Sakalti
/

tara-3.8B

Text Generation

text-generation-inference

Model card Files Files and versions

Uploaded model

Developed by: Sakalti
License: mit
Finetuned from model : unsloth/Phi-3.5-mini-instruct

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

Downloads last month: 1

Safetensors

Model size

4B params

Tensor type

F16

·

Model tree for Sakalti/tara-3.8B

Base model

microsoft/Phi-3.5-mini-instruct

Finetuned

unsloth/Phi-3.5-mini-instruct

Finetuned

(110)

this model

Finetunes

1 model

Quantizations

1 model

Dataset used to train Sakalti/tara-3.8B