README.md

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
  - microsoft/orca-math-word-problems-200k
language:
  - en
license: bigcode-openrail-m
quantized_by: bartowski
pipeline_tag: text-generation

Llamacpp Quantizations of dolphincoder-starcoder2-7b

Using llama.cpp release b2354 for quantization.

Original model: https://huggingface.co/cognitivecomputations/dolphincoder-starcoder2-7b

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

Filename	Quant type	File Size	Description
dolphincoder-starcoder2-7b-Q8_0.gguf	Q8_0	7.86GB	Extremely high quality, generally unneeded but max available quant.
dolphincoder-starcoder2-7b-Q6_K.gguf	Q6_K	6.07GB	Very high quality, near perfect, recommended.
dolphincoder-starcoder2-7b-Q5_K_M.gguf	Q5_K_M	5.31GB	High quality, very usable.
dolphincoder-starcoder2-7b-Q5_K_S.gguf	Q5_K_S	5.12GB	High quality, very usable.
dolphincoder-starcoder2-7b-Q5_0.gguf	Q5_0	5.12GB	High quality, older format, generally not recommended.
dolphincoder-starcoder2-7b-Q4_K_M.gguf	Q4_K_M	4.58GB	Good quality, similar to 4.25 bpw.
dolphincoder-starcoder2-7b-Q4_K_S.gguf	Q4_K_S	4.31GB	Slightly lower quality with small space savings.
dolphincoder-starcoder2-7b-Q4_0.gguf	Q4_0	4.22GB	Decent quality, older format, generally not recommended.
dolphincoder-starcoder2-7b-Q3_K_L.gguf	Q3_K_L	4.17GB	Lower quality but usable, good for low RAM availability.
dolphincoder-starcoder2-7b-Q3_K_M.gguf	Q3_K_M	3.78GB	Even lower quality.
dolphincoder-starcoder2-7b-Q3_K_S.gguf	Q3_K_S	3.27GB	Low quality, not recommended.
dolphincoder-starcoder2-7b-Q2_K.gguf	Q2_K	2.91GB	Extremely low quality, not recommended.

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