This models was using "yahma/alpaca-cleaned" This dataset is licensed under CC BY SA 4.0

Last Update : 2023-05-25

Uploaded model

  • Developed by: Sakalti
  • License: apache-2.0
  • Finetuned from model : Sakalti/Tara-3.8B-v1.1

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month
61
Safetensors
Model size
3.82B params
Tensor type
FP16
·
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 Sakalti/SJT-4B

Finetuned
Sakalti/tara-3.8B
Finetuned
(1)
this model
Quantizations
1 model

Datasets used to train Sakalti/SJT-4B