Uploaded model

  • Developed by: IBM
  • Quantized by: sroecker
  • License: apache-2.0
  • Derived from model : ibm/merlinite-7b

This is just a quantized 4bit version created for further fine-tuning.

Downloads last month
4
Safetensors
Model size
3.86B params
Tensor type
F32
BF16
U8
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for sroecker/merlinite-7b-bnb-4bit

Finetuned
ibm/merlinite-7b
Quantized
(8)
this model