qwp4w3hyb's picture
Update README.md
7ce04f8 verified
|
raw
history blame
899 Bytes
metadata
base_model: Nexusflow/Starling-LM-7B-beta
datasets:
  - berkeley-nest/Nectar
language:
  - en
library_name: transformers
tags:
  - starling
  - reward model
  - RLHF
  - RLAIF
model-index:
  - name: Nexusflow/Starling-LM-7B-beta-iMat-GGUF
    results: []
license: apache-2.0

Starling-LM-7B-beta-iMat-GGUF

Source Model: Nexusflow/Starling-LM-7B-beta

Quantized with llama.cpp commit 46acb3676718b983157058aecf729a2064fc7d34

Imatrix was generated from the f16 gguf via this command:

./imatrix -c 512 -m $out_path/$base_quant_name -f $llama_cpp_path/groups_merged.txt -o $out_path/imat-f16-gmerged.dat

Using the dataset from here