4_XS 3.94GB Decent quality, new method with similar performance to Q4.
OpenCerebrum-1.0-7b-DPO-Q4_0.gguf Q4_0 4.10GB Decent quality, older format, generally not recommended.
OpenCerebrum-1.0-7b-DPO-Q3_K_L.gguf Q3_K_L 3.82GB Lower quality but usable, good for low RAM availability.
OpenCerebrum-1.0-7b-DPO-Q3_K_M.gguf Q3_K_M 3.51GB Even lower quality.
OpenCerebrum-1.0-7b-DPO-IQ3_M.gguf IQ3_M 3.28GB Medium-low quality, new method with decent performance.
OpenCerebrum-1.0-7b-DPO-IQ3_S.gguf IQ3_S 3.18GB Lower quality, new method with decent performance, recommended over Q3 quants.
OpenCerebrum-1.0-7b-DPO-Q3_K_S.gguf Q3_K_S 3.16GB Low quality, not recommended.
OpenCerebrum-1.0-7b-DPO-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