Hugging Face's logo

mradermacher
/
piano-medley-7b-i1-GGUF

Transformers
GGUF
English
Merge
mergekit
Inference Endpoints
imatrix
Model card Files Community
piano-medley-7b-i1-GGUF / README.md
mradermacher's picture
mradermacher
auto-patch README.md
64a4584 verified
preview code
|
raw
history blame
3.93 kB
metadata
base_model: chargoddard/piano-medley-7b
datasets:
  - pankajmathur/orca_mini_v1_dataset
  - openai/summarize_from_feedback
  - PygmalionAI/PIPPA
  - chargoddard/rpguild
  - lemonilia/LimaRP
  - PKU-Alignment/PKU-SafeRLHF
  - Intel/orca_dpo_pairs
  - allenai/ultrafeedback_binarized_cleaned
language:
  - en
library_name: transformers
license: cc-by-nc-4.0
quantized_by: mradermacher
tags:
  - merge
  - mergekit

About

weighted/imatrix quants of https://huggingface.co/chargoddard/piano-medley-7b

static quants are available at https://huggingface.co/mradermacher/piano-medley-7b-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 i1-IQ2_M 2.6
GGUF i1-Q2_K 2.8 IQ3_XXS probably better
GGUF i1-IQ3_XXS 2.9 lower quality
GGUF i1-Q3_K_S 3.3 IQ3_XS probably better
GGUF i1-Q3_K_M 3.6 IQ3_S probably better
GGUF i1-Q3_K_L 3.9 IQ3_M probably better
GGUF i1-IQ4_XS 4.0
GGUF i1-Q4_0 4.2 fast, low quality
GGUF i1-Q4_K_S 4.2 optimal size/speed/quality
GGUF i1-Q4_K_M 4.5 fast, recommended
GGUF i1-Q5_K_S 5.1
GGUF i1-Q5_K_M 5.2
GGUF i1-Q6_K 6.0 practically like static Q6_K

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. Additional thanks to @nicoboss for giving me access to his hardware for calculating the imatrix for these quants.