mradermacher's picture
auto-patch README.md
d2d5d4c verified
metadata
base_model: ibm-granite/granite-20b-code-instruct-r1.1
datasets:
  - bigcode/commitpackft
  - TIGER-Lab/MathInstruct
  - meta-math/MetaMathQA
  - glaiveai/glaive-code-assistant-v3
  - glaive-function-calling-v2
  - bugdaryan/sql-create-context-instruction
  - garage-bAInd/Open-Platypus
  - nvidia/HelpSteer
  - bigcode/self-oss-instruct-sc2-exec-filter-50k
language:
  - en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
  - code
  - granite

About

static quants of https://huggingface.co/ibm-granite/granite-20b-code-instruct-r1.1

weighted/imatrix quants are available at https://huggingface.co/mradermacher/granite-20b-code-instruct-r1.1-i1-GGUF

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link Type Size/GB Notes
GGUF Q2_K 8.0
GGUF Q3_K_S 9.0
GGUF Q3_K_M 10.7 lower quality
GGUF IQ4_XS 11.2
GGUF Q4_K_S 11.8 fast, recommended
GGUF Q3_K_L 11.8
GGUF Q4_K_M 12.9 fast, recommended
GGUF Q5_K_S 14.1
GGUF Q5_K_M 14.9
GGUF Q6_K 16.7 very good quality
GGUF Q8_0 21.6 fast, best quality

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

image.png

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.