bartowski's picture
Llamacpp quants
d838827 verified
metadata
datasets:
  - cognitivecomputations/dolphin
  - jondurbin/airoboros-2.2.1
  - cognitivecomputations/dolphin-coder
  - teknium/openhermes
  - ise-uiuc/Magicoder-OSS-Instruct-75K
  - ise-uiuc/Magicoder-Evol-Instruct-110K
  - m-a-p/Code-Feedback
  - m-a-p/CodeFeedback-Filtered-Instruction
language:
  - en
license: bigcode-openrail-m
quantized_by: bartowski
pipeline_tag: text-generation

Llamacpp Quantizations of dolphincoder-starcoder2-15b

Using llama.cpp release b2354 for quantization.

Original model: https://huggingface.co/cognitivecomputations/dolphincoder-starcoder2-15b

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

Filename Quant type File Size Description
dolphincoder-starcoder2-15b-Q8_0.gguf Q8_0 16.96GB Extremely high quality, generally unneeded but max available quant.
dolphincoder-starcoder2-15b-Q6_K.gguf Q6_K 13.10GB Very high quality, near perfect, recommended.
dolphincoder-starcoder2-15b-Q5_K_M.gguf Q5_K_M 11.43GB High quality, very usable.
dolphincoder-starcoder2-15b-Q5_K_S.gguf Q5_K_S 11.02GB High quality, very usable.
dolphincoder-starcoder2-15b-Q5_0.gguf Q5_0 11.02GB High quality, older format, generally not recommended.
dolphincoder-starcoder2-15b-Q4_K_M.gguf Q4_K_M 9.86GB Good quality, similar to 4.25 bpw.
dolphincoder-starcoder2-15b-Q4_K_S.gguf Q4_K_S 9.25GB Slightly lower quality with small space savings.
dolphincoder-starcoder2-15b-Q4_0.gguf Q4_0 9.06GB Decent quality, older format, generally not recommended.
dolphincoder-starcoder2-15b-Q3_K_L.gguf Q3_K_L 8.96GB Lower quality but usable, good for low RAM availability.
dolphincoder-starcoder2-15b-Q3_K_M.gguf Q3_K_M 8.10GB Even lower quality.
dolphincoder-starcoder2-15b-Q3_K_S.gguf Q3_K_S 6.98GB Low quality, not recommended.
dolphincoder-starcoder2-15b-Q2_K.gguf Q2_K 6.19GB Extremely low quality, not recommended.

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