Tara-3.8B-v1.1 / README.md
Sakalti's picture
Upload model trained with Unsloth
bc3c6b7 verified
|
raw
history blame
560 Bytes
metadata
base_model: Sakalti/tara-3.8B
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - sft
license: apache-2.0
language:
  - en

Uploaded model

  • Developed by: Sakalti
  • License: apache-2.0
  • Finetuned from model : Sakalti/tara-3.8B

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